U.S. patent application number 14/753062 was filed with the patent office on 2016-12-29 for system and method for implementing personal emergency response system based on uwb interferometer.
The applicant listed for this patent is ECHOCARE TECHNOLOGIES LTD.. Invention is credited to Yossi Kofman, Rafi ZACK.
Application Number | 20160379474 14/753062 |
Document ID | / |
Family ID | 57483982 |
Filed Date | 2016-12-29 |
United States Patent
Application |
20160379474 |
Kind Code |
A1 |
ZACK; Rafi ; et al. |
December 29, 2016 |
SYSTEM AND METHOD FOR IMPLEMENTING PERSONAL EMERGENCY RESPONSE
SYSTEM BASED ON UWB INTERFEROMETER
Abstract
A non-wearable Personal Emergency Response System (PERS)
architecture is provided, having a synthetic aperture antenna based
RF interferometer followed by two-stage human state classifier and
abnormal states pattern recognition. In addition, it contains a
communication sub-system to communicate with the remote operator
and centralized system for multiple users' data analysis. The
system is trained to learn the person's body features as well as
the home environment. The decision process is carried out based on
the instantaneous human state (Local Decision) followed by abnormal
states patterns recognition (Global decision). The system global
decision (emergency alert) is communicated to the operator through
the communication system and two-ways communication is enabled
between the monitored person and the remote operator. In some
embodiments, a centralized system (cloud) receives data from
distributed PERS systems to perform further analysis and upgrading
the systems with updated database (codebooks).
Inventors: |
ZACK; Rafi; (Kiryat-Ono,
IL) ; Kofman; Yossi; (Raanana, IL) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
ECHOCARE TECHNOLOGIES LTD. |
Beer Sheva |
|
IL |
|
|
Family ID: |
57483982 |
Appl. No.: |
14/753062 |
Filed: |
June 29, 2015 |
Current U.S.
Class: |
340/539.11 |
Current CPC
Class: |
G08B 25/016
20130101 |
International
Class: |
G08B 25/01 20060101
G08B025/01 |
Claims
1. A non-wearable monitoring system comprising: a radio frequency
(RF) interferometer configured to transmit signals at a specified
area and receive echo signals via an antenna array; an
environmental clutter cancellation module configured to filter out
static non-human related echo signals; a human state feature
extractor configured to extract from the filtered echo signals, a
quantified representation of position postures, movements, motions
and breathing of at least one human located within the specified
area; a human state classifier configured to identify a most
probable fit of human current state that represents an actual human
instantaneous status; and an abnormality situation pattern
recognition module configured to apply a pattern recognition based
decision function to the identified states patterns and determine
whether an abnormal physical event has occurred to the at least one
human in the specified area.
2. The system according to claim 1, wherein the extracted features
are vector quantized, and wherein the classifier is configured to
find the best match to a codebook which represents the state being
a set of human instantaneous condition/situation which is based on
said quantized features.
3. The system according to claim 1, wherein the RF interferometer
is an ultra-wide band (UWB) RF interferometer which includes: a
multiple synthetic aperture antennas arrays; UWB pulse generator,
UWB transmitter and UWB receiver configured to capture echo signal
from every antenna and every array.
4. The system according to claim 1, wherein the environmental
clutter cancellation module comprises a static environment detector
configured to ensure that no human body at the environment, static
clutter estimator and static clutter subtraction.
5. The system according to claim 1, wherein the human state
features extractor comprises: a back-projection unit configured to
estimate the reflected clutter from a specific voxel to extract the
human position and posture features; a Doppler estimator configured
to extract the human motions and breathing features; and a features
vector generator configured to create a quantized vectors of the
extracted features.
6. The system according to claim 1, wherein the human state
classifier comprises a training unit configured to quantize the
known states features vectors and generate the states code-vectors;
a distance function configured to measure the distance between
unknown tested features vectors and pre-defined known code-vectors;
and a classifier unit configured to find the best fit between
unknown tested features vector and pre-determined code-vectors set,
classifier output consisting of the most probable state and the
relative statistical distance to the tested features vector.
7. The system according to claim 1, wherein the abnormality pattern
recognition module comprises: a training unit configured to
generate the set of abnormal states patterns as a reference
codebook, and set of states transition probabilities, and states
patterns matching function to find and alert on a match between a
tested states pattern and the pre-defined abnormal pattern of the
codebook.
8. The system according to claim 1, further comprising a
communication sub-system configured to communicate an alert upon
determining of an abnormal physical event.
9. The system according to claim 8, wherein the communication
sub-system comprises: a signaling link configured to transmit the
system alerts to far end, a two way voice and video communication
to interact with the monitored person, and two-way data link to
remotely upgrade the system.
10. The system according to claim 8, further comprising a remote
centralized data analyzing unit comprising: a data collection unit
to receive the monitoring and alerts units' data, data analyzer to
find new abnormal patterns based on multiple users situations,
abnormal patterns codebook generator to update the codebook with
the new abnormal patterns.
11. The system according to claim 1, configured to operate with
similar systems in a master-slave configuration in which the RF
interferometer and set of antennas are configured to act as a
repeater communicating between at least two systems.
12. The system according to claim 1, wherein parameters obtained in
a training sequence are used to configure the human state
classifier per a specific person.
13. The system according to claim 12, wherein the trained
environmental parameters are calculated by monitoring a human in
various locations and positions in a predefined order.
14. The system according to claim 7, wherein the abnormal patterns
reference codebook is remotely updated with new abnormal patterns
received from data analysis by multiple users.
15. The system according to claim 1, wherein the system further
includes an interface with at least one of: a wearable medical
sensor configured to sense vital signs of the human, and a home
safety sensor configured to sense ambient conditions at said
specified area, and wherein data from said at least one sensor are
used by said decision function for improving the decision whether
an abnormal physical event has occurred to the at least one human
in said specified area.
Description
FIELD OF THE INVENTION
[0001] The present invention relates to the field of elderly
monitoring, and more particularly, to a system architecture for
personal emergency response system (PERS).
BACKGROUND OF THE INVENTION
[0002] Elderly people have a higher risk of falling, for example,
in residential environments. As most of elder people will need
immediate help after such a fall, it is crucial that these falls
are monitored and addressed upon in real time. Specifically, one
fifth of falling elders are admitted to hospital after staying on
floor for over one hour following a fall. The late admission
increases the risk of dehydration, pressure ulcers, hypothermia,
and pneumonia. Acute falls leads to high psychological effect of
fear and high impact on daily life quality.
[0003] Most of the existing personal emergency response systems
(PERS), which take the form of fall detectors and alarm buttons,
are wearable devices. These wearable devices have several
disadvantages. First, they cannot recognize the human body
positioning and posture.
[0004] Second, they suffer from limited acceptance and use due to:
Elders' perception and image issues, high rate of false alarms and
miss-detects, elders neglect re-wearing when getting out of bed or
bath, and, and long term usage of wearable might lead to user skin
irritations. Third, the wearable PERS are used mainly after
experiencing a fall (very limited addressable market).
[0005] Therefore, there is a need for a paradigm shift toward
automated and remote monitoring systems.
SUMMARY OF THE INVENTION
[0006] Some embodiments of the present invention provide a unique
sensing system and a breakthrough for the supervision of the
elderly during their stay in the house, in general, and detect
falls, in particular. The system may include: a UWB-RF
Interferometer, Vector Quantization based Human states classifier,
Cognitive situation analysis, communication unit and processing
unit.
[0007] According to some embodiments of the present invention, the
system may be installed in the house's ceiling, and covers a
typical elder's apartment with a single sensor, using
Ultra-Wideband RF technology. It is a machine learning based
solution that learns the elder's unique characteristics (e.g.,
stature, gait and the like) and home primary locations (e.g.
bedroom, restroom, bathroom, kitchen, entry, etc.), as well as the
home external walls boundaries.
[0008] According to some embodiments of the present invention, the
system may automatically detect and alert emergency situation that
might be encountered by elders while being at home and identify the
emergency situations.
[0009] According to some embodiments of the present invention, the
system may detect falls of elderly people, but may also identify
other emergencies situations, such as labor briefing, sleep apnea,
as well as other abnormal cases, e.g., sedentary situation,
repetitive non-acute falls that are not reported by the person. It
is considered as a key element for the elderly connected smart
home, and, by connecting the system to the network and cloud, it
can also make a use of big data analytics to identify new patterns
of emergencies and abnormal situations.
[0010] These, additional, and/or other aspects and/or advantages of
the present invention are set forth in the detailed description
which follows; possibly inferable from the detailed description;
and/or learnable by practice of the present invention.
BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The subject matter regarded as the invention is particularly
pointed out and distinctly claimed in the concluding portion of the
specification. The invention, however, both as to organization and
method of operation, together with objects, features, and
advantages thereof, may best be understood by reference to the
following detailed description when read with the accompanying
drawings in which:
[0012] FIG. 1 is a block diagram illustrating a non-limiting
exemplary architecture of a system in accordance with embodiments
of the present invention
[0013] FIG. 2 is another block diagram illustrating the
architecture of a system in further details in accordance with
embodiments of the present invention;
[0014] FIG. 3 is a diagram illustrating conceptual 2D Synthetic
Aperture Antennas arrays in accordance with some embodiments of the
present invention;
[0015] FIG. 4 is a table illustrating an exemplary states
definition in accordance with some embodiments of the present
invention;
[0016] FIG. 5 is a table illustrating an exemplary states matrix in
accordance with some embodiments of the present invention;
[0017] FIG. 6 is a table illustrating an exemplary abnormal
patterns in accordance with some embodiments of the present
invention; and
[0018] FIG. 7 is a diagram illustrating a cloud based architecture
of the system in accordance with embodiments of the present
invention;
[0019] FIG. 8 is a floor plan diagram illustrating initial
monitored person training as well as the home environment and
primary locations training in accordance with embodiments of the
present invention; and
[0020] FIG. 9 is a diagram illustrating yet another aspect in
accordance with some embodiments of the present invention.
[0021] It will be appreciated that for simplicity and clarity of
illustration, elements shown in the figures have not necessarily
been drawn to scale. For example, the dimensions of some of the
elements may be exaggerated relative to other elements for clarity.
Further, where considered appropriate, reference numerals may be
repeated among the figures to indicate corresponding or analogous
elements.
DETAILED DESCRIPTION OF THE INVENTION
[0022] With specific reference now to the drawings in detail, it is
stressed that the particulars shown are by way of example and for
purposes of illustrative discussion of the preferred embodiments of
the present invention only, and are presented in the cause of
providing what is believed to be the most useful and readily
understood description of the principles and conceptual aspects of
the invention. In this regard, no attempt is made to show
structural details of the invention in more detail than is
necessary for a fundamental understanding of the invention, the
description taken with the drawings making apparent to those
skilled in the art how the several forms of the invention may be
embodied in practice.
[0023] Before at least one embodiment of the invention is explained
in detail, it is to be understood that the invention is not limited
in its application to the details of construction and the
arrangement of the components set forth in the following
description or illustrated in the drawings. The invention is
applicable to other embodiments or of being practiced or carried
out in various ways. Also, it is to be understood that the
phraseology and terminology employed herein is for the purpose of
description and should not be regarded as limiting.
[0024] FIG. 1 is a block diagram illustrating a non-limiting
exemplary architecture of a system 100 in accordance with
embodiments of the present invention. System 100 may include a
radio frequency (RF) interferometer 120 configured to transmit
signals via Tx antenna 101 and receive echo signals via array 110-1
to 110-N. It should be noted that transmit antennas and receive
antennas may take different form and according to a preferred
embodiment, in each antenna array they may be a single transmit
antenna and several receive antennas. An environmental clutter
cancellation module may or may not be used to filter out static
non-human related echo signals. System 100 may include a human
state feature extractor 130 configured to extract from the filtered
echo signals, a quantified representation of position postures,
movements, motions and breathing of at least one human located
within the specified area. A human state classifier may be
configured to identify a most probable fit of human current state
that represents an actual human instantaneous status. System 100
may include a abnormality situation pattern recognition module 140
configured to apply a pattern recognition based decision function
to the identified states patterns and determine whether an abnormal
physical event has occurred to the at least one human in the
specified area. A communication system 150 for communicating with a
remote server and end-user equipment for alerting (not shown here).
Communication system 150 may further include two-way communication
system between the caregiver and the monitored person for real-time
assistance.
[0025] FIG. 2 is another block diagram illustrating the
architecture of a system in further details in accordance with some
embodiments of the present invention as follows:
[0026] UWB-RF interferometer 220--this unit transmits an Ultra
wideband signal (e.g., pulse) into the monitored environment and
receives back the echo signals from multiple antenna arrays to
provide a better spatial resolution by using the Synthetic Antenna
Aperture approach. In order to increase the received
signal-to-noise (SNR), the transmitter sends multiple UWB pulse and
receiver receives and integrates multiple echo signals (processing
gain). The multiple received signals (one signal per each Rx
Antenna) are sampled and digitally stored for further signal
processing.
[0027] Environmental Clutter Cancellation 230. The echo signals are
pre-processed to reduce the environmental clutter (the unwanted
reflected echo components that are arrived from the home walls,
furniture, etc.). The output signal mostly contains only the echo
components that reflected back from the monitored human body.
Environmental Clutter Cancellation 230 is fed with the trained
environmental parameters 232. In addition, the clutter cancellation
includes a stationary environment detection (i.e., no human body at
zone) to retrain the reference environmental clutter for doors or
furniture movement cases.
[0028] Feature extraction 240--The "cleaned" echo signals are then
processed to extract the set of features that will be used to
classify the instantaneous state of the monitored human person
(e.g. posture, location, motion, movement, breathing). The set of
the extracted features constructs the feature vector that is the
input for the classifier.
[0029] Human state classifier 250--The features vector is entered
to a Vector Quantization based classifier that classifies the
instantaneous features vector by statistically finding the closest
pre-trained state out of a set of N possible states, i.e., finding
the closest code vector (centroid) out of all code vectors in a
codebook 234. The classifier output is the most probable states
with its relative probability (local decision).
[0030] Cognitive Situation Analysis (CSA) 260--This unit recognizes
whether the monitored person is in an emergency or abnormal
situation. This unit is based on a pattern recognition engine
(e.g., Hidden Markov Model--HMM, based). The instantaneous states
with their probabilities are streamed in and the CSA search for
states patterns that are tagged as emergency or abnormal patterns,
such as a fall. These predefined patterns are stored in a patterns
codebook 234. If case that CSA recognizes such a pattern, it will
send an alarm notification to the healthcare center or family care
giver through the communication unit (e.g., Wi-Fi or cellular).
[0031] Two-way voice/video communication unit 150--this unit may be
activated by the remote caregiver to communicate with the monitored
person when necessary.
[0032] The UWB-RF interferometer unit 220 may include the following
blocks:
[0033] Two-dimensional UWB antenna array 110-1-110-N to generate
the synthetic aperture through all directions, followed by antenna
selector.
[0034] UWB pulse generator and Tx RF chain to transmit the pulse to
the monitored environment
[0035] UWB Rx chain to receive the echo signals from the antenna
array followed by analog to digital converter (ADC).
[0036] The sampled signals (from each antenna) are stored in the
memory, such as SRAM or DRAM.
[0037] In order to increase the received SNR, the RF interferometer
repeats the pulse transmission and echo signal reception per each
antenna (of the antenna array) and coherently integrates the
digital signal to improve the SNR.
Environmental Clutter Cancellation
[0038] The environmental clutter cancellation is required to remove
the unwanted echo components that are reflected from the
apartment's static items as walls, doors, furniture, etc.
[0039] The clutter cancellation is done by subtracting the unwanted
environmental clutter from the received echo signals. The residual
clutter represents the reflected echo signals from the monitored
human body.
[0040] According to some embodiments of the present invention, the
clutter cancellation also includes stationary environment detection
to detect if no person at the environment, such as when the person
is not at home, or is not at the estimated zone. Therefore, a
periodic stationary clutter check is carried out and new reference
clutter fingerprint is captured when the environment is identified
as stationary.
[0041] The system according to some embodiments of the present
invention re-estimates the environmental clutter to overcome the
clutter changes due to doors or furniture movements.
Multiple Features Extraction
[0042] The "cleaned" echo signal vectors are used as the raw data
for the features extraction unit. This unit extracts the features
that mostly describe the instantaneous state of the monitored
person. The following are examples for the set of the extracted
features and the method it's extracted:
[0043] Position--the position is extracted as the position (in case
of 2D--angle/range, in case of 3D--x,y,z coordinates) metrics
output of each array baseline. The actual person position at home
will be determined as a "finger print" method, i.e., the most
proximity to the pre-trained home position matrices (centroids)
codebook.
[0044] Posture--the person posture (sitting, standing, and laying)
will be extracted by creating the person "image" by using, e.g., a
back-projection algorithm.
[0045] Both position and posture are extracted, for example, by
operating, e.g., the Back-projection algorithm on received echo
signals--as acquired from the multiple antennas array in SAR
operational mode.
[0046] The following is the used procedure to find the human
position and posture:
[0047] Dividing the surveillance space into voxels (small cubic) in
cross range, down range and height
[0048] Estimating the reflected EM signal from a specific voxel by
the back projection algorithm
[0049] Estimating the human position by averaging the coordinates
of the human reflecting voxels for each baseline (Synthetic
Aperture Antenna Array).
[0050] Triangulating all baselines' position to generate the human
position in the environment
[0051] Estimating the human posture by mapping the human related
high-power voxels into the form-factor vector
[0052] Tracking the human movements in the environment (bedroom,
restroom, etc.)
[0053] Human motion--The monitored human body may create vibrations
and other motions (as gestures and gait). Therefore, it introduces
frequency modulation on the returned echo signal. The modulation
due to these motions is referred to as micro-Doppler (m-D)
phenomena. The human body's motion feature is extracted by
estimating the micro-Doppler frequency shift vector at the target
distance from the system (down range).
[0054] Human breathing--During the breathing (respiration) the
chest wall moves. The average respiratory rate of a healthy adult
is usually 12-20 breaths/min at rest (.about.0.3 Hz) and 35-45
breaths/min (.about.0.75 Hz) during labored breathing. The
breathing frequency feature is extracted by estimating the spectrum
on the slow-time sampled received echo signal at the target
distance (down range) from the system.
[0055] The features vector is prepared by quantizing the extracted
features with a final number of bits per field and adding the time
stamp for the prepared vector. This vector is used as the entry
data for the human state classifier (for both training and
classifying stages).
Human State Classifier
[0056] The Human state classifier is a VQ (Vector Quantization)
based classifier. This classifier consists of two main phases:
[0057] Training phase--it's done offline (supervised training) and
online (unsupervised training), where a stream of features vectors
reflecting various states are used as a preliminary database for
vector quantization and finding the set of code-vectors (centroids)
that sufficiently representing the instantaneous human states. The
set of the calculated code-vectors are called codebook. Some
embodiments of the training sessions are provided in more details
hereinafter.
[0058] Classifying phase--it's executed during the online operation
while an unknown features vector is entered into the classifier and
the classifier determines what the most probable state that it
represents. The classifier output is the determined states and the
set of the measured statistical distances (probabilities), i.e.,
the probability of State-i given the observation-O (the features
vector). The aforementioned probability scheme may be formulated
by: P (Si|O). The determined instantaneous state is called "Local
Decision".
[0059] The VQ states are defined as the set of instantaneous states
at various locations at the monitored home environment. Therefore,
any state is a 2 dimension results which is mapped on the VQ state
matrix.
[0060] The State matrix consists of the state (row) and location
(Column) followed by a time stamp. Typical elderly home environment
consists of the specific locations (Primary zones) and others
non-specified locations (Secondary zones). State is defined as the
combination of posture/motion at a specific location (e.g. S.sup.21
will indicate sleeping at Bedroom).
[0061] FIG. 3 is a diagram illustrating conceptual 2D Synthetic
Aperture Antennas arrays in accordance with some embodiments of the
present invention. Antenna array system 300 may include several
arrays of antennas 320, 330, 340, and 350. Each row may have at
least one transmit antenna and a plurality of receive antennas. The
aforementioned non-limiting exemplary configuration enables to
validate a location of a real target 310 by eliminating the
possible images 310A and 310B after checking reflections received
at corresponding arrays of antennas 330 and 320, respectively. It
is well understood that the aforementioned configuration is a
non-limiting example and other antennas configurations may be used
effectively.
[0062] FIG. 4 is a table 400 illustrating an exemplary states
definition in accordance with some embodiments of the present
invention.
[0063] FIG. 5 is a table 500 illustrating an exemplary states
matrix in accordance with some embodiments of the present
invention.
Cognitive Situation Analysis (CSA)
[0064] The CSA's objective is to recognize the abnormal human
patterns according to a trained model that contains the possible
abnormal cases (e.g., fall). The core of the CSA, in this
embodiment, may, in a non-limiting example a Hidden Markov Model
(HMM) based pattern recognition.
[0065] The CSA engine searches for states patterns that are tagged
as an emergencies or abnormal patterns. These predefined patterns
are stored in a patterns codebook.
[0066] The output of the CSA is the Global recognized human
situation.
[0067] FIG. 6 is a table 600 illustrating exemplary abnormal
patterns in accordance with some embodiments of the present
invention. It can be seen that in the first abnormal case (Critical
fall), it appears that the person was sleeping in the leaving room
(S25), then was standing (S45) and immediately fell down (S65). He
stayed on floor (S15) and start being in stress due to high
respiration rate (S75).
[0068] The CSA may contain additional codebook (irrelevant
codebook) to identify irrelevant patterns that might mislead the
system decision.
Communication Unit
[0069] The communication unit creates the channel between the
system and the remote caregiver (family member or operator center).
It may be based on either wired (Ethernet) connectivity or wireless
(e.g., cellular or WiFi communication or any other communication
channel).
[0070] The communication unit provides the following
functionalities: [0071] 1. This unit transmits any required ongoing
situation of the monitored person and emergency alerts. [0072] 2.
It enables the two way voice/video communication with the monitored
person when necessary. Such a communication is activated either
automatically whenever the system recognizes an emergency situation
or remotely by the caregiver. [0073] 3. It enables the remote
system upgrades for both software and updated codebooks (as will be
in further detail below) [0074] 4. It enables the communication to
the centralized system (cloud) to share common information and for
further big data analytics based on multiple deployments of such
innovated system
[0075] FIG. 7 is a diagram illustrating cloud-based architecture
700 of the system in accordance with embodiments of the present
invention. Raw data history (e.g., states stream) is passed from
each local system 100A-100E to the central unit located on a cloud
system 710 and performs various data analysis to find correlation
of states patterns among the multiple users' data to identify new
abnormal patterns that may be reflected just before the recognized
abnormal pattern. New patterns code vectors will be included to the
CSA codebook and cloud remotely updates the multiple local systems
with the new code-book. The data will be used to analyze daily
operation of local system 100A-100E.
[0076] FIG. 8 is a diagram illustrating a floor plan 800 of an
exemplary residential environment (e.g., an apartment) on which the
process for the initial training is described herein. The home
environment is mapped into the primary zones (the major home places
that the monitored person attends most of the time as bedroom 810,
restroom 820, living room 830 and the like) and secondary zones
(the rest of the barely used environments).
[0077] The VQ based human state classifier (described above) is
trained to know the various primary places at the home. This is
done during the system setup while the installer 10A (being the
elderly person or another person) stands or walks at each primary
place such as bedroom 810, restroom 820, and living room 830 and
let the system learns the "finger print" of the echo signals
extracted features that mostly represents that place. These finger
prints are stored in the VQ positions codebook.
[0078] In addition, the system learns the home external walls
boundaries. This is done during the system setup while the
installer stands at various places along the external walls and let
the system tunes its power and processing again (integration)
towards each direction. For example, in bedroom 810, installer 10A
may walk along walls in route 840 so that the borders of bedroom
810 are detected by tracking the changes in the RF signal
reflections throughout the process of walking. A similar border
identification process can be carried out in restroom 820, and
living room 830.
[0079] Finally, the system learns to identify the monitored person
10B. This is done by capturing the finger print of the extracted
features on several conditions, such as (1) while the person lays
at the default bed 812 (where he or she is supposed to be during
nighttime) to learn the overall body volume (2) while the person is
standing to learn the stature, and (3) while the person walks to
learn the gait.
[0080] All the captured cases are stored in the VQ unit and are
used to weight the pre-trained codebooks and to generate the
specific home/person codebooks.
[0081] According to some embodiments, one or additional persons
such as 20 can also be monitored simultaneously. The additional
person can be another elderly person with specific fingerprint or
it can be a care giver who needs not be monitored for abnormal
postures.
[0082] FIG. 9 is a diagram illustrating yet another aspect in
accordance with some embodiments of the present invention. System
900 is similar to the system described above but it is further
enhanced by the ability to interface with at least one wearable
medical sensor 910A or 910B coupled to the body of human 10
configured to sense vital signs of human 10, and a home safety
sensor 920 configured to sense ambient conditions at said specified
area, and wherein data from said at least one sensor are used by
said decision function for improving the decision whether an
abnormal physical event has occurred to the at least one human in
said specified area. The vital signs sensor may sense ECG, heart
rate, blood pressure, respiratory system parameters and the like.
Home safety sensors may include temperature sensors, smoke
detector, open door detectors and the like. Date from all or some
of these additional sensors may be used in order to improve the
decision making process described above.
[0083] In the above description, an embodiment is an example or
implementation of the inventions. The various appearances of "one
embodiment," "an embodiment" or "some embodiments" do not
necessarily all refer to the same embodiments.
[0084] Although various features of the invention may be described
in the context of a single embodiment, the features may also be
provided separately or in any suitable combination. Conversely,
although the invention may be described herein in the context of
separate embodiments for clarity, the invention may also be
implemented in a single embodiment.
[0085] Reference in the specification to "some embodiments", "an
embodiment", "one embodiment" or "other embodiments" means that a
particular feature, structure, or characteristic described in
connection with the embodiments is included in at least some
embodiments, but not necessarily all embodiments, of the
inventions.
[0086] It is to be understood that the phraseology and terminology
employed herein is not to be construed as limiting and are for
descriptive purpose only.
[0087] The principles and uses of the teachings of the present
invention may be better understood with reference to the
accompanying description, figures and examples.
[0088] It is to be understood that the details set forth herein do
not construe a limitation to an application of the invention.
[0089] Furthermore, it is to be understood that the invention can
be carried out or practiced in various ways and that the invention
can be implemented in embodiments other than the ones outlined in
the description above.
[0090] It is to be understood that the terms "including",
"comprising", "consisting" and grammatical variants thereof do not
preclude the addition of one or more components, features, steps,
or integers or groups thereof and that the terms are to be
construed as specifying components, features, steps or
integers.
[0091] If the specification or claims refer to "an additional"
element, that does not preclude there being more than one of the
additional element.
[0092] It is to be understood that where the claims or
specification refer to "a" or "an" element, such reference is not
be construed that there is only one of that element.
[0093] It is to be understood that where the specification states
that a component, feature, structure, or characteristic "may",
"might", "can" or "could" be included, that particular component,
feature, structure, or characteristic is not required to be
included.
[0094] Where applicable, although state diagrams, flow diagrams or
both may be used to describe embodiments, the invention is not
limited to those diagrams or to the corresponding descriptions. For
example, flow need not move through each illustrated box or state,
or in exactly the same order as illustrated and described.
[0095] Methods of the present invention may be implemented by
performing or completing manually, automatically, or a combination
thereof, selected steps or tasks.
[0096] The descriptions, examples, methods and materials presented
in the claims and the specification are not to be construed as
limiting but rather as illustrative only.
[0097] Meanings of technical and scientific terms used herein are
to be commonly understood as by one of ordinary skill in the art to
which the invention belongs, unless otherwise defined.
[0098] The present invention may be implemented in the testing or
practice with methods and materials equivalent or similar to those
described herein.
[0099] While the invention has been described with respect to a
limited number of embodiments, these should not be construed as
limitations on the scope of the invention, but rather as
exemplifications of some of the preferred embodiments. Other
possible variations, modifications, and applications are also
within the scope of the invention. Accordingly, the scope of the
invention should not be limited by what has thus far been
described, but by the appended claims and their legal
equivalents.
* * * * *