U.S. patent application number 11/725514 was filed with the patent office on 2007-09-20 for method and system for continuous monitoring and training of exercise.
Invention is credited to Mark H. Schwartz, Hong Wang, Le Yi Wang.
Application Number | 20070219059 11/725514 |
Document ID | / |
Family ID | 38518657 |
Filed Date | 2007-09-20 |
United States Patent
Application |
20070219059 |
Kind Code |
A1 |
Schwartz; Mark H. ; et
al. |
September 20, 2007 |
Method and system for continuous monitoring and training of
exercise
Abstract
A method and system is invented for continuous monitoring,
real-time analysis, and automated and personalized training of
exercise. The system embodies a multi-sensor data acquisition
system to measure body sounds, body signs, vital signs, motions,
and machine settings continuously and automatically. The system is
able to capture the body sounds and other vital signs, analyze
them, and report and display summarized results. The signal
processing functions utilize a unique signal separation and noise
removal methodology by which authentic signals can be extracted
from interfered signals and in noisy environments, even when
signals and noises have similar frequency components or are
statistically dependent. The method and system will facilitate
continuous monitoring, real-time analysis, and computerized
evaluation of level of effort, physical stress, and resulting
fatigue during physical activity or exercise. In addition, based on
body sound data, or in combination with other monitored
physiological signals, and knowledge of the individual and exercise
being performed, the system will evaluate the person's physical
performance and then act as an automated coach to guide exercise
intensity and duration thereby optimizing and individualizing the
training process. The invention is especially targeted, but not
limited to, cardiopulmonary monitoring for athletes for improving
the efficiency and safety of exercise, rehabilitation programs for
out-of-shape individuals, and routine exercise of the general
population.
Inventors: |
Schwartz; Mark H.; (Livonia,
MI) ; Wang; Le Yi; (Novi, MI) ; Wang;
Hong; (Novi, MI) |
Correspondence
Address: |
Mark H. Schwartz
18421 Laurel Drive
Livonia
MI
48152
US
|
Family ID: |
38518657 |
Appl. No.: |
11/725514 |
Filed: |
March 19, 2007 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
60783424 |
Mar 17, 2006 |
|
|
|
Current U.S.
Class: |
482/8 ;
482/1 |
Current CPC
Class: |
A61B 7/003 20130101;
A63B 2230/42 20130101; A63B 24/0062 20130101; A63B 2071/0627
20130101; A63B 2230/04 20130101; A63B 2230/43 20130101; A61B 5/0205
20130101; A63B 24/0084 20130101; A63B 2225/20 20130101; A63B
2220/40 20130101; A63B 24/0075 20130101; A61B 5/318 20210101; A61B
5/7203 20130101; A63B 2024/0068 20130101; A63B 71/0622 20130101;
A63B 2220/20 20130101; A63B 69/16 20130101; A63B 2225/10 20130101;
A61B 7/04 20130101; A63B 22/02 20130101; A63B 2022/0658 20130101;
G16H 20/30 20180101; A63B 2220/13 20130101; A61B 5/02405 20130101;
A63B 21/0628 20151001; A63B 2225/54 20130101; G06F 1/1626 20130101;
A63B 2225/15 20130101; A63B 22/0664 20130101; A63B 2022/0652
20130101; A61B 5/721 20130101; A63B 22/0605 20130101; A63B 2225/50
20130101; A63B 2230/06 20130101; A63B 2220/17 20130101 |
Class at
Publication: |
482/8 ;
482/1 |
International
Class: |
A63B 15/02 20060101
A63B015/02; A63B 71/00 20060101 A63B071/00 |
Claims
1. A method for automating exercise monitoring and training,
comprising: a. capturing sensor signals of body sounds and vital
signs and noises from a plurality of target locations, and removing
off-band and statistically independent noises; b. performing
adaptive individualized noise cancellation which further reduces
noises; c. performing a signal separation process which extracts
authentic signals by reducing or eliminating signal interferences;
and d. performing pattern recognition to derive characteristic
parameters and patterns with their values, and their trends along
with quality ratings of these quantities.
2. The method of claim 1 wherein the multiple pulmonary-related
sound signals and their derived parameters and patterns such as
respiratory rates, respiratory rate variations, lung sound
frequency spectrum are combined with cardio-related sound signals
and patterns such as heart sounds, heart rates, heart rate
variability to jointly characterize a person's cardiopulmonary
functions and activity levels.
3. The method of claim 1 wherein: a. the sensor signals of body
sounds and noises from a plurality of target locations are captured
such that the distributed background noises can be approximated as
lumped noise sources, off-band noises are filtered by pre-filters,
and statistically independent noises are separated from useful
signals by adaptive noise cancellation methods; and then removed;
b. the adaptive individualized noise cancellation is performed by
reducing noises that may have overlapping frequency components with
the target signals or is statistically correlated with the target
signals, whereby in-band and statistically correlated noises are
separated by time-shared adaptive noise cancellation methods; c.
the signal separation process which identifies the signal
transmission channels iteratively and individually, separates
interfered signals cyclically, and extracts authentic signals in
real-time, all by using the cyclic system reconfiguration and
signal separation methods; whereby target signals from multiple
body signal sources that characterize body reaction to exercise and
that have similar stochastic and frequency features are physically
separated both from each other and also from extraneous sources of
noise that may be statistically correlated with or have overlapping
frequency components with the target signals, and d. the pattern
recognition process is performed wherein the authentic signals
obtained by said processing of background noise removal and signal
interference reduction are further processed to derive
characteristic parameters and patterns with their values, their
trends along with quality ratings of these quantities in terms of
statistical confidence criteria, all these are performed
iteratively, adaptively, and individually in real time.
4. The method of claim 3 wherein said body signal sensors are
acoustic sensors and for example measure heart and lung and airway
sounds.
5. The method of claim 2 wherein said body sound sensors for
respiratory and cardio functions further comprise additional body
sign and vital sign sensors such as chest movement sensors to
measure volume changes in chest and abdomen, oximetry sensors for
measuring blood oxygen concentrations, and EKG for heart functions.
The expanded set of signals is jointly processed with
functionalities as in the method of claim 1 for sound signals that
include: a. removing off-band noises with pre-filtering and
removing statistically independent noises by adaptive noise
cancellation; b. removing in-band and statistically dependent
noises by the time-shared adaptive noise cancellation methods; c.
separating authentic signals from signal interference by the
adaptive and individualized cyclic signal separation methods; d.
performing adaptive and individualized parameter and pattern
extraction to derive characteristic parameters and patterns with
their values, their trend along with quality ratings of these
quantities in terms of statistical confidence criteria, all these
are performed iteratively, adaptively, and individually in real
time.
6. The method of claim 5 wherein the signals from body sounds, body
signs, and vital signs are processed to estimate cardiopulmonary
capabilities, such as Max HR and Max Lung Volume, from said sensors
of measurements of body sounds and body signs.
7. The method of claim 6 further comprising means for performing
real-time adaptive and individualized diagnosis whereby the
parameters and patterns obtained by said parameter and pattern
extraction methods are further processed to derive exercise related
analysis and diagnosis, and presented so that the individual
engaging in physical activity can monitor the impact of their
activity from these quantities.
8. The method of claim 7 wherein said real-time individualized
pattern recognition and diagnosis generates indices including at
least one of exercise effort, physical stress, energy fatigue, and
fitness levels of endurance, speed, power, and strength.
9. The method of claim 8 further comprising capturing activity
levels by means of direct transmission from an exercise machine,
from motion sensors located on said athlete, from sensors on the
exercise machine, or by a combination of these means.
10. The method of claim 9 wherein said diagnosis recognizes
imminent physical cardiopulmonary problems performs at least one
of: (1) activating warning alarms for deviation of key parameters
from their safe regions; (2) providing feedback indication for
successful restriction of said vital signs, said physical activity
levels or said indices to a normal region: and (3) making remedial
recommendations for changes in said activity level based on the
automated parameter trajectories thereby preventing exercise from
reaching dangerous levels.
11. The method of claim 10 further comprising means for generating
advice using an expert coach decision-making process which employs
the expert decision logic stored in a database of exercise training
rules, expert guidelines, and athlete training experience, together
with said individualized pattern recognition and diagnosis, to
analyze said activity levels to rate the current and accumulated
level of effort of an individual engaged in exercise or physical
activity, make comparison with the exercise goals, and generate
individualized and optimized recommendations for exercise in real
time.
12. A method for generating multi-media exercise activity displays
for playing a combined graphical and acoustical summary of said
real-time individualized pattern recognition and diagnosis
comprising: a. capturing the signals: b. performing noise removal
and signal separation functions to extract authentic signals; c.
synchronizing signals in time such that all signals have compatible
time stamps and sampling rates; d. scaling signals in amplitude
such that all signals have compatible relative ranges, precision
levels, and data representation word lengths; e. extracting
dynamically characteristic parameters to be used for display
functions; f. creating dynamic visualization mappings of the
extracted parameters to displaying variables such as shape, color,
music tune, frequency, etc; g. generating graphics for display of
the mappings by creating commands compatible with display software
such as Media Player; h. generating tones for audible commands
compatible with play by multimedia software such as MIDI sound
software; whereby the generated multi-media display provides the
athlete with the ability to visually and audibly observe the impact
of exercise on said signals of body sounds, body signs, vital
signs, motions and said individualized pattern diagnose
outcomes.
13. The method of claim 11 further comprising means for generating
multi-media body signal displays by using multi-media body signal
display method of claim 12.
14. A computer program product for automating personal exercise
monitoring and coaching of training, comprising: a. a module for
capturing vital sign signals of an exercising athlete; b. a module
for signal interfacing with measurement sensors, off-band noise
removal by using pre-filtering, statistical independent noise
removal by adaptive noise cancellation; c. a module for removing
in-band noise by using the time-shared adaptive noise cancellation
methods, separating interfered signals to generate authentic
signals by using the cyclic signal separation methods; d. a module
for deriving in real-time actual physical activity levels by
processing authenticated signals of body sounds, body signs, vital
signs, and motions; e. a module for performing parameter extraction
and pattern recognition of characteristic features of exercise
levels, dynamic pattern tracking for dynamic trend analysis of
exercise activity, optimal analysis and diagnosis for rating
current exercise activity in relation to personal goals and expert
guidelines, and the impact of physical exertion on these extracted
patterns; f. a module for inputting personal characteristics
information to facilitate retrieval and entry of personal workout
information; g. a personal fitness database to receive information
on personal exercise activity level, machine information, exercise
activity record, and store them for tracking of longitudinal
progress; h. a module for expert coaching of training that makes
recommendations to improve training results based on exercise
rules, expert training guidelines, athlete training experiences,
the activity levels and the extracted patterns, determining warning
alarms for deviation of key parameters from their safe and
desirable regions, making remedial recommendations to improve
training and preserve safety, and populating the personal fitness
database with history of exercise performance; and i. a display
module for presenting to said athlete the impact of exercise on the
fitness levels and improvements, and trajectories of extracted key
parameters that reflect exercise intensity and its impact on
personal fitness and for presenting recommendations from the expert
coach module.
15. The computer program product of claim 14 wherein the module for
personal characteristics input further comprises user interface
software which allows the operator to enter actual exercise results
including repetitions, force or weight levels, and number of sets
among others.
16. The computer program product of claim 15 wherein the product
further comprises an interface which permits communication and
transfer of said results of the exercise workout including said
processed activity level and vital sign data for advanced analysis
to a central server and for communicating data with and storing the
records on the-central server.
17. The computer program product of claim 16 for automating
personal exercise monitoring and coaching of training wherein the
product resides on a portable computing device.
18. The computer program product of claim 17 wherein the portable
computing device includes a scanning device capable of
automatically detecting and recognizing an exercise machine by at
least one automatic and wireless means such as Bluetooth, RFID,
barcode, and magnetic strip.
19. The computer program product of claim 18 wherein the portable
computing device includes a wireless transmitter which permits
communication with the gymnasium computer server.
20. The computer program product of claim 14 wherein said expert
coach module presents an exercise from a stored workout specifying
the next exercise to be performed by the athlete.
21. The computer program product of claim 14 wherein said expert
coach module monitors the vital signs in conjunction with
performance of an exercise and verifies the quality of the
performance of the exercise by using at least one criteria
including motion smoothness of said athlete during the exercise and
smoothness of the athletes in controlling breath volumes, rhythms
and rates prior to providing new recommendations for the subsequent
exercise.
22. A system for automating exercise monitoring and training for a
gymnasium, comprising: a. an athlete wearing sensors for measuring
body sounds, body signs, vital signs, and motions; b. a plurality
of exercise machines with unique identification tags for use in
training by the athlete; c. a portable computing device for
automating personal exercise monitoring and coaching of training
that captures signals of said sensors from the athlete and that can
also manually or automatically recognize a piece of exercise
equipment based upon the unique identification tag; d. a personal
exercise monitor and trainer server that receives, retrieves, and
communicates the results of the workout by the athlete; e. a local
area network for supporting communication between the portable
computing device and the server; and f. a training machine
database.
23. The gymnasium exercise monitoring and training system of claim
22 wherein the training machine database can be used to store,
retrieve, and communicate information on machine settings to fit
the individual's body size and exercise level requirements to
achieve proper ergonomic relations for comfort and safety, and to
store, retrieve, and communicate the workout program and workout
results for the athlete. The training machine database will store,
retrieve, and communicate the alternative workout repetitions and
weights to recommend to the athlete so that the workout objectives
are best met.
24. The gymnasium exercise monitoring and training system of claim
22 that includes wireless or wired means on the exercise machines
to communicate among said portable exercise device, the personal
exercise monitor, and trainer server, to form a networked gymnasium
exercise monitoring and training system.
25. The gymnasium exercise monitoring and training system of claim
24 wherein said trainer server can monitor and communicate
simultaneously and in real time outputs from personal exercise
devices from a multitude of athletes and can analyze the group and
individual results and thereby assisting a single trainer in
observing and training a group of athletes at once from a
supervisory class trainer server and tracking activity and progress
of the each individual as well as the class as a whole.
26. The gymnasium exercise monitoring and training system of claim
25 wherein said trainer server includes an expert coaching module
which can provide automated training and coaching.
27. The gymnasium exercise monitoring and training system of claim
25 wherein a number of class training systems communicate with a
central class contest server which can automatically and in real
time monitor exercise competitions among the multitudes of
gymnasium locations with the class training systems.
28. The exercise contest training systems of claim 27 wherein the
central class contest server can permit multiple classes to compare
their levels of effort with other classes at the same time so that
contests can be held to reward both individual members of an
exercise class or permit competition between disparate classes in
order to reward absolute performance but also level of effort and
group effort and also ensures that no athlete reaches a dangerous
level for their health.
29. The exercise contest training system of claim 28 wherein the
central class contest server judges said contest and rewards
athletes based on at least one of a number of performance and
activity level and extracted vital sign combinations during the
contest.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of U.S. Provisional
Application No. 60/783,424 filed on Mar. 17, 2006. The disclosure
of the above application is incorporated herein by reference.
FIELD
[0002] This disclosure relates to methods and systems for
facilitating continuous monitoring, real-time analysis, and
computerized evaluation of level of effort, physical stress,
resulting fatigue, and remaining energy reserves during physical
activity or exercise and then performing evaluation of that
person's physical performance and acting as an automated coach to
guide exercise intensity and duration thereby optimizing and
individualizing the training process. It also makes possible more
efficient coaching and training of groups.
BACKGROUND
[0003] The statements in this section merely provide background
information related to the present disclosure and may not
constitute prior art.
Continuous Monitoring of Exercise
[0004] Currently, heart rate is primarily used as an indicator of
exercise intensity in many settings and situations by individuals
performing exercise. These active individuals typically use heart
rate monitors that are built into either wrist watch type devices
or into cardiac training equipment such as treadmills, recumbent
bicycles and elliptical trainers, among others. However, the
utility of conventional exercise monitors is limited to simple
calculation of the heart rate, virtual distance moved, and
sometimes calorie expenditure rather than objective level of
effort, or actual measures of fatigue, stress and remaining
capacity for activity.
Body Sounds and Body Signs for Exercise Monitors
[0005] Continuous monitoring of body functions can be of essential
importance in evaluation of athletes for optimal pulmonary and
cardiac training and for detection of dangerous conditions during
physical activity before they become critical. Typical body sounds
include heart sounds, lung sounds, upper airway respiratory sounds,
etc. Other body signs such as chest movements contain further
physiological information. These body sounds and signs contain
specific information that is related to exercise. For example, some
essential parameters can be derived from body sounds: heart rate,
heart pumping volume, respiratory rate, inhale/exhale durations and
volume, among others. Also, chest movements can be used to derive
respiratory volumes. All these physiological parameters as well as
others can be used jointly to measure a person's levels of effort,
stress, fatigue and fitness.
[0006] For instance, it is well perceived and commonly used that
the heart rate is useful for assessing activity levels. Also, it is
known that heart rate variability indicates a person's effort and
mental stress. Combined parameters, such as inspiration duration
vs. the overall respiratory rate can be effectively used to
evaluate a person's level of effort and fatigue. Further, signal
analysis of the body sounds, such as Fourier analysis and
statistical analysis, can extract features for body activity and
exertion. Such features are necessary to accurately estimate total
calorie expenditure.
Noise Reduction During Body Sound Acquisition
[0007] To obtain quantitative and reliable monitoring and detection
of emergency situations, it is especially important that body sound
acquisition obtains sounds of high clarity. But acoustic
environments of gymnasiums and other related sports type facilities
impose great challenges for body sound acquisition. Unlike acoustic
labs in which noise levels can be artificially controlled and
reduced, and body sounds can be processed off-line, these
environments are very complex acoustically due to loud music,
clanging of weights and vibrations from strength training machines,
conversations, audio from televisions, and other real-life aural
artifacts. The unpredictable and broadband natures of such noises
render these physical training locations very difficult
environments for sound analysis.
[0008] The body sound analyzer invention disclosed in U.S. patent
application Ser. No. 11/367,807 surmounts the problems inherent in
body sound acquisition and analysis and this device and methods can
be applied to clinical settings such as might be found in a
physical rehabilitation center.
[0009] However, this new system and method can also be used in
removing noise from other physiological (such as vital signs), and
motion signals (such as chest movements), and applied to
non-clinical settings much akin to rehabilitation centers which are
essentially exercise studios. Because body sounds and vital signs
contain such a rich reservoir of vital physiological information,
this type of data can be useful for monitoring a person's response
to physical activity, and can be definitive in determining the
amount of effort being exerted by a person participating in
strenuous physical exercise.
Separation of Body Sounds During Exercise
[0010] Performance of physical tasks places a tax on the
cardiopulmonary systems of the human body. Changes in these
physiological systems must be evaluated in order to quantify the
person's physical reaction to exercise. Body sounds and vital
signs, such as heart and lung, interact with each other during data
acquisition. Exercise introduces even more corruption among body
sounds and causes difficulty for capturing authentic body sounds
and vital signs, and causing difficulties in subsequent diagnosis.
The body sound analyzer invention of U.S. patent application Ser.
No. 11/367,807, which the present disclosure builds upon, provides
multiple improvements in the ability to separate the overlapping
body sounds and remove confounding noise. In the present invention,
the body sound analyzer invention will be used in its extension to
other signals including vital signs and motion measurements. This
technology is highly desirable, specifically for the present
invention because it helps to perform computerized cardiopulmonary
evaluation during exercise, to use the functionality afforded by
the previously disclosed body sound analyzer disclosure of U.S.
patent application Ser. No. 11/367,807.
Pattern Recognition and Evaluation of Exercise Physiology
[0011] Body sounds, vital signs, and motions contain a rich
reservoir of vital physiological, pathological, and fitness
information that is of critical importance for clinical diagnosis
and sports medicine. Continuous monitoring of body sounds, vital
signs, and motions therefore could provide a non-invasive and
inexpensive means for assisting in evaluating accurately and in
real-time the impact of physical activity in terms of level of
effort, physical stress, overall fatigue, relation to peak
performance, and relative remaining energy reserves with respect to
maximum available. Moreover it becomes more feasible to have the
information necessary to encourage an exerciser to greater effort
in order to meet the levels needed for them to expend sufficient
calories to support their weight loss goals. In addition, it is
possible that by monitoring heart and lung functions continuously a
number of the sudden deaths that occur during exercise might be
avoided by use of the exercise monitors disclosed in the present
application.
Prior Art in Sports Training
[0012] Historical improvements by athletes in sports performance
are attributable to advances in technique and form, but also due to
increases in strength, neuromuscular speed, and cardiovascular
endurance. Recent improvements in these areas have been assisted by
new exercise technologies. The most modern sports training centers
are able to use sophisticated physiological monitors identical to
the most expensive equipment used by physicians. Migration of
training techniques used by professional and elite athletes to the
general population has increased understanding that aerobic and
anaerobic exercise can be made more efficient by training based on
heart rate.
[0013] In order to more accurately measure aerobic capacity, sports
doctors measure many physiological variables including lung
functions. While pulmonary function is measured for elite athletes
it is not currently practical to measure for ordinary athletes
unless there are some prevailing medical conditions such as
exercise induced asthma. Even when there is the possibility of
exercise induced respiratory problems, lung function is still not
measured during day-to-day training by professional athletes, much
less amateurs.
[0014] Currently, in actual practice, day-to-day training falls
under three categories of monitoring. (1) The athlete uses self
observation of their perceived heart effort, and breathing effort
or how "out of breath" they feel to subjectively assess how
relatively hard they are pushing themselves and how tired they are;
(2) The athlete uses the same cues supplemented with objective
values from a heart rate monitor; and (3) a trainer directly
observes the exercise being performed and uses both their own
personal experience with the individual, and their expert knowledge
to assess from visual and auditory cues and possibly heart rate
information, how hard the athlete is trying relative to their own
ability and how much reserve energy is available for continued
effort.
Prior Art in Heart Rate Monitors
[0015] A very large number of products are now available to
portably monitor the heart rate. The rationale for their use is:
(1) in order to reach fitness goals, exercise must be at the right
intensity; (2) heart rate is currently the only accurate
measurement of intensity or exertion level; and (3) portable heart
rate monitors (HRM) are the easiest and most accurate way to
continuously measure heart rate.
[0016] A heart rate monitor (HRM) is a tool used to help set the
pace for exercise. If an individual exercises too hard, they will
most likely quit the activity before they get the real benefit. By
contrast, there are people who exercise at too leisurely a rate and
therefore do not realize the benefits of losing weight or enhancing
cardiovascular functions. Either too slow or too fast a workout
prevents the full benefit of exercise to be gained. Currently, HRM
devices can be used to set pace levels during a workout. The claim
for these HRM devices is that a user could know that they are
getting a similar workout from a treadmill, a weight circuit or
jumping rope by measurement of their heart rate alone. The
companies that sell these devices and their customers thereby tend
to equate heart rate with workout intensity.
[0017] But elite athletes have resting heart rates that would be
dangerously low in a normal person. The extreme high levels of
heart rate for elite athletes during strenuous exercise would
likewise indicate dangerous heart rhythms in a normal person. While
a single example, this illustrates that it is not the case that
heart rate is a complete measure of exercise impact. It is further
clear that heart rate alone does not indicate effort level of the
cardiopulmonary system. Therefore a truer measure of exertion
during exercise must combine more information, such as heart and
lung functions and other body signs.
Prior Art in Aerobic Training Machine Monitors
[0018] Aerobic training machines include stationary bicycles,
recumbent stationary bicycles, spinning bicycles, treadmills,
elliptical training machines, rowing machines, cross country skiing
machines, and stair climbing machines, among others. Electronics
and programmability are important additional features on advanced
aerobic training machines. A built-in heart rate monitor has become
the standard on many cardio training machines. These built-in
monitors typically require that the athlete grasp two conductive
electrodes so that the heart signal can be picked up by the
electrocardiogram (ECG) circuitry. These internal ECG devices are
manufactured for example by the company Polar USA
(www.polarusa.com). Polar makes a system that can be built into an
exercise machine and communicate wirelessly with a Polar chest ECG
sensor worn by the athlete. The heart rate results are
automatically displayed on the display built into the cardio
exercise machine.
[0019] Other than the heart rate, the electronics of cardio
machines typically does hot have the capability to measure other
physical or physiological information from the athlete. Because of
the lack of such information, the display on the exercise machine
can only include information regarding virtual distance traveled,
time exercised or information reflecting the machine level of
difficulty settings.
Prior Art in Strength Training Machine Monitors
[0020] Even the most expensive and elaborate strength training
machines (STM) typically do not have feedback displays for
physiological measurements from the exercising athlete as these
STMs are usually weight or resistance based and have no inherent
need for electronic instrumentation. The exception includes some of
the strength machines which use hydraulic resistance mechanisms.
These types of STMs have an electronic display for their resistance
settings and sometimes the number of repetitions. But even in those
cases, the STMs typically do not have built in heart rate monitors.
This may be because the manufacturers expect that the athlete will
be using cardio machines for their cardiopulmonary training.
[0021] This situation seems to hold even though circuit training
has become popular. The circuit training concept is that switching
quickly between strength machines with no pause will thereby
elevate heart rate and give a cardio workout at the same time as
the strength training workout.
Prior Art in Fitness Training Classes
[0022] Group fitness classes are very popular at larger health
clubs. These classes include gentle stretching as in yoga but more
frequently are some type of aerobic training ranging from
kick-boxing to step aerobics, hip-hop dance, and spinning or
bicycling among others. The class trainer frequently instructs the
class members to take their pulse rate manually. Increasingly, many
participants use a personal HRM to ease their pulse taking during
the exercise class.
[0023] The goals of such classes are often perceived as determining
how hard the trainees should be working during the workout. Success
is often measured on the basis of achieving targeted exertion
levels (target zones) defined by percentages of the maximum heart
rate (Max HR). Max HR is the highest heart-rate value that can be
reached with an all-out effort to the point of exhaustion.
[0024] But basing the workout on Max HR is problematic. This is
because the best method for determining Max HR remains an object of
debate. The rule of thumb used in most aerobic classes is to
estimate Max HR with the formula "220 minus your age." However
after research into the reliability of this method, exercise
physiologists have concluded that Max HR cannot reliably be deduced
using this simple equation. This is due in large part to the fact
that Max HR is dependent on genetics more than age. In fact, most
people of similar age do not have the same Max HR. Without accurate
measurement of Max HR the target zones dependent on this value will
also be inaccurate. Therefore classes conducted based on use of HRM
cannot really achieve their stated objectives.
[0025] In fact, more accurate methods for estimation of Max HR
employ maximal and sub-maximal tests to evaluate the body's
reactions to real aerobic loads. The most precise of these
alternatives uses complex maximal oxygen consumption or maximal
oxygen uptake (VO2 max) equipment to pinpoint the body's
biochemical reactions at various stages of exertion. While a
maximal oxygen uptake test does yield an accurate determination of
the true Max HR, it requires an all-out effort, is very physically
demanding, requires supervision, and is not advised for those who
are not already in relatively excellent shape.
[0026] All of the above mentioned prior systems are therefore
deficient in their ability to serve as a platform for automated
training of an athlete based on their individual capabilities.
Prior systems use means for making their assessment of exercise
level based on strictly heart rate thresholds that are derived from
patient populations, but do not provide a means to generate
individualized true level of effort assessments based on
information more than heart rate. In particular, no prior exercise
systems use body sounds, vital signs, and motions information to
better assess personal level of effort. No prior art is able to put
confidence values on the assessments of performance they determine.
Likewise no prior art has provision for real-time tracking of
personalized athletic assessment variables. Therefore no prior art
can accurately perform an energy balance calculation and accurately
determine when enough calories have been expended to provide for
weight loss. Moreover, none provides means for continuous updating
of their underlying training or coaching algorithms. Likewise prior
art does not provide means to train simultaneously and also
individually all the members of an exercise class based on
objective measures of their personal fitness and activity level. No
prior art has the means to automatically recognize the fatigue
level of the athlete based on the motion on a machine or in control
of movement on an exercise machine, much less use this information
for coaching. Moreover no prior art has means to permit
competitions between remote classes to serve as a motivational tool
to help all the athletes achieve their best possible performance
and reward the classes and individuals for their own efforts with
respect to their personal capacities.
Objects
[0027] In view of the above state of the art, the present invention
seeks to realize the following objects and advantages.
[0028] It is a primary object of the present invention to provide a
method and system for monitoring multiple sites of body sounds,
vital signs, and motions automatically and continuously, and
thereby calculate measures of physiological rates and their
variability in heart beat, breathing, and other physiological
rhythms.
[0029] It is another object of the present invention to provide a
method and system with means for the cancellation of background
noise that has overlapping time and frequency components with body
sounds, vital signs, and motions.
[0030] It is another object of the present invention to provide a
method and system with means for separation of body sounds, vital
signs, and motions on the basis of the rhythmic nature of these
body sounds, vital signs, and motions, such as heart beats and the
inhale/exhale cycle in lung sounds, with means for time-shared and
individualized noise cancellation in order to identify the signal
transmission channels iteratively, in real-time to separate body
sounds, vital signs, and motions and to remove undesirable noise
artifacts and to perform channel identification and noise
cancellation.
[0031] It is another object of the present invention to provide a
method and system with means for real-time and individualized
adaptive pattern extraction display of extracted heart rates,
breath rates, and other body signals along with variability of
these quantities so that the individual engaging in physical
activity can monitor the impact of their activity on these
quantities.
[0032] It is another object of the present invention to provide a
method and system with means for real-time and individualized
adaptive pattern extraction of personal response to exercise that
rates its quality in terms of confidence criteria.
[0033] It is another object of the present invention to be able to
estimate maximum cardiopulmonary capability including for example
Max HR and Max Lung Volume without uncomfortably or even
dangerously high levels of effort.
[0034] It is another object of the present invention to provide a
method and system with means for generating personal indices for
exercise effort, physical stress, fatigue, and fitness levels.
[0035] It is another object of the present invention to provide a
method and system with means for optimized dynamic recommendations
for exercise geared to an individual's personal goals.
[0036] It is another object of the present invention to provide a
method and system which more accurately rates the current and
accumulated level of effort of an individual engaged in exercise or
physical activity based upon their personal vital signs and actual
physical work being performed.
[0037] It is another object of the present invention to provide a
method and system which can permit a trainer to observe a group of
members of an exercise class from a supervisory system and track
how each individual in the class and how the class as a whole is
responding to and tolerating the activity.
[0038] It is another object of the present invention to provide a
method and system which can permit multiple classes to compare
their levels of effort with other classes at the same time so that
contests can be held to reward both individual members of an
exercise class or permit competition between disparate classes in
order to reward absolute performance but also level of effort and
group effort all while making sure no participant reaches a
dangerous level for their health.
[0039] It is another object of the present invention to provide a
method and system with ability to monitor physical activity and
recognize imminent physical cardiovascular problems warn to prevent
exercise from reaching dangerous levels
[0040] It is another object of the present invention to provide
affirmation for successful restriction of key parameters to a
normal region, warning alarms for deviation of key parameters from
their safe regions, and make remedial recommendations for activity
based on the automated parameter trajectories.
[0041] It is another object of the present invention to provide a
method and system which can manually recognize or automatically
recognize a piece of exercise equipment and from a stored database
remind an individual about how to adjust the machine to fit the
individual's body size and exercise level requirements.
[0042] It is another object of the present invention to provide
user interface software which captures automatically or allows the
operator to enter actual exercise performed including repetitions,
force or weight levels, and number of sets among others relevant
factors.
[0043] It is also an object of the present invention to provide a
means to store the results of the completed daily exercise program
and transfer for analysis to conventional personal computers in
order to support analysis of progress.
[0044] It is also an object of the invention to allow the exercise
machines to communicate with the present invention to make known
the particular machine type and model so that the system of the
invention remembers that machine and can remind the athlete of the
preferred position settings for that machine and so that the proper
ergonomic relations are achieved for comfort and safety and to also
remember or store the optimum workout repetitions and weights to
recommend to the user so that the workout objectives are best met
be they large number of repetitions with low weight for maximum
weight loss, or low number of repetitions and maximum weight or
resistance for greatest muscle size or bulk gain.
[0045] These and other objects and advantages of the present
invention will become more apparent from the description and claims
which follow, or may be learned by the practice of the
invention.
[0046] Further areas of applicability of the present invention will
become apparent from the detailed description provided hereinafter.
It should be understood that the detailed description and specific
examples, while indicating the preferred embodiment of the
invention, are intended for purposes of illustration only and are
not intended to limit the scope of the invention.
SUMMARY
[0047] This application claims the benefit of Provisional Patent
Application No. 60/783,424 filed on Mar. 17, 2006.
[0048] In order to optimally perform continuous monitoring and
training of exercise, a personal exercise monitor and trainer
(PEMT) system is provided. A Body Sound/Signal Analyzer module
(BSA) is incorporated in the present PEMT system and methods which
provide objective measurement of the level of effort expended by
the user and make possible estimation of the remaining energy
reserves. The BSA is a computerized cardiopulmonary analysis module
which can separate overlapping body sounds, vital signs, and
motions so that they can be utilized for real-time diagnosis.
However it has analysis algorithms can be applied to any
physiological signals. These processed sensor signals are combined
within the present system and methods for further analysis with
signals from additional physiological sensors. Informational
parameters are generated from these signals, which include, for
example, useful characteristics of lung and heart sounds, heart
rates, and variability, respiratory rate, inhale and exhale
duration and strength, magnitude, frequency center, frequency band,
body oxygenation and exhaled gases, etc. Based on these
informational parameters among others, the following pattern
recognition module or stage uses a new methodology of
multi-variable analysis to accurately estimate, among other
variables, the effort level and energy reserves remaining for the
particular individual.
[0049] Accordingly, a system and methods for physical training are
provided which minimizes the burden of memory of machine settings,
level of effort determination, physical monitoring, and progress
record keeping among others upon the user and thereby maximizes the
efficiency of exercise. The system and methods include a way to
automatically or manually acquire information about which strength
training or cardio machine the user is currently using to exercise.
Advance setup of the system captures the configuration information
necessary to determine optimal physical position settings for
ergonomics and proper level settings to meet that particular user's
training goals. Once recommended settings are implemented by the
user, the system can communicate or interact with electronics on
the exercise machine to acquire progress information including for
example number of repetitions or virtual distance traveled.
Alternatively motion sensors, for example accelerometers, can be
reversibly placed on the machine or are built directly into the
present system to estimate these values based on movements of the
machine itself or motion values of the user. The method based on
the information regarding the user progress, target level of
effort, actual level of effort and current physical condition
provides expert coaching recommendations in order to meet goals of
weight loss, strength gain or cardio conditioning among others. The
method and system can transmit the results of the workout to a
remote system for data storage and record keeping. The system can
likewise be implemented to perform all its operations on the remote
computing device and use local display modules either attached to
the exercise machines or transmit to mobile display units kept by
each user. The method can include means to verify the safety of
each user and make warnings before exercise might reach dangerous
levels. In the case that an health risk situation does inevitably
arise, the present system and method could immediately recognize
the emergency and could use the information to activate internal
communication means to summon first responders to the exact
location of the person having medical problems.
[0050] In other features, an exercise system for training classes
of students is provided. The system includes means to capture and
display to an trainer data captured from each student individually
and summary information for the class as a whole. This permits the
trainer to give personal feedback to individual students while
still optimally challenging the majority of the group. This set of
features along with means for communication allows the disclosed
system to be used in competitions between either subgroups within
the single location or between locations with compatible systems.
This feature can be used to further motivate the exercising
participants through competition and contests. In alternative
embodiments, means are included which translate combinations of the
measured physiological sensor values and calculated levels of
effort to control graphics on local or common graphical display
units. These controlled visual displays will serve to feedback to
the user a better sense of their progress and provide information
for better gauging training progress and becoming trained to
recognize personal physiological status and estimate
self-observable parameters.
[0051] Further areas of applicability of the present invention will
become apparent from the detailed description provided hereinafter.
It should be understood that the detailed description and specific
examples, while indicating the preferred embodiments of the
invention, are intended for purposes of illustration only and are
not intended to limit the scope of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
[0052] The present invention will become more fully understood from
the detailed description and the accompanying drawings,
wherein:
[0053] FIG. 1 shows an overview of the personal exercise monitor
and trainer system and its main sub-modules and their connections
to empirical devices of the system and method in accordance with an
embodiment of the present invention.
[0054] FIGS. 2a and 2b show two alternative personal exercise
monitor and trainer or PEMT systems built upon different
arrangements of sub-modules for the BSA module as it can be used in
systems based on the present invention.
[0055] FIGS. 3a, 3b, and 3c show the activity level determination
process from an individual, from a cardio training machine, and
from a strength training machine respectively.
[0056] FIG. 4 shows an exemplary hardware overview for a gymnasium
equipped with personal exercise monitor and trainer systems.
[0057] FIG. 5 shows the flowchart of the process for PEMT Machine
Database Setup and PEMT Gymnasium Setup.
[0058] FIG. 6 shows the flowchart of the process for PEMT workout
setup.
[0059] FIG. 7 shows the flowchart of the process for PEMT workout
operations.
[0060] FIG. 8 shows the flowchart of the process for PEMT reporting
operations.
[0061] FIG. 9 shows an exemplary use of display software to make
graphical display of PEMT system outputs.
[0062] FIG. 10 shows the usage of multiple personal exercise
monitor and trainer systems to constitute a networked or PEMT based
class system.
[0063] FIG. 11 shows the flowchart of the process for PEMT class
trainer system operations.
[0064] FIG. 12 shows the flowchart of the process for PEMT class
contest operations.
[0065] FIG. 13 shows a general overview of the function sub-modules
of the BSA module and signal processing method which is at the core
of the present invention.
[0066] FIGS. 14a, 14b, and 14c show alternative arrangements of
sub-modules for the BSA module which can be used in systems based
on the present invention.
DETAILED DESCRIPTION
[0067] The following description is merely exemplary in nature and
is not intended to limit the present disclosure, application, or
uses. It should be understood that throughout the drawings,
corresponding reference numerals indicate like or corresponding
parts and features.
[0068] The following discussion assumes the reader is familiar with
personal coaching processes, cardiopulmonary testing and training
equipment, strength training machines, and non-invasive
physiological body sensors as applied to assisting with exercise
training procedures.
[0069] The present disclosure describes various embodiments of a
system and method for personal exercise monitoring and training
that comprise means for (1) initial setup--as provided by a special
exercise machine database containing, machine models, machine
settings, range of values for each setting, and athlete database
with alternatives for various workout schedules; (2) vital sign
data capture and analysis--as provided by special body sensor
capture noise cancellation, signal separation, pattern recognition,
and diagnosis algorithms; (3) activity level capture--as provided
by a combination of active and dynamic sensors which can capture
motions and positions of any exercise machines; (4) expert coach
module--as provided by feedback of coaching advice based on
analysis of the vital signs and actual activity level among other
information and thereby making of recommendations as to how much
harder, faster, or longer the athlete should exercise in order to
optimally meet preprogrammed training goals; (5) multi-media
display--as provided for example by a graphical display and speaker
to remind the athlete with the setting values necessary to adjust
the exercise machine under current use for their personal
ergonomics and to effect their prompting with the number of
exercise repetitions and levels or distances to be used as the
current goal; (6) data capture--to provide, for example by touch
screen capabilities, for the multi-media display of workout
information such that corrections can be entered by the user to the
setup settings and to provides means for data entry of the actual
exercise performed; (7) record data storage--as provided by
automated or user assisted entry of the performance data into a
personal fitness database being used to populate the current
workout exercise fields to permit progress tracking; and (8)
internal user recognition--as provided by an embedded device
identification process which provides means for an exercise machine
to identify the current user, and as provided by locally or
remotely stored setup information prompting the user with machine
settings and recommended machine usage in terms of repetitions and
intensity levels. Various embodiments of personal exercise
monitoring and training methods and systems include various
implementations and combinations of the above described elements as
will be described in more detail below.
Hardware Overview of the Preferred Embodiment
[0070] As shown in FIG. 1, the personal exercise monitor and
trainer system 500 is akin to a human coach in that it assesses the
level of effort being expended by the athlete as well as the actual
activity being performed. However, the PEMT system 500 does not
guess at the level of effort but actually calculates these values
objectively within the BSA-C processing module 230. The objective
measures of activity level as determined by the activity level
module 150 are combined with the level-of-effort values which are
results of calculations by the PEMT Vitals Analysis Module B 320 on
signals from the vital sign sensors 30. The PEMT system 500 also
contains information comprising personal characteristics for the
athlete. This data can be gained by using the personal
characteristics input module 510 which can allow the athlete for
example to enter their age, and weight, and includes values such as
their body fat percentage, body mass index (BMI), and resting heart
rate among other general indicators of overall health and
fitness.
[0071] In an exemplary embodiment of the personal exercise monitor
and trainer system 500, as shown in FIG. 1, the expert coach module
550 stores these values in the personal fitness database 520 to
support basis of workouts on individual capacities and strengths as
well as activity levels and levels of effort.
[0072] As shown in FIG. 2, the sound sensors 30 are placed on
measurement sites on an athlete 10 to capture body sounds, such as
tracheal, bronchial, heart, etc., and for noise references. Sound
waves acquired by the sensors will then be processed using the body
sound or signal processing modules. As shown in FIG. 2a, if the
vital sign sensors are acoustic sensors 31, then when using the
BSA-B 220 sub-module for analysis, the personal exercise monitor
and trainer system (PEMT) can display simple extracted quantities
such as the heart rate, breathing rate, and heart rate variability
and breathing or lung rate variability which allow the athlete to
self assess their exercise effort using much more complete
information than that given by a simple heart rate. While body
sound sensors alone are sufficient to support the simplest PEMT
calculations, the inclusion of other vital sign sensors such as ECG
or pulse oximetry sensors, allows the BSA-C 230 module to calculate
more complex assessments of athletic efforts. For example, when
chest movement sensors 32 are included to measure movement in the
ribcage and movement in the abdomen, it is possible for the BSA-C
230 module to extrapolate values for tidal volumes and, as shown in
FIG. 2b, extract individualized patterns which can support the
calculation and display of the level of effort, physical stress
level, level of fatigue, and even estimate the remaining energy
reserve of the athlete or the percent capacity for physical
activity remaining.
[0073] As shown in FIG. 2b, these values can be displayed
graphically by an alphanumeric display on a watch type device, or
even be sent in a wireless fashion to a device with graphical
display capability such as a PDA with wireless connectivity. The
PDA or some other computing device may contain the computing
software to perform the filtering and noise removal as well as the
BSA-C module 230 calculations, or these signal processing functions
can be divided between a number of distinct hardware modules either
residing closer to the vital sign sensors 30 and therefore worn by
the athlete 10.
[0074] Any number of combinations of displays or feedback means of
calculation results could be utilized to optimize ease of use by
the athlete. For example, rather than a wrist based display or
audio feedback through a headset or earphones, the athlete may wear
a set of prescription or non-prescription eye glasses with means to
function as a heads up display. For example, the athlete may wear
glasses such as those disclosed in U.S. Pat. No. 6,801,363, which
have the ability to act as a glasses mounted display. In this way,
the athlete never has to modify their movements or activity to
avail the assessment of their performance. This type of head
mounted display arrangement permits the maintenance of best form
while at the same time permitting the determination by the user of
the PEMT system of maximal or optimum effort.
[0075] For the PEMT system or methodology to enhance or replace the
function of a human trainer or coach, the PEMT can measure vital
signs from the athlete, but also receive data on what constitutes
the actual physical activity being performed. As shown in FIG. 3a,
if the athlete 10 is exercising by performing calisthenics or body
weight exercises, then the most practical way for the PEMT to
calculate this activity level is by analysis of signals from motion
and/or position sensors 110, for example accelerometers and
coordinate sensors, which give movement values or relative
positions of sensed body parts to a coordinate system in three
dimensions. As shown in FIG. 3b, if the athlete 10 is exercising
using some form of cardio training equipment such as a bicycle,
recumbent bike, or treadmill type device 410, the suitable sensors
can capture the virtual distance the athlete 10 has in effect
traveled 114, the velocity of motion or for example some value of
revolutions per minute (RPM) 116 from the roller mechanism on the
equipment and some value of resistance 112. On a treadmill-type
machine the resistance value is typically replaced by the incline
angle which when adjusted serves to make the athlete feel like they
are walking, jogging, or running up a hill of a particular
pitch.
[0076] As shown in FIG. 3c, the athlete 10 may be exercising with
the objective of achieving increased muscle strength. In this case,
a different set of sensor types is necessary to record the set of
exercise machine values which more properly assess the muscle
building activity. For strength training machines 420, the sensor
types will typically include a sensor which measures the number of
repetitions of complete movement 122, the weight setting typically
measured in pounds or number of counter weight plates 120, and seat
settings for body position or incline 118. These latter adjustments
may affect the leverage necessary to move the weights and they
therefore affect the activity level.
[0077] Weight lifters typically count the number of sets they
complete in addition to the number of reps performed. The activity
level module 400 shown in FIG. 3c contains analysis capabilities
which allow it to determine whether the pause between repetitions
is sufficiently long to consider these repetitions as belonging to
a new set.
[0078] Therefore as shown in FIGS. 3a, 3b and 3c, based on
measurements taken directly from sensors on the exercise machine
itself or from the sensing of movement of the athlete's body in
space, and after capture of the sensor data by the data acquisition
(DAQ)/filtering/noise removal module 55 to extract clean sensor
signals, the activity level module 400 calculates assessment of the
overall levels of athletic activity, work, and power that are being
performed.
[0079] Shown in FIG. 4 is a hardware overview of one possible
embodiment of a fitness center or health club which is enabled for
use of the PEMT systems 500. However it is still possible for an
individual PEMT standalone device to accomplish most if not all of
the functions shown by the hardware in FIG. 4 although with more
manual or assisted operations by the athlete. As shown in FIG. 4,
the athlete 10 wears the vital sign sensors 30 either on wrist,
attached to chest or abdomen or elsewhere in order to make
effective sensor contact. These vital sign sensors 30 communicate
through direct or wireless connection with the main PEMT system
185. The PEMT PDA system 185 can communicate wirelessly with
exercise machines such as STM 420 or CTM equipment 410 in the gym
for example using an ID capturing device such as RFID, IR reader,
laser scanner, or some other wireless means. This communication
link can establish which exercise machine the athlete 10 is
currently using. Alternatively the athlete 10 can manually set the
machine identifier into the PEMT 185 using the built in input
functions such as a key pad or touch screen display. The exercise
machine 420 may or may not have its own ability to calculate and
communicate the activity level automatically to the PEMT device
185. As depicted in FIG. 4, a local network 660 can facilitate
communication with a supervisory computer 610 for PEMT units that
spread throughout the whole gym. Said supervisory computer 610 then
can assume much of the analysis and communications responsibilities
of the individual training machines and the PEMT units. In some
cases, it would only be necessary for the athlete 10 to wear the
PEMT sensors 30 and the central computer 610 could perform the
computing tasks ordinarily performed by the PEMT computing module
185. The trainer 20 as shown in this figure is able to monitor the
activity of numerous athletes 10 which is especially useful during
an exercise class.
[0080] FIG. 5 is flowchart diagram that details the process to
perform the setup of the personal computer database for use with
the PEMT device 180 shown in FIG. 1 especially as used in a
gymnasium which expedites the use of the devices such as shown in
FIG. 4. That is, the training machine database 710 in FIG. 4 is
populated for a particular gymnasium using the process shown in
FIG. 5. On the personal computer of the gymnasium, such as the PEMT
server 610 shown in FIG. 4, the user runs a database application or
a dedicated software program that creates the database of all
exercise machines at the gym. As shown, the user selects an
exercise machine to be entered into the training machine database
710. Each machine is first assigned an unique #. It can be the
preference of the gymnasium management as to whether machines of
identical manufacturer and model number are assigned the same
identification number. This is a consideration because even
machines which are manufactured to be identical can age differently
over time and thereby have different impacts on a workout. Once
each machine is given a unique identifier for database purposes, a
human readable physical ID Tag is created and affixed to the
machine in a permanent but conspicuous fashion. This ID Tag may in
addition to being visually readable, use radio frequency
technologies, may have bar code properties, or some other means can
be used to make said ID Tag machine readable, scannable or
detectable at a distance. Once the machine is tagged, this setup
process solicits choice of what class of exercise the machine
supports. This is because machines of same class for example,
cardio training or strength training machines tend to be similar in
function and therefore its setup in the database can be expedited
by first determining to which class a machine belongs.
[0081] As shown in FIG. 5, in this representative embodiment, for
each machine the ergonomic settings are first named and entered
with their range of values. The ergonomic settings are those
settings which are primarily dependent on a person's skeletal
dimensions and to a lesser extent their flexibility. Therefore,
these values do not typically change with any amount of training.
They are also not directly involved in the training process. They
are therefore handled differently by the training machine database.
Once the exercise is underway the ergonomic settings remain
unchanged. Following entry of the ergonomic variables, the other
setting types are entered which do change with the workout.
[0082] Also as shown in FIG. 5, if the machine being entered is a
member of the cardio training machine (CTM) class the ergonomic
settings are first entered which will typically include seat height
on a stationary bicycle, or distance from the pedals on a recumbent
bicycle. Typically these are settings which have integer values
between one and ten. Then the other setting types are named and
entered with their range of values. For example, elliptical trainer
machines frequently have a resistance or level of difficulty
setting between 0 and 100. The speed setting measures from rest or
zero strides per minute on up to whatever speed a human athlete can
move on the machine which typically would not go over 200 strides
per minute. Once both the ergonomic settings and exercise specific
settings are captured, this settings data is saved and stored in
the training machine database 710.
[0083] If the machine being entered is a strength training machine
(STM) the ergonomic settings are again first entered in this
embodiment. For STM machines there are frequently settings for seat
height, and for handle length, handle height, leg length, or arm
length. Tilt angle for arms or body are also frequent ergonomic
settings for STMs. All these variables typically have integer
values between one and ten. Once these values are entered the
setting types covering the specific exercise are entered. These
will include for example the weight, incline angle and repetitions.
Repetitions is an open quantity which is not set by the user of the
machine and so no value is necessary for upper end in range of
values for entry in the database. Again, once all the pertinent
database fields are entered with name and range of values for
ergonomic and exercise settings, this STM machine data is stored
into the training machine database 710 for future usage by PEMT
devices and methods.
[0084] FIG. 6 is flowchart diagram that details the process to
perform the creation of a personal workout and schedule for the
personal fitness database 520 for use with the PEMT device 180
shown in FIG. 1, especially as used in a gymnasium which expedites
the use of the devices such as shown in FIG. 4. As shown in FIG. 6,
to expedite the creation of a personal workout, the training
machine database 710 is downloaded to the PEMT based device. For
the purpose of this embodiment, the PEMT is a PDA device with
wireless communication capability 185. To create a workout, the
athlete 10 can work directly with a personal trainer 20 who is
experienced in creating personalized workouts, or may work by
themselves and follow workout samples given in popular exercise
books such as "Body for Life" by Bill Phillips or well know
magazines such as "Muscle & Fitness."
[0085] As shown in FIG. 6, the athlete 10 selects the first machine
to be used in the new workout and then uses some means to capture
the unique ID number associated with that machine as created in the
process of FIG. 5. This capture of the ID number can be done
remotely and automatically by the athlete walking up to the
exercise machine and using an optical scanner, or an RFID receiver
built directly into the PEMT PDA 185 device. These are just two of
the many means that can be employed by the PEMT device to
automatically identify the machine that is nearest the device. Once
the exercise machine is uniquely identified the PEMT device calls
up in software the set database of values for that type of machine
created in FIG. 5. Then the PEMT software solicits from the athlete
the particular values to be entered into the database for the
athlete during that workout. For example, as shown in FIG. 6, if
the athlete has selected a particular cardio machine, the PEMT
software knows how many ergonomic values are necessary to
completely setup that machine for the user. In this embodiment,
that information came via download from the training machine
database 710. Using the information from the training machine
database 710, the PEMT workout setup software prompts the athlete
with the name of the setting and can present the athlete with a
range of values in a list to expedite the choice making.
[0086] In order to expedite choice making for ergonomic settings,
the athlete can test alternatives on the machine itself. This is
why a preferred method for workout creation is to create it in the
gym where the machines are available for scanning of their ID tags
and testing of setting values. Therefore, the athlete might sit on
the seat and adjust its position to test the value before data
entry and verify that it is the most comfortable setting. The most
comfortable will typically be the safest and best setting for
expediting the exercise process. Once the ergonomic settings are
entered, the athlete likewise enters start setting values based on
prompts from the PEMT workout setup software. The software for
example will request for a treadmill the incline level setting, the
speed setting in miles per hour, and also the time for the workout
or the virtual distance to be traveled. In this fashion, the
athlete is assisted in entering the crucial and complete
information necessary to optimally use all the equipment. This
information is no longer necessary for the athlete to remember as
long as they can use their PEMT PDA device 185.
[0087] In this same fashion, the athlete can also create a workout
which employs strength training machines. While this class of
machines will tend to have different names of settings, the process
is similar that the athlete must follow to add use of a STM to the
particular workout. Workouts can be of any length. Although this
practice is not typically recommended by trainers, PEMT workouts
can mix both cardio and strength machines.
[0088] Once the ergonomic data and settings data are entered for
each machine in the new workout, the athlete can name the workout
and assign a schedule to it. For example, workouts programs are
sometimes upper body and lower body on alternate days. Or for
example, Mondays might be shoulders and arms and Tuesday can be
legs and abdominals. Any schedule can be assigned to any workout
and the. PEMT PDA will then, depending on the schedule, and using
the calendar capability built into the PDA, prompt the athlete with
the preferred workout suggestions based on pre-selected schedules.
The named workout is then stored in the personal fitness database
520 for that athlete on the PEMT PDA device 185.
[0089] In alternative embodiments, the athlete would have an
identifying wristband or card key and each exercise machine would
have a detector which could detect its current user. Alternatively,
the athlete could manually identify themselves to the PEMT device
on the exercise machine or the PEMT device on the exercise machine
can have some biometric sensor to identify the user athlete. In
this way, by moving between stations the athlete could be
identified and the exercise machine could communicate with a
central PEMT server and database to lookup both machine information
and that athletes preferred settings.
[0090] FIG. 7 shows an exemplary method of an athlete interacting
with the PEMT device 185. The user of the invention 10 can follow
the flowchart of the process in FIG. 7 to assist in expediting
workout operations. The athlete selects and runs the perform
workout software program on the PEMT device. In this representative
embodiment, the user is first prompted with the option of
performing a scheduled workout or picking from a list of previously
stored and named workouts. For example, if it is Monday, the PEMT
software will offer the workout scheduled for Mondays first on the
list of choices. Also on the list maybe items with names for body
parts such as "chest and legs", "arms and back" or "cardio
distance", or "cardio speed", or "cardio hills". The athlete may
choose from one of the list of previously created and stored
workouts or may decide to follow a "manual" or freeform workout for
that day.
[0091] The left half of FIG. 7 shows the PEMT workout process in
the case of the athlete choosing a previously stored workout. Once
a particular workout is chosen, the PEMT device displays which
machine, is to be used for the first exercise. At the same time, or
after acceptance by the athlete, the PEMT device 185 displays the
ergonomic settings and exercise plan for that machine. In the
event, that a machine recommended is broken, an option is given for
eliminating that particular exercise for the day. In the event,
that the machine required for the next recommended exercise is not
available because it is already occupies, an option is given for
skipping over that particular exercise until later in the workout.
The athlete then adjusts the exercise machine by following the
predetermined ergo settings.
[0092] As shown in FIG. 7, the program then gives displays the
settings for strength exercises by giving the start weight and
number of repetitions to follow. If a sequence of weight levels and
repetitions is part of the workout then the display will show this
accordingly. As a set is completed it can be checked off as done
using the touch screen display.
[0093] Also as shown in FIG. 7, if the next exercise in the workout
requires a cardio machine, the PEMT device displays the incline
level for a treadmill for example, or the resistance level for an
elliptical machine for example. In most cases in order to
completely instruct for performance of a cardio exercise, a speed,
distance or time value will be displayed.
[0094] In alternative embodiments, the motion sensors can be either
on the athlete or on the exercise machine and communicate by
wireless or some other means with the PEMT and then that device can
know for example exactly how many repetitions of an exercise were
performed. Motion sensors on the athlete can be used by PEMT to
actually count repetitions performed because PEMT analysis
algorithms will recognize characteristic motion patterns of a
person when using each machine type. In yet another alternative
embodiment, the exercise machines have PEMT compatible motion
sensors which can automatically count reps, and also detect and
communicate other machine settings such as weight level, or the
virtual distance actually traveled on a CTM. The exercise machine
can even contain its own PEMT or some other sensor and analysis
device with motion analysis algorithms which can on board the
exercise machine itself assess for example the athlete's ability to
handle that weight level by analyzing smoothness of motion of
repetition performance for that machine. This on board PEMT device
then communicates wirelessly with the portable PEMT device of the
athlete so that it can use that information directly for the expert
coach module analysis and in this embodiment fewer sensors need be
worn by the athlete.
[0095] In the exemplary embodiment shown in FIG. 7, the PEMT can
monitor the vital signs of the athlete and can in real time
recommend changes in cardio machine settings to challenge the
athlete's physiological response in the most accurate fashion. Not
just heart rate but lung function and overall effort levels can be
used to safely challenge an athlete in their workout performance.
As the vital signs are monitored to control level of effort the
overall workout length and difficulty can be adjusted by the PEMT
to challenge the athlete to use a predetermined amount of energy
reserves such as needed for distance training.
[0096] Most importantly, the PEMT is constantly analyzing the data
from the vital sign sensors and the extracted parameters for
dangerous reactions during exercise. The PEMT has different levels
of reaction to medical dangers which can range from decreasing the
difficulty of the workout, to warning the athlete, to actually
summoning medical aid in the event the vital signs indicate an
emergency situation. When the expert coach module 550 within PEMT
determines the athlete is overly stressed, has reached a level of
too much fatigue, or even detected a sufficiently large loss of
form or technique in performance of the exercise, the PEMT can
recommend through its multi-media display anything to help the
athlete recover which can include among other recommendations a
water break, rest, doctor consultation, adjustment to the exercise
routine by scaling back, or can even make an emergency phone
call.
[0097] In addition to checking for medical emergencies, the PEMT
expert coach module makes real time adjustments to the workout
intensity based on overall goals and the vital sensors analysis.
This real-time adjustment feature can be toggled on or off by the
athlete depending on their feelings for that workout. On some days
the athlete might feel energetic and desirous of a greater
challenge, while on other days the athlete might feel for example a
cold coming on and is not desirous to push their limits. However,
the PEMT algorithms are designed to detect strength or weakness in
the performance and vital sign reaction to the workout and can make
recommendations accordingly.
[0098] As an exercise is completed, the athlete again can check it
off as done by using the touch screen display of the PEMT device.
In the event that more or less reps or deviations are made from the
suggested weight or difficulty levels the changes performed can be
manually entered by the athlete. If the workout is not complete as
shown in FIG. 7, the process is repeated again with the PEMT
displaying the next exercise on the workout list. This process
continues until the workout is complete when the workout results in
terms of exercises, deviations and vital sign summary are recorded
for that workout and stored in the personal fitness database 520
for future analysis and tracking.
[0099] The process of operation when the PEMT is used in a free
form mode or when a previously stored workout is not followed is
shown on the right side of FIG. 7. In this usage case, the athlete
selects an available exercise machine and either automatically by
some in some fashion means such as optical, magnetic, or RFID among
others captures the ID number of the machine. The PEMT can then
display the ergonomic settings and a list of previously stored
preferred exercises using that machine. It can automatically search
these previous uses of that machine from within any stored workout.
After machine adjustment, the user can either follow a suggested
exercise for that machine or use coaching from the expert coach
feature of the PEMT to push their workout in a preconfigured
fashion. The expert module may be set for example to a strength
training mode which will recommend low repetitions and high weight
or weight loss mode with high reps and low weight. The PEMT all the
while is checking the vital signs and motion sensors for quality of
performance and stress level for example. In this fashion the PEMT
can mimic the processes that an experienced human coach follows but
with much better understanding and insight into the real-time
physiological response to the exercise by the athlete.
[0100] As in the use of preconfigured workouts, the process
continues in this fashion for each exercise. However, in this case
the process continues until the athlete indicates to the PEMT
device that the workout is over. Again the workout followed and
performed is recorded based on automatically acquired information
and that manually entered into the PEMT by the athlete along with a
summary of vital signs during the workout.
[0101] FIG. 8 shows the flowchart of the process for PEMT reporting
operations. For use of the PEMT in standalone operation mode, the
PEMT is connected directly to the users personal PC. Daily workout
results can be uploaded from storage within the PEMT device by the
PEMT software program which also analyzes workout routines,
calculates statistics, generates charts, and produces trends of
progress in terms of workout and physiological effects. As shown in
FIG. 8, graphs can be generated for trends in the athlete's
performance on specific exercises, overall changes in fitness
levels such as cardio endurance and arm strength among others. The
amount of calories burned during workouts as a function of time can
also be graphed. These are mere examples of the types of analysis
that can be generated when the PEMT data is uploaded. In the
embodiment of FIG. 8, in addition to simple graphing and summary of
performance and trending over time, the PEMT expert coach module
550 of the PEMT server is shown to make more advanced
recommendations to produce a report that summarizes the current
workout results in relation to goals and objectives of the
exercise, comparison with related groups, and recommendations from
exercise experts. In addition, inputs from a personal trainer, if
available, can be incorporated into the analysis and reports. The
output of this function will be stored in the personal fitness
database 520 for future utility.
[0102] For use of the PEMT in server-based operation mode, all the
functions performed above by the personal PEMT can be performed on
a PEMT server remotely with wired or wireless connections to the
personal PEMT. In this mode, the personal PEMT will serve as a
connection node between the PEMT server and the trainee and the
exercise facility.
[0103] As shown in FIG. 9, the display functions of the PEMT system
include graphical and multimedia functions that can be integrated
with typical software packages such as Real Player or Microsoft
Media Player. The medium of display can be the PEMT screen itself,
a TV screen, a computer screen, or a projector among others. For
example, in Real Player or Microsoft Media Player, the related
parameters such as motion, position, speed, and other physical
values, can be transformed simultaneously into visual effects and
music tunes with various rhythms, tones, frequencies, and power
bands, for combined multimedia surrounding and visualization. The
displayed values by the graphics program can be determined and set
by any designated parameter levels from PEMT, such as values of the
vital signs, level of activity values, level of effort, or some
combination of these parameters. With such versatile display
functions, the athletes and PEMT system users will have a real-time
feedback display of their workout with an informative and
comforting visual and audio environment.
[0104] As shown in FIG. 9, in an exemplary embodiment, the PEMT
performs a process to captures the vital signs with signal
interfaces and adaptors 810 and performs filtering and noise
removal 55 to extract authentic physiological signals from
noise-corrupted measurements. Then a series of signal processing
functions follows to facilitate visualization and multi-media
presentation. First the processed vital signs, which are usually
collected with different sampling rates and time stamps, are
synchronized and re-sampled 830 if necessary to be represented in a
uniform time frame. Then, synchronized signals, which usually have
different value ranges and precision levels, under a proper
magnitude scaling process 840 to become compatible in their
precision and relative value ranges in their computer
representations. The characteristic parameter extraction module 850
is used to derive characteristic parameters from the signals.
Typically, simple parameters such as heart rate, breath rate can be
extracted relatively easily from signals. More sophisticated
parameters such as effort levels and oxygen consumption volumes
must be derived with more involved algorithms. Dynamic
visualization mapping module 860 is a real-time interface function
between extracted parameters and display software. This process
module associates parameter values to designated display media
selections such as color, music rhythms, among others. This allows
parameter values to be displayed as visual and audio effects. The
signals can then be displayed via a display software process 870,
such as Microsoft Media Player, to expedite visualization and audio
representation on any display devices 880.
[0105] Frequently athletes participate as a member in group
training classes. Many people favor being in a class setting for
their exercise rather than doing it alone. This may be because it
is less boring, because of the added social value, or because it is
motivational and motivates the class participants to push
themselves out of a sense of general cooperation and competition.
FIG. 10 shows how members of a class can each have their own PEMT
system communicate their activity level and level of effort or in
some cases just an overall level of effort or activity level of the
group or combination of these. Through communication means as shown
in FIG. 10 the PEMT system 500 can reside on an Ethernet network or
even communicate via the internet to the PEMT class trainer server
(CTS) 610. This PEMT CTS computer 610 runs supervisory software
which combines all the class information into a summary report
display of the whole class activity and also makes comparison of
each student relative to the class average. In this way, the class
trainer 20 can assess using objective data how the class as a whole
is performing relative to overall goals and also how the individual
students are performing relative to the group mean or average. If
too many class members are not achieving the requested activity
level it would indicate to the trainer 20 that the overall class
goals are set too high or are too difficult. By contrast, if every
athlete 10 in the class is exceeding the stated goals then these
targets might be considered too easy by the trainer 20 and said
targets can be modified accordingly.
[0106] As also shown in FIG. 10, the summary of class results can
be displayed via a screen projector 670 for all class members to
see on a large projection screen 680 located in front of the
exercise studio or small monitors located throughout the room.
Graphical indicators can be generated in the reporting software and
visually shown to allow the student to judge how they compare to
the group either through some distinguishing icon on the general
screen 680 or by comparing displayed values on their personal PEMT
180 with the class averages displayed on the common display
680.
[0107] A system for competition or contest between disparate
classes can be created based upon PEMT systems 500 by having
multiple class systems 600 as shown in FIG. 10 having their PEMT
class trainer server 610 communicating in some means with each
other through a supervisory computer, for example over the
Internet. By sending information from multiple classes running
simultaneously contests can be held between disparate health clubs
or various organizations locally, or nationally, or even
internationally. Multiple and various ways can be designed for
winning the competition. The competition can be strictly based on
activity level, for example which group pedals a longer cumulative
virtual distance in a period of time, or which group lifts more
pounds in a period of time or number of repetitions. But it is also
possible to set rewards based on which class or individuals within
are trying harder or have a higher level of effort. This reward
process allows contest winners to not just be the biggest or
strongest athletes but those that try the hardest or perform
closest to their personal maximum capabilities. In the case of
these contests the projector can display tracking in real-time of
how one class is performing relative to the other contest
participants.
[0108] FIG. 11 elaborates functional and operational procedures of
the PEMT class trainer system 600 depicted in FIG. 10. The flow
diagram illustrates an exemplary process of training a class of
athletes by using PEMT devices 185. In the embodiment shown in FIG.
11, each participating athlete uses a PEMT device 180 or 185 during
class. The device can be either be embodied as (1) PEMT standalone
units or (2) a PEMT monitor unit built into the studio exercise
equipment such as stationary bicycles among other exercise
machines.
[0109] As athletes 10 enter the class, they attach their vital sign
sensors and establish communications between their PEMT device 185
or 180 and the PEMT class trainer server 610, via wireless networks
or wired directly into the local gymnasium network or remote site
by a wide area network (WAN). Once communication is established,
the PEMT 185/180 sends setup information identifier information to
Class Trainer Server 610 including (1) athlete unique identifier;
(2) athlete demographics such as age, sex, and location; (3)
athlete fitness data including for example their fitness level,
health concerns, fitness goals, and Max HR among others. These
values can be obtained from a setup file contained in the PEMT
device with assessments either made by the device during prior
workouts or entered into the device after testing by the personal
or group trainer.
[0110] Once all the athletes have established communications
between their PEMT devices and the PEMT class trainer server, and
their devices have sent their necessary personal information, the
trainer can start the class with instructions for the first
exercise. As the athletes perform the exercise, their PEMT devices
send vital sign data continuously and automatically to the PEMT CTS
610. The PEMT CTS combines all athlete data and performs data
analysis: (1) checking vital signs to ensure individual athlete
safety; (2) monitoring the individual progress for each athlete by
comparing his/her efforts against the previous classes that athlete
has taken; (3) summarizing the class or group results in tables and
graphs; and (4) displaying these group results on the trainer's
monitor 20.
[0111] The trainer 20 studies the individual and group report
summaries and can then use this objective information to optimize
the training of the class. In current group exercise situations the
trainer can only tell how a student is doing by observing
subjectively their movements and judging with experience their
stress levels. The PEMT system makes it possible for the trainer to
gain more comprehensive and objective information on the effort and
stress levels of each athlete as well as the class with necessary
statistics such as mean, variance, trend, and deviations from
designated goals and objectives.
[0112] The class trainer server (CTS) 610 displays for the trainer
instantaneous and trend information: (1) athlete identifier
including perhaps their physical location in the exercise studio;
(2) heart and lung breathing rates and their variability; (3) level
of effort with respect to their personal target zone defined for
example by the ranges of heart rate and respiratory rate; (4)
critical conditions such as for example an unhealthy variability in
heart rate; (5) summary statistics of the class, such as the
percentage of the athletes who are in the desired target zone. This
information among others allows the trainer to adjust the level and
pace of training adaptively during the class. PEMT information
processing can combine machine information such as RPMs in a
spinning class with activity information such as motion sensors
described in FIG. 10 to generate real-time machine data, and
control machine settings to fit training programs if the exercise
machine is equipped with such control functions.
[0113] As shown in FIG. 11, once the trainer 20 can review the
real-time summary information presented by the CTS 610 the trainer
provides feedback instructions to individuals and the class as a
whole. After verifying that no class members are having medical
difficulty, the trainer 20 can give encouragement or incentive to
any lagging students and give appropriate praise to the students
that are achieving or exceeding their personal goals. Likewise, the
trainer 20 can assess the efforts of the class as a whole and
adjust the difficulty levels to challenge the class without overly
doing so. Also as shown in FIG. 11, this class training process can
be repeated for each new exercise that the trainer assigns.
[0114] FIG. 12 is a process flow diagram illustrating an exemplary
method for classes of athletes which are enabled with PEMT devices
185 or 180 to hold physical exercise competitions in a remote
fashion. This diagram summarizes steps for performing the class
competitions using the PEMT class trainer system 600 as illustrated
in FIG. 10. In the embodiment shown in FIG. 12, each participating
location or class is assumed to have all of their students enabled
with a PEMT device 180 or 185 during class and moreover in this
exemplary embodiment each class competing in the contest has a
class trainer server 610 in order to participate.
[0115] As shown in FIG. 12, multiple PEMT class trainer servers 610
establish communications with a remote class contest server 620 or
alternatively establish communications with a contest management
website. Once connected, the class trainer 20 registers their class
for competition by uploading information identifying the contest
level or degree of difficulty of competition and events that their
group wants to compete, the number of athletes in the group, and
perhaps the age distribution of the class among other pertinent
information. Other types of information the trainer could indicate
include proficiency ratings for example A, B, C for skill events
such as bike riding or treadmill running and equipment type among
others.
[0116] The remote contest server then (1) performs a matching of
compatible registrants; (2) publishes rules for the contest such as
defining the contest events, for example a thirty minute bike ride
at 90 RPM or at some heart rate zone; and (3) initiates the contest
for example by firing a virtual starting gun on the class
displays.
[0117] While the contest is in progress, the class trainer servers
610 send continuously a summary of the progress data of all their
group's participants to the central class contest server 620. The
class contest server 620 collates the information from the
disparate participating groups for contest monitoring and
analysis.
[0118] The class contest server 620 combines results from each
group in a particular contest and sends the current standing
information to the PEMT class trainer servers 610 and also sends
additional summary information regarding for example individual
standout performances back to the participant locations for display
to their group. In this fashion, the groups essentially can get
real-time feedback about their group's standings and this
information can be motivational to get the group as a whole to try
harder or work together. Each local participating club has a group
display which presents the current standings for motivation of
class members.
[0119] In an alternative embodiment, the class contest server 620
can update team standings and positions in a race and communicate
the results to the participants by publishing on a contest website
the real-time summary of standings.
[0120] Once the contest is over, be it a timed event or for example
some virtual distance type event among other types, the class
contest server 620: (1) analyzes final results; (2) judges the
contest winners for both individual and group categories; (3) makes
awards; and (4) publishes a summary of the contest results.
Body Sound, Body Sign and Motion Measurements
[0121] This invention introduces a monitoring system that is
equipped with body sound, body sign, and motion sensors attached to
multiple sites of a person's body to acquire body sounds and
signals simultaneously and continuously. The system is capable of
performing signal separation, noise cancellation, and
computer-assisted signal pattern analysis. Based on the sensor
data, the system provides a non-invasive means to accurately and
promptly determine heart rate, lung or breathing rate, heart rate
variability and lung rate variability among other physiological
indicators.
[0122] FIG. 13 shows an overview of the BSA module 95 as previously
disclosed in U.S. patent application Ser. No. 11/367,807. This
module receives input from several body sound, vital sign, and
motion sensors 30, performs associated data acquisition for
measuring body sounds, vital signs, and motions continuously and
provides means for output of results, including for example a
digital display. It can provide extensive signal analysis in
particular of heart and lung sounds but also of other vital signs
and thereby provide the core functions for an improved exercise
training device.
[0123] Shown in FIGS. 14a and 14b are scaled versions of the BSA
module 95, which can be made to perform useful subsets of the total
processing tasks shown in FIG. 13 and as such need to include fewer
analysis modules and have the ability to perform less powerful
functions., However with fewer analysis sub-modules, the derivative
systems can be made smaller and for less cost. BSA-A module 210 can
perform the extraction and separation of heart and lung sound or of
other signals. BSA-B module 220 can perform all the functions of
BSA-A module 210 with the added ability to perform pattern
recognition. For completeness, as shown in FIG. 2c, BSA-C module
230 adds a sub-module to BSA-B module 220 in order to perform
higher level abstractions in real-time on the extracted
individualized patterns. Trending, diagnosis and the generation of
conclusions based on changes in movements of the extracted patterns
are performed by the real-time individualized optimal diagnosis
sub-module 90.
[0124] The present invention combines output from body sounds,
vital signs, and motions sensors with other non-invasive sensors
for transcutaneous monitoring of respiratory gases and respiratory
movement. For example, the transcutaneous oxygen sensor measures
the PO2 through the skin and reflects skin tissue oxygen tension
beneath it. Tissue oxygen tension is the primary goal of the
peripheral circulation and hence is the variable to track. This
variable will follow the trend of arterial or PaO2 values during
adequate blood flow states and follows changes in cardiac output
during circulatory shock. Therefore PtcO2 can be included in the
invention along with body sounds for determining the adequacy of
ventilation.
[0125] Likewise, transcutaneous PCO2 is a noninvasive measure of
tissue ventilation. This body sign can be useful for monitoring
cardiopulmonary decompensation and for additional real-time
assessment of the adequacy of tissue ventilation.
[0126] For real-time evaluation of respiration efficiency during
exercise, the non-invasive measurement of respiratory movement can
be employed. For example, it has been shown that breath frequency
undergoes changes when measured with an apparatus. The
disadvantages of direct ventilation monitoring devices include (1)
decreases in respiratory rate, (2) increases in tidal volume, (3)
subject awareness that breathing is being monitored, (4) limited
subject mobility, (5) difficult to implement in children, and (6)
inability to implement for long term studies. These issues can all
be detrimental if they occur during ordinary or everyday exercise
situations.
[0127] In light of these problems with direct measurement of
respiration, some scientific investigators have shown that
respiration volume can be measured indirectly and non-invasively by
recording motions of the chest. Respiratory motion reflects change
in thoracic gas volume which under most circumstances is equivalent
to spirometry measurements of tidal volume. Studies of the
volume-pressure relationship of the ribcage and abdomen have shown
that compartmental volume change or the volume exchange at the
mouth is approximately equal to the sum of the volume change of the
ribcage and abdominal compartments. While the contribution of these
motions changes with posture, these values among others are
alternatively used in the present invention as indicators of
respiratory efficiency of an individual.
Multi-Sensor Body Sounds, Vital Signs, and Motions Monitoring
System
[0128] The system of the invention includes a data acquisition
module which consists of several sensors for measuring body sounds,
vital signs, and motions continuously and a data input unit that is
connected to a computing device. For convenience of operation and
transport, all the hardware systems may be embedded in one overall
system unit.
[0129] For sound measurements, the acoustic sensors can be of any
types that are sufficiently sensitive to acquire body sounds. These
may include, but are not limited to, electronic stethoscopes,
microphones, accelerometers, or special-purpose body sound sensors.
The sensors will be attached to the designated auscultation sites
and noise reference locations. In order to obtain noise
measurements that represent the lumped impact of distributed and
multi-source noises from the heart, lung, and other sound sensors,
the noise reference sensors will be placed in the vicinity of the
sound sensors. Some of the types of acoustic sensors require
amplifiers to enhance sensitivity and signal/noise ratios. In these
cases, amplifiers will be either connected to the sensors or
embedded with the sensors in compact packaging. The outputs of the
sensors will be connected to the data acquisition unit through
signal wire interfacing, analog or digital, such as serial ports,
USB ports, or wireless connections.
[0130] Other body signs and motions will be measured by respective
sensors. For example, chest movements can be measured by pressure
or motion sensors attached to a chest strap. Blood oxygen levels
can be measured by a pulse oximeter. ECG can be measured with
electromagnetic sensors.
[0131] The main software is embodied in a Body Sound/Signal
Analyzer Processing System that contains all the modules for
processing body sounds, vital signs, and motions . The signals are
first conditioned and synchronized by the "Data Acquisition"
module. To obtain authentic signals for body sounds, vital signs,
and motions, signals are filtered to remove off-band and
independent noises by the "Filtering" module and "ANC" module. A
new advanced noise cancellation technique, embodied in the module
"Time Shared Noise Cancellation", has been developed to remove
in-band and correlated noises. The "Signal Separation" module
embodies the new cyclic system reconfiguration method to separate
interfered signals. The "Pattern Recognition" module employs a
stochastic pattern recognition algorithm that extracts key
parameters for characterizing signal patterns with quantitative
confidence levels. Then, the "Diagnosis" module identifies abnormal
respiratory, cardiac, or other related conditions and diseases.
Finally, the "Display and Storage" module provides a user interface
for sound pattern feedback and display, information storage, and
diagnostic outputs.
Noise Reduction
[0132] The noise reduction methodology of U.S. application Ser. No.
11/367,807 is uniquely designed to reduce the effect of
signal/noise correlation. This method was derived on the basis of
the unique nature of biological signals such as body sounds: (1)
Breathing, heart, and upper airway sounds are not stationary, and
usually have distinctive stages (inhale, exhale, and transitional
pause in lung sounds, for example). (2) Sounds in signal-intensive
stages, such as inhale and exhale stages in lung sounds, contain
rich information about related body functions and can be processed
for diagnosis. (3) During transitional pause, body sounds are very
small and noises are dominant.
[0133] The noise canceling approach of this invention combines this
unique method with the prior regular filtering techniques. The new
method first uses a band-pass filter to eliminate the off-band
noises (for example, sensors rubbing with skin or chest movement).
After-filtering signals are then used in conducting channel
identification during the pause interval, and noise cancellation
during the signal-intensive stages. Upon establishing a reliable
model of noise transmission channels, noise cancellation can be
achieved even when signal and noise are highly correlated during
inhale and exhale. Therefore, the method introduced in this
invention complements the traditional filtering and ANC for
applications in which time-varying statistical features render ANC
ineffective, leading to significantly improved quality of noise
cancellation.
[0134] The method of time-shared adaptive noise cancellation has
been shown to reduce the impact of inherent noises on accuracy of
sound pattern recognition [20,20,21], The method of the present
invention utilizes the unique features of lung sounds, heart
sounds, snoring, and other body sounds. By combining cyclically
reconfigured system identification for channel modeling,
frequency-domain filtering, stochastic noise separation, the
present method provides a far more robust and effective noise
reduction than what was included in prior patents. Prior method
patents proposed use of signal magnitudes and slopes to separate
noise and signals. It is well known that such separations are not
applicable to most noise cancellation cases. The noise cancellation
method of the present invention includes the following new
features. For concreteness, the detailed descriptions are given in
examples with reference to lung sound, heart sound, and related
respiratory signals. These are not to be viewed as the only domain
of applications of this technology.
[0135] 1. A virtual noise representation by placing noise reference
sensors at strategically selected locations. These locations have
two key requirements: (1) They do not receive too much targeted
signals such as lung, heart or, snoring sounds. (2) They are
relatively close to signal sensors such as those for lung, heart,
or snoring sounds. Typical locations include shoulders, arms, but
are not limited to these.
[0136] Location proximity between the targeted signals and
reference sensors allows representation of noises from many sources
to be approximated by a lumped noise near the reference sensor. The
method replaces distributed noise sources (which are impossible to
describe accurately and separately) with a lumped noise source.
[0137] 2. Cyclic separation of phases in signals such as lung,
heart, and snoring sounds. In this example, while the overall
sounds of heart, lung and snoring are not stationary processes,
signals that are confined in separate stages are approximately
stationary. For example, for lung sounds, the phases are inhale,
exhale, and pause. For heart sounds, the phases are systolic, and
pause. Mathematically, if all inhale segments of a breathing sound
are extracted and concatenated into a single waveform, then this
waveform is approximately stationary. This formulation allows this
invention to apply powerful modeling and signal processing
methodologies that are applicable only to stationary processes.
[0138] 3. Time-shared noise cancellation. It is observed that due
to diminishing lung sounds during the pause interval, the
correlation between the sound and noise in the pause interval is
much smaller than that for inhale and exhale processes, leading to
our time-shared adaptive noise cancellation algorithm. The measured
lung sound during the pause stage is essentially the output of the
noise channel in that interval. As a result, we can use
input/output pair to identify the noise transmission channel in
this interval. This will not require any assumption regarding
independence of signals and noises. The key steps in the algorithm
are:
[0139] (1) During a pause stage, the measured noise reference
(virtual input) and lung sound (output) are used to identify the
noise channel.
[0140] (2) During the inhale and exhale phases, the estimated noise
channel model is used to extract the original lung sound.
[0141] 4. Recursive algorithms for channel identification. Adaptive
filtering and stochastic approximation algorithms are used to
derive recursive algorithms to update noise channel models and to
achieve noise cancellation, from cycle to cycle. This
cycle-to-cycle recursion is computationally very efficient since
models are updated by using only new measurements and no past data
needs to be stored or remembered. Also, by gradually discarding old
data via, for example, exponential discarding data windows, this
method can in fact track time-varying channel characteristics, that
can be used in continuous monitoring and diagnosis of breath
sounds.
[0142] 5. Enhanced method of noise cancellation by combining
time-shared adaptive noise cancellation with filtering and
stochastic separation. The time-shared noise cancellation is
further enhanced by targeted filtering and stochastic
separation.
[0143] 6. Individually targeted frequency filtering. The novelty of
this feature of the invention is to identify an individual
patient's baseline frequency ranges for targeted diagnosis
conditions (such as "normal" and "crackle") from initial data.
These frequency ranges are then used to generate an individualized
frequency filter that separates signals outside these frequency
ranges since they are irrelevant to diagnosis targets.
Signal Separation
[0144] Signal separation involves two source signals s1 and s2. For
example, in heart/lung sound separation problems, s1 is the heart
sound and s2 is the lung sound. The measurements x1 and x2 are
subject to cross interference from both source signals. A typical
example in medical applications is separation of heart and lung
sounds. In this case, the original source signals are heart and
lung sounds. Their measurements, either by using stethoscopes or
acoustic sensors, are subject to signal interference in which both
heart and lung sounds are heard in each measured signal. The signal
transmission channels are unknown. The goal is to generate
authentic source signals s1 and s2 by using only the measurements
x1 and x2. Since the channel transfer functions are unknown and may
vary with time and/or operating conditions, they must be identified
in real time. As a result, separation of heart from lung sounds
becomes a problem of adaptive signal separation.
[0145] One key feature used in this invention for signal separation
is the cyclic nature of these two signals: Each signal undergoes
phases: signal emerging (inhale and exhale for lung sounds and
heart beating for heart sound) and pausing (lung sound pausing in
between inhale and exhale and heart sound pausing in between heart
beats). This invention discloses how these vital sign features can
be used effectively in separating the signals.
[0146] The main approach of cyclic system reconfiguration is
explained as follows. The 2.times.2 system has two signal sources
s1 and s2 and two observations x1 and x2. The observations are
assumed to be convolution sums of the source signals, with unknown
source-to-observation channels G12 (interference of sound 2 by
sound 1) and G21 (interference of sound 1 by sound 2). The signal
interference occurs when each observation contains signals from
both sources. The signals from each source before interference from
the other source are called p1 and p2, which are the authentic
sounds that can be heard during auscultation without interference.
The methodology of this invention is designed to recover p1 and p2.
It is understood by those versed in the art that if all
transmission channels are known, p1 and p2 can be directly
recovered by mathematical inversion of the 2.times.2 system.
[0147] But the signal transmission channels G12 and G21 are
unknown. As a result, obtaining p1 and p2 is a blind signal
separation (BSS) problem. There exist many approaches to the BSS
problem such as output de-correlation, higher order statistics,
neural network based methods, minimum mutual information and
maximum entropy, and geometric based methods. Although the
underlying principles and approaches of those standard methods are
different, most of these algorithms assume that the original
signals are statistically independent and the separation processes
are then dependent on this key property. The present invention
introduces a new method to identify the unknown transmission
channels by simplifying the complex BSS problem to a set of regular
identification problems without any constraints on the independence
of the source signals.
[0148] The-new method of U.S. patent application Ser. No.
11/367,807 requires that the source signals should have some
rhythms, namely the signals undergo intervals of existence and
almost non-existence sequentially and yet are non-synchronized.
Many biomedical signals bear these features, including for example
heart beats, lung sound, and snoring. The approach of U.S. patent
application Ser. No. 11/367,807 uses these features to reconfigure
iteratively the transmission channels so that the blind
identification problem can be reduced into a number of regular
identification problems.
[0149] The following intervals are consequently recognized by the
invention.
[0150] (1) Interval Class I: p1 is nearly zero and p2 is large.
[0151] In this case, x1=G21*p2 and x2=p2. As a result, sensor
measurements x1 and x2 during Interval Class I can be used to
identify the transmission channel G21.
[0152] (2) Interval Class II: p2 is nearly zero and p1 is
large.
[0153] In this case, x2=G12*p1 and x1=p1. As a result, sensor
measurements x1 and x2 during Interval Class II can be used to
identify the transmission channel G12.
[0154] Once the transmission channels have been identified, this
invention can get the desired separated signals p1 and p2 by
inverting the transmission system.
Body Sounds, Vital Signs, and Motions Pattern Recognition
[0155] It is well understood in pulmonary medicine that there are
no universal sound patterns or parameter thresholds that
definitively indicate a disease or medical condition much less
exertion level. Individualized pattern recognition that combines
information from body sounds, vital signs, and motions needs to be
established that is capable of capturing pattern shifting in each
individual athlete. To advance the frontier in computer-aided body
sound analysis to real-life applications, new methods are needed to
develop individualized pattern recognition techniques.
[0156] The pattern recognition methodology of the present invention
discloses a new technique of individualized pattern recognition and
diagnosis [20,26]. The key properties of pattern recognition
accuracy, confidence levels, noise impact, and noise reduction are
rigorously established. The invention starts with a set of
characterizing variables that can be extracted from body sounds,
vital signs, and motions. For an example of lung sounds, these
variables may include, but are not limited to, inhale length and
strength, exhale length and strength, breath cycle length, in the
time domain; and center frequency, power, frequency bandwidth, for
inhale and exhale individually, in the frequency domain. Changes in
these variables provide information to the invention algorithm for
determination of lung sound pattern variations. The goals of sound
pattern recognition and diagnosis in this invention include: (1) to
dynamically capture changes in these key parameters; (2) to relate
these changes to potential causes. The invention includes the
following improvements over prior pattern recognition methods:
[0157] 1. A general methodology to extract multiple parameters from
body sounds, vital signs, and motions that can be used to
characterize different patterns, depending on targeted
applications. These parameters include, as an example, heart rates,
and variability, respiratory rate, inhale and exhale duration and
strength, magnitude, frequency center, frequency band, etc.,
Although the above variables have been used in their individual
applications as useful characteristics of lung and heart sounds, a
general methodology of multi-variable analysis is new. The new
methodology is general and applicable if other parameters are
used.
[0158] 2. Individualized parameter distributions that are derived
from data using stochastic analysis methods. It is well known that
patient sound patterns vary dramatically and population patterns
are not a good approach for diagnosis. This invention makes it
possible to define individual baselines for diagnosis.
[0159] 3. A dynamic pattern tracking method that captures pattern
shifting in each person. The main issue for sound pattern
classification is to dynamically capture the changes of the
individualized key parameters. To detect pattern shifting, this
invention treats these calculated parameters, over each cycle of
body sounds, vital signs, and motions, as stochastic processes. A
method of windowed averaging with gradual data discarding is used
to track pattern changes in a patient.
Individualized Diagnosis
[0160] A method of optimally selecting diagnosis regions to
maximize accuracy of diagnosis is used. The method is based on a
stochastic optimization procedure that uses a multi-objective
performance index to minimize combined errors of "misdiagnosis" and
"false alarm." The invention method generates diagnosis regions
accurately, individually, and objectively. This is in contrast to
prior methods that use subjectively selected thresholds, which
depend on "population average values," or trial-and-error decision
processes.
[0161] The diagnosis module utilizes a recursive decision process
that is computationally efficient for continuously monitoring lung
sounds. This includes a recursive method which updates diagnosis
regions when new data have been acquired. Consequently, the method
of the invention does not need to compute the regions repeatedly
when observation of body sounds, vital signs, and motions produces
new parameters continuously over a long period of time.
Physiological Indices
[0162] The diagnosis module of the present invention will generate
physiological indices for physical effort, stress, fatigue, fitness
levels. The module takes as inputs the main parameters generated
from body sounds, vital signs, and motions by the pattern
recognition module, as well as activity levels from exercise
machines.
[0163] Activity level information from exercise machines and
facilities defines personal characteristics, and the type, the load
and duration of an exercise program. For example, for a treadmill,
a person's weight, platform incline angle, speed, and duration are
the parameters that define the activity level. Similarly, on a
stationary bicycle or rowing machine, the resistance and duration
become the activity level measurements.
[0164] Physical effort is a relative measure of a person's physical
activity. This can be measured by many possible variables,
depending on exercise goals. One typical example of physical effort
indicators is a combined measure of heart rate, respiratory rate,
and respiratory strength, and their variations. When a person
performs exercise, his/her heart rate, respiratory rate, and
respiratory strength increase. Relative increase of these
parameters from the person's normal values at rest before exercise
and the rate of this increase over the course of the exercise show
the person's physical effort in exercise. On the other hand, for
people with a specific goal of exercise, some other parameters may
be used. For instance, for cardiac exercise, one may use first or
second heart sounds as well heart rate to define physical effort
levels. An analogy may also be drawn for weight-loss exercise in
which integrated respiratory volumes over the period of exercise
will be more directly related to physical effort level in calorie
burning.
[0165] Fatigue levels are indicated by a combination of many
factors. When a person is exhausted during an exercise, his/her
heart rate, respiratory rate, respiratory volumes change, and also
his/her pace of exercise will deviate. Typically, a slowing-down in
the pace of bicycle peddling and/or certain body motion and
postures form a common scenario of fatigue.
[0166] Physical stress is an undesirable condition during exercise.
Short of breath, over-rated heart beating, panting in respiratory
sounds, acute asthma, are typical stress indicators. There are more
scientific and subtle signs of stress, such as heart beat
variations, that provide further useful information on physical
stress.
[0167] A person's fitness level can be derived from a relationship
among physical effort, activity level, and fatigue. An out-of-shape
person must make a huge effort for a relatively low level of
exercise activity. This is also reflected by relatively fast
increase in their fatigue. In contrast, a well-trained athlete can
endure high levels of activity with low effort and low fatigue.
[0168] This invention introduces a method and system that will use
data from body sound parameters, body signs, and activity levels to
generate measurable indices for physical effort, stress, fatigue,
fitness levels. These indices can be generically expressed as
nonlinear functions: [0169] I=f(hr,hrv,rr,rs,rv, al,ep, . . . )
where hr=heart rate, hrv=heart rate variation, rr=respiratory rate,
rs=respiratory strength, rv=respiratory volume, al=activity level,
ep=exercise pace, etc.
[0170] The actual function form for one specific application can be
derived by population studies, statistical analysis, and data
fitting. On the other hand, after establishing the function form
from a representative population and targeted goals, the function
can be further adapted to an individual by fine tuning its function
coefficients using the individual's exercise profiles and
historical data on his/her physical effort, among other
parameters.
Personal Identification and Workout Programs
[0171] A personal identification module of the present invention
allows direct and fast communication between the person and the
exercise facility. The module has the following main functions:
[0172] (1) The exercise machine will recognize the person by an
input device, such as a card scanner, RFID tag, IR reader, wireless
reader, etc.
[0173] (2) The workout history and designated current workout goal
will enter the machine. The machine will adjust its speed, load,
and duration accordingly.
[0174] (3) The current workout results will be entered to the
personal card or electronic memory storage device as part of the
training record that can be carried with the person.
Personal Trainer Module
[0175] The personal trainer module provides advice for exercise
levels and targets in real time, personalized to fit the individual
needs. Currently, the most common advice in an exercise machine is
the recommended range of heart rates, adjusted to a person's age.
The personal trainer module is a comprehensive functional software
that performs the following functions:
[0176] (1) In its display screen, an exercise level can be
identified as a color-coded region in the parameter space. For
example, when heart rate and respiratory rate are used jointly as
physical effort levels, a region can be an area on the space with
heart rate as the x-axis and respiratory rate as the y-axis.
Consequently, a target exercise level will become a target region
on the screen.
[0177] (2) To reach the target region gradually the module displays
the timed sequence of the intermediate desirable regions that move
toward the target region as guidance for the trainee.
[0178] (3) During an exercise, the module shows the physical effort
trajectory vs. suggested trajectories of desired regions and
provides suggestion in modifications in machine load (weight,
incline angles, resistance forces, etc.), intensity (speed, pace,
etc.), and duration.
[0179] (4) During and after exercises, the module derives
statistical data for the person to understand the current
performance levels, comparative charts of training progress, and
improvement of fitness levels, etc.
[0180] (5) In relation to the goals designated by the person or a
professional, the module adjusts target regions accordingly.
Personal Trainer Group Module
[0181] The main function of this module is to integrate data from
many individuals in a group, such as a class, a club, an
association, an age group, a population class, among others to
perform statistics and to produce comparative information to guide
and improve exercise programs.
[0182] The description of the invention is merely exemplary in
nature and, thus, variations that do not depart from the general
design of the invention are intended to be within the scope of the
invention. Such variations are not to be regarded as a departure
from the intent and scope of the invention.
REFERENCE KEYS IN FIGURES
[0183] 10 Athlete [0184] 20 Trainer [0185] 30 Vital Sign Sensor
[0186] 31 Acoustic Transducer [0187] 32 Chest Movement Sensor
[0188] 40 Filtering of Off-Band Noise [0189] 50 Adaptive Noise
Cancellation for Independent Noise Removal [0190] 55
DAQ/Filtering/Noise Removal Module [0191] 60 Time-Shared Adaptive
Noise Cancellation [0192] 70 Cyclic System Reconfiguration Method
for Signal Separation [0193] 75 Combined Cyclic System
Reconfiguration Method for Signal Separation and Noise Cancellation
[0194] 80 Adaptive Individualized Pattern Recognition [0195] 90
Real-Time Individualized Optimal Diagnosis [0196] 95 Body Sound
Analyzer System [0197] 100 Digital Display [0198] 112 Resistance
Sensor [0199] 114 Virtual Distance Sensor [0200] 115 Revolutions
Sensor [0201] 118 Incline Sensor [0202] 120 Weight/Level Sensor
[0203] 122 Repetitions Sensor [0204] 150 Activity Level Module
[0205] 180 PEMT Portable Digital Assistant System [0206] 185 PEMT
Portable Digital Assistant w/wireless System [0207] 190 Computer
System [0208] 200 Conventional Stethoscope System [0209] 210 Body
Sound/Signal Analyzer Module A [0210] 220 Body Sound/Signal
Analyzer Module B [0211] 230 Body Sound/Signal Analyzer Module C
[0212] 310 PEMT Vitals Analysis Module A [0213] 320 PEMT Vitals
Analysis Module B [0214] 400 Activity Level Mapping [0215] 410
Cardio Training Machine [0216] 420 Strength Training Machine [0217]
500 Personal Exercise Monitor and Trainer System [0218] 505
Personal Exercise Monitor and Trainer System w/ wireless [0219] 510
Personal Characteristics Input Module [0220] 520 Personal Fitness
Database [0221] 550 Expert Coach Module [0222] 600 Personal
Exercise Monitor and Trainer Class System [0223] 610 Personal
Exercise Monitor and Trainer Class Trainer Server [0224] 620
Personal Exercise Monitor and Trainer Class Contest Server [0225]
660 Network [0226] 670 Digital Projector [0227] 680 Projection
Screen [0228] 700 Personal Exercise Monitor and Trainer System
Enabled Gymnasium [0229] 710 Training Machine Database
REFERENCES
[0230] [1] N. Gavriely, Y. Palti, and G. Alroy: "Spectral
characteristics of normal breath sounds", J. Appl. Physiol., vol.
50, no. 2, pp. 320-324, February 1981.
[0231] [2] V. Iyer, P. Ramamoorthy, H. Fan and Y. Plolysonsang:
"Reduction of heart sounds from respiratory sounds by adaptive
filtering", IEEE Duns. Biomed. Eng., vol. 33, no. 12, pp.
1141-1148, 1986.
[0232] [3] L. J. Hadjileontiadis and S. M. Panas: "Adaptive
reduction of heart sounds from lung sounds using fourth-order
statistics", IEEE fiuns. Biomed. Eng., vol. 44, no. 7, pp. 642-648,
1997.
[0233] [4] Z. Moussavi "An overview of heart-noise reduction of
lung sound using wavelet transform based filter", Proceedings of
the 25.sup.th Annual International Conference of the IEEE, pp.
458-461, September 2003.
[0234] [5] Barschdorff, D.; Bothe, A.; Rengshausen, U., Heart sound
analysis using neural and statistical classifiers: a comparison.
Computers in Cardiology, 415-418, September 1989.
[0235] [6] Charleston, S.; Azimi-Sadjadi, M. R.; Gonzalez-Camarena,
R., Interference cancellation in respiratory sounds via a
multiresolution joint time-delay and signal-estimation scheme,
Biomedical Engineering, IEEE Transactions, 1006-1019, October
1997.
[0236] [7] Guo Z. Durand L G. Lee H C. Allard L. Grenier M C. Stein
P D. Artificial neural networks in computer-assisted classification
of heart sounds in patients with porcine bioprosthetic valves.
Medical & Biological Engineering & Computing. 32(3):311-6,
1994 May.
[0237] [8] Hadjileontiadis, L. J.; Panas, S. M. Adaptive reduction
of heart sounds from lung sounds using fourth-order statistics.
IEEE Transactions on Biomedical Engineering, 44 (7): 642-648,
1997.
[0238] [9] Hadjileontiadis, L. J.; Panas, S. M. Adaptive reduction
of heart sounds from lung sounds using wavelet-based filter. Stud.
Health Technol. Inform. 43 (Part B): 536-540, 1997.
[0239] [10] Haghighi-Mood, A.; Torry, J. N., Application of
advanced signal processing techniques in analysis of heart sound.
Signal Processing in Cardiography, IEE Colloquium, 8/1-8/5,
1995.
[0240] [11] Haghighi-Mood, A.; Torry, J. N. Time-varying filtering
of the first and second heart sounds, 18th Annual International
Conference of the IEEE, 950-951 vol. 3, November 1996.
[0241] [12] S. Haykin, Adaptive Filter Theory, Prentice-Hall,
Englewood Cliffs, N.J., 1990.
[0242] [13] S. Haykin, ed. Unsupervised Adaptive Filtering, Vol. I
and II, John Wiley & Sons, Inc., 2000.
[0243] [14] Kompis M. Russi E. Adaptive heart-noise reduction of
lung sounds recorded by a single microphone. Proc. Annual
International Conference of the IEEE, Vol. 2, 691-692, 1992.
[0244] [15] Longhini C. Portaluppi F. Arslan E. Pedrielli F. The
fast Fourier transform in the analysis of the normal
phonocardiogram. Japanese Heart Journal. 20(3):333-9, 1979 May.
[0245] [16] Lu Y S. Liu W H. Qin G X. Removal of the heart sound
noise from the breath sound. Engineering in Medicine and Biology
Society, 1988., Proceedings of the Annual International Conference
of the IEEE, 175-176 vol. 1, November 1988.
[0246] [17] Pasterkamp H. Kraman S. Wodicka G. Respiratory sounds.
Am. J. Respir Crit Care Med. Vol. 156: 974-987, 1997.
[0247] [18] B. Widrow and S. D. Stearns, Adaptive Signal
Processing. Prentice-Hall, Englewood Cliffs, N.J., 1985.
[0248] [19] Hong Wang, Han Zheng, Le Yi Wang, Howard J. Normile,
Jeremy Nofs, Adaptive Noise Cancellation and Lung/Heart Sounds
Extraction Via Time-split Transmission Channel Reconfiguration,
WSEAS Transactions on Biology and Biomedicine, Issue 3, Volume 3,
pp. 204-211, March 2006.
[0249] [20] Razmig Haladjian, Hong Wang, Le Yi Wang, Han Zheng,
"Computer-Aided Continuous Lung Sound Auscultation in Ventilated
Patients", Annual Conference of American Society of
Anesthesiologists, Las Vegas, October 2004.
[0250] [21] H. Wang, L. Y. Wang, H. Zheng, R. Haladjian, M. Wallo,
Lung sound/noise separation in anesthesia respiratory monitoring,
WSEAS Transactions on Systems, Vol. 3, pp. 1839-1844, June
2004.
[0251] [22] Le Yi Wang, Hong Wang, Han Zheng, and George Yin,
"Multi-Sensor Lung Sound Extraction Via Time-Shared Channel
Identification and Adaptive Noise Cancellation", 2004 IEEE Control
and Decision Conference, December 2004.
[0252] [23] L. Y. Wang, G. Yin, H. Wang, Identification of Wiener
Models with Anesthesia Applications, Int. J. of Pure and Applied
Mathematical Sciences, pp. 35-61, 2004.
[0253] [24] Le Yi Wang and Hong Wang, Computers in Anesthesia, in
Encyclopedia of Medical Devices & Instrumentation, 2nd Edition,
Edited by Dr. John G. Webster, John Wiley \& Sons, Inc.,
February 2006.
[0254] [25] Hong Wang, Han Zheng, Le Yi Wang, Howard J. Normile,
Jeremy Nofs, Separation of Lung and Heart Sound for Anesthesia
Diagnosis, Proceedings of the 2006 WSEAS International Conference
on Mathematical Biology and Ecology (MABE '06), Miami, Fla., USA,
Jan. 18-20, 2006 (pp 63-68).
[0255] [26] H. Zheng, H. Wang, L. Y. Wang, and G. Yin, Time-Shared
Channel Identification for Adaptive Noise Cancellation in Breath
Sound Extraction, Journal of Control Theory and Applications, Vol.
2, No. 3, pp. 209-221, August 2004.
[0256] [27] Han Zheng, Hong Wang, Le Yi Wang, and George Yin, "Lung
Sound Pattern Analysis for Anesthesia Monitoring", 2005 American
Control Conference, June 2005.
[0257] [28] Han Zheng, Le Yi Wang, Hong Wang, Cyclic System
Reconfiguration for Adaptive Separation of Lung and Heart Sounds,
2006 ACC Conference, Minneapolis, Jun. 14-16, 2006.
* * * * *