CN108354610A - A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor - Google Patents
A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor Download PDFInfo
- Publication number
- CN108354610A CN108354610A CN201710755632.2A CN201710755632A CN108354610A CN 108354610 A CN108354610 A CN 108354610A CN 201710755632 A CN201710755632 A CN 201710755632A CN 108354610 A CN108354610 A CN 108354610A
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- axis
- egc
- real time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor, the detection method include:1)There is tumble stress reaction and the under normal circumstances movable electrocardio sample data of daily behavior using EGC sensor acquisition;2)Sample data is pre-processed;3)Extract the feature of sample;4)Grader is trained with the feature of sample;5)The data of acquisition three-axis sensor and EGC sensor in real time.
Description
Technical field
The present invention relates to the fields such as medical treatment & health, signal processing, machine learning, are sensed based on three axis more particularly to one kind
The Falls Among Old People detection method and detecting system of device and EGC sensor.
Background technology
According to statistics, China is at the end of the 20th century into aging society, it is contemplated that it will enter depth ageing stage to the year two thousand fifty,
As the country of aging degree most serious, this also will bring huge pressure and challenge to Chinese society from many aspects.At this
In the case of kind, the demands such as life care, trip of the elderly are increasingly prominent, wherein it is particularly problematic to be embodied in safe healthcare,
It is mainly reflected at 2 points:First, the elderly's physical function is degenerated, they are easily unexpected or because of sick (especially cardiovascular and cerebrovascular
Disease) it falls.According to foreign statistic, there are about 1/3 65 years old old men at least to fall once every year, falls in the elderly's cause of death
Ratio be up to 25%, tumble is very easy to cause old man's fracture, internal organ concussion;If cannot be succoured in time after falling, meeting
Further increase lethality and disability rate;Tumble not only causes injury physiologically to the elderly, can also bring psychological the moon
Shadow;In addition, no one ventured is assisted in after current social Falls in Old People, no one ventured is rescued, become a kind of universal social phenomenon gradually,
In this case, it is even more fatal to the elderly to fall;Therefore it is directed to active demand of the elderly to safety assurance, utilizes electronics
Information technology solves the problems, such as that this has great social value.
Existing fall detection scheme just with acceleration transducer, there is certain limitation and rate of false alarm mostly, and
Once and acceleration transducer leaves the person, acceleration transducer is such as thrown away to intentional false operation of falling on desk or artificial
It is inadequate just with acceleration transducer judgement Deng these.On the other hand, numerous studies have shown that any type mood shape
State all may be with the variation of several physiology or psychological characteristics, autonomic nerves system and endocrine system due to these variations by people
System dominates, therefore when individual is during tumble, it may appear that the variation of mental emotion, it at this time also can be by autonomic nerves system control
System, and reflect onto the electrocardiosignal of individual.
Invention content
It is an object of the invention to overcome the shortcomings of the prior art, and Falls Among Old People detection can be solved by providing one kind
The Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor of the not high problem of accuracy rate.
The purpose of the present invention is achieved through the following technical solution:One kind being based on three-axis sensor and EGC sensor
Falls Among Old People detection method, should detection method includes the following steps:
1) use EGC sensor acquisition that there is tumble stress reaction and the under normal circumstances movable electrocardio of daily behavior
Sample data;
2) sample data is pre-processed;
3) feature of sample is extracted;
4) feature of sample is used to train grader;
5) data of three-axis sensor and EGC sensor are acquired in real time;
6) in real time pre-process and calculate three-axis sensor acceleration change rate and peak value and judge whether be more than threshold
Otherwise value is judged to not falling if it exceeds just in next step judging;
7) the front and back each 10 seconds electrocardiogram (ECG) datas cached in EGC sensor are extracted, by pretreatment, extract feature, input
To trained grader, judge whether the heartbeat stress reaction with tumble state, if there is being judged to falling, otherwise
It does not fall.
As preferred:In the step 1), during the EGC sensor gathered data, mainly acquisition has
Tumble stress reaction state, including dump forward, topple over backward and daily behavior active state under normal circumstances, including such as
The electrocardio sample data walk, run, sit, lain;
In the step 2), sample data is pre-processed, is mainly carried out using common signal antinoise method
Whether denoising, denoising are labeled sample after completing and fall;
In the step 3), R wave positioning is carried out to ecg signal data first, determines the data point of phase between RR, so
Afterwards according to the wave characteristics of the RR interval series of electrocardiosignal, extracts several and best embody the phase between the RR of heartbeat stress reaction
The mathematical statistics feature of sequence.
As preferred:In the step 4), using sorter model such as machine learning algorithm or deep learning algorithm pair
Whether tumble carries out two classification, i.e., the feature of obtained each sample and mark is input in sorter model and is trained,
And the sorter model for completing training for detecting electrocardiosignal with the presence or absence of the heartbeat stress reaction fallen in real time;
The step) in, it is desirable that old man is in human body shirtfront cardia body-worn three-axis sensor and electrocardio sensing
Device, so that EGC sensor will acquire electrocardiogram (ECG) data in real time;Three-axis sensor is corrected according to wearing mode before the use, is made
With needing gathered data in real time in the process, and EGC sensor can cache each 10 seconds data before and after certain moment, exist in this way
During judging whether stress reaction using electrocardiosignal, judged using front and back 10 seconds data.
In the step 6), pretreatment in real time, which calculates the acceleration change rate of three-axis sensor and peak value judgement, is
No is more than specific threshold, judges that electrocardio with the presence or absence of the stress reaction fallen, is otherwise determined as in next step if it exceeds being put into
It does not fall;In the process, there is due to sensor in gatherer process noise jamming, it is therefore desirable to enter to filter out to noise,
Usable filter is filtered;Acceleration change rate (RAC) and three-axis sensor vector peak value (SVM) are defined as follows:
Wherein, Xn、YnAnd ZnIt is X, Y, Z 3-axis acceleration amplitude after denoising respectively;
In the step 7), front and back each 10 seconds data this moment are extracted in EGC sensor, data are pre-processed,
Extraction feature is simultaneously input to trained grader, judges to whether there is tumble stress reaction in the process, if deposited
It is being judged as falling, be not otherwise to fall.
A kind of detecting system for the Falls Among Old People detection method based on three-axis sensor and EGC sensor, institute
The system stated is realized using the framework of B/S, includes mainly three axis acceleration sensors, three-axis gyroscope and core signal sensor
Module, smart mobile phone, server, monitoring platform software sharing;Three axis acceleration sensors, three-axis gyroscope and the electrocardio
Signal transducer module is correctly worn on old man front and corrects sensor assembly, and the sensor assembly passes through bluetooth connection intelligence
Energy cell phone application, and the data that smart mobile phone real-time reception sensor assembly acquires after successful connection, smart mobile phone pass through movement
Network upload the data to server in real time, and simultaneously foundation collects display data the monitoring platform software in server in real time
Data calculated in real time, and detect whether to fall, if the monitoring of old man will be alarmed and send messages to immediately by falling
The monitoring personnel of people or caregiver, side can also make an immediate response and give first-aid measures.
The present invention is mainly combined using 3-axis acceleration and EGC sensor, in the case of acquisition people falls first
Electrocardiosignal and 6 kinds of daily routines behaviors are the electrocardio sample number of normal conditions such as to walk, run, jumping, above going downstairs, sitting down, lying down
According to by pretreatment, with the feature extracted with normal cardiac RR intervals sample of falling come training machine Study strategies and methods;
During old man's use, three-axis sensor and EGC sensor real-time data collection, first real-time judge three-axis sensor plus
Whether velocity variations rate (RAC) and acceleration peak value (SVM) are more than the threshold value set, if it exceeds threshold value just utilizes electrocardio
Front and back each 10 seconds data of sensor caching after preprocessed and extraction feature, are input to trained grader and sentence
It is disconnected whether to fall.
The beneficial effects of the invention are as follows:The present invention by acquiring the data of three-axis sensor and EGC sensor in real time, according to
The data of upper two aspect carry out dual judgement respectively according to this, improve validity and the accuracy of Falls Among Old People detection.
Description of the drawings
Fig. 1 is the idiographic flow block diagram of the present invention.
Fig. 2 is certain 10 seconds electrocardio training data figure fallen forward of the invention.
Fig. 3 is the R wave locations drawing that the present invention is positioned using difference threshold algorithm.
Fig. 4 is the datagram of 3-axis acceleration sensor during certain tumble of the invention.
Fig. 5 is that of the present invention run based on the Falls Among Old People detecting system of three-axis sensor and EGC sensor is illustrated
Figure.
Specific implementation mode
Below in conjunction with drawings and examples, the present invention is described in detail.It is that one kind is sensed based on three axis shown in Fig. 1
The Falls Among Old People detection method particular flow sheet of device and EGC sensor, described detection method includes the following steps:
1) use EGC sensor acquisition that there is tumble stress reaction and the under normal circumstances movable electrocardio of daily behavior
Sample data;
2) sample data is pre-processed;
3) feature of sample is extracted;
4) feature of sample is used to train grader;
5) data of three-axis sensor and EGC sensor are acquired in real time;
6) in real time pre-process and calculate three-axis sensor acceleration change rate and peak value and judge whether be more than threshold
Otherwise value is judged to not falling if it exceeds just in next step judging;
7) the front and back each 10 seconds electrocardiogram (ECG) datas cached in EGC sensor are extracted, by pretreatment, extract feature, input
To trained grader, judge whether the heartbeat stress reaction with tumble state, if there is being judged to falling, otherwise
It does not fall.
In step 1), with EGC sensor gathered data during, mainly acquire 4 kinds of tumble postures and turn forward
, topple over backward, topple over to the left and topple over to the right and 6 kinds of daily routines behaviors are walked, run, jump, above go downstairs, sit down, lie
The sensing data of inferior normal condition, if Fig. 2 is the electrocardiogram (ECG) data of certain process that dumps forward.
In step 2), sample data is pre-processed, mainly wavelet threshold denoising method is used to use sym6
Wavelet basis function carries out 3 layers of decomposition to collected data, and the detail signal of the high frequency to decomposing is gone using soft-threshold function
It makes an uproar, then is reconstructed to obtain the data after denoising to each layer signal;After denoising is completed, electrocardio sample is made whether to fall
Mark, can indicate to fall with 1, and 0 indicates not fall to be labeled.
In step 3), the feature of sample data is extracted, R wave positioning is carried out to ecg signal data, determines the phase between RR
Data point and period are the first-order difference and two using electrocardiosignal using difference threshold algorithm during R waves position
The quadratic sum of order difference protrudes R waves position, reuses threshold value and positions R waves for 0.95, if some position is more than threshold
Value, then it is assumed that the position is the R waves positioning that R waves position is as shown in Figure 3 10 seconds electrocardiosignal, the R waves position that * is indicated
It sets;Above-mentioned parameter is represented by:
First-order difference:
Second differnce:
First-order difference and second differnce quadratic sum:
Wherein x (n) is phase electrocardiogram (ECG) data point between RR.For the RR interval datas of each period, according to whether fall into
Rower is noted.After R wave location determinations, according to the feature of RR interval series, the mathematical statistics feature of RR interval series is extracted, can extract
Between maximum RR in the mean value of RR interval series, the mean square deviation of RR interval series, RR interval series in phase range, RR interval series
Minimum RR between phase range, the mean value of the adjacent difference of RR interval series, the adjacent difference of RR interval series root mean square and RR between phase sequence
Arrange 7 features such as adjacent ratio of the difference less than 50 milliseconds;
RRmax=Max (RR1, RR2..., RRn-1, RRn)
RRmin=Min (RR1, RR2..., RRn-1, RRn
Wherein, n be electrocardio sample data RR between phase number, RRmeanIt is the mean value of RR interval series, RRstdIt is the phase between RR
The mean square deviation of sequence, RRmaxIt is phase maximum magnitude, RR between RR in RR interval seriesminIt is phase minimum model between RR in RR interval series
It encloses, RRadjmeanIt is the mean value of phase adjacent difference between RR, RRadjstdIt is the root mean square of phase adjacent difference between RR.
In step 4), using random forest (RF) integrated classifier to whether falling two classification of progress, i.e., it will obtain
7 features and mark of each sample are input to random forest grader (or neural network) and are trained, in the training process
The number that tree is arranged is 100, and the depth of tree is 10.
In step 5), it is desirable that old man's body-worn three-axis sensor and EGC sensor, such as human body shirtfront cardia,
This is because EGC sensor will acquire electrocardiogram (ECG) data in real time;Three-axis sensor is corrected according to wearing mode before the use,
Gathered data in real time is needed during use, and EGC sensor can cache each 10 seconds electrocardiogram (ECG) datas before and after certain moment,
In this way during judging whether stress reaction using electrocardiosignal, judged using front and back 10 seconds data.
In step 6), pretreatment calculates the acceleration change rate of three-axis sensor in real time and peak value judges whether to surpass
Specific threshold is crossed, if it exceeds just in next step judging, is otherwise judged to not falling;It is three during certain is fallen as shown in Figure 4
Axis accelerator has the state being obviously mutated, in the process, since sensor has noise jamming in gatherer process,
It needs to enter to filter out to noise, usable median filter is filtered, and it is 4 to take filtering section;Acceleration change rate (RAC)
It is defined as follows with three-axis sensor vector peak value (SVM):
Wherein, Xn、YnAnd ZnIt is X, Y, Z 3-axis acceleration amplitude after denoising respectively.
In step 7), front and back 10 second data of extraction EGC sensor caching, and gone using wavelet threshold denoising method
It makes an uproar, then carries out R wave positioning, extract the feature of RR interval series, be input to grader, judge during this 10 seconds, if
Otherwise it is not to fall if there is being judged as falling there are tumble state.
It is the operation of the Falls Among Old People detecting system of the present invention based on three-axis sensor and EGC sensor shown in Fig. 5
Schematic diagram.The detecting system using B/S framework realize, mainly include three axis acceleration sensors, three-axis gyroscope and
Core signal sensor module, smart mobile phone, server, monitoring platform software sharing;The three axis acceleration sensors, three axis
Gyroscope and core signal sensor module are correctly worn on old man front and correct sensor assembly, the sensor assembly
By bluetooth connection smart mobile phone APP, and the data that smart mobile phone real-time reception sensor assembly acquires after successful connection, intelligence
Energy mobile phone upload the data to server in real time by mobile network, and the monitoring platform software in server shows number in real time
It is calculated in real time according to and according to collected data, and detects whether to fall, disappeared if falling immediately alarm and send
The guardian to old man or caregiver are ceased, the monitoring personnel on side can also make an immediate response and give first-aid measures.
Example the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (4)
1. a kind of Falls Among Old People detection method based on three-axis sensor and EGC sensor, it is characterised in that the detection method packet
Include following steps:
1) use EGC sensor acquisition that there is tumble stress reaction and the under normal circumstances movable electrocardio sample of daily behavior
Data;
2) sample data is pre-processed;
3) feature of sample is extracted;
4) feature of sample is used to train grader;
5) data of three-axis sensor and EGC sensor are acquired in real time;
6) in real time pre-process and calculate three-axis sensor acceleration change rate and peak value and judge whether be more than threshold value, such as
Fruit is more than just to judge in next step, is otherwise judged to not falling;
7) the front and back each 10 seconds electrocardiogram (ECG) datas cached in EGC sensor are extracted, by pretreatment, feature is extracted, is input to
Trained grader judges whether the heartbeat stress reaction with tumble state, if there is being judged to falling, does not otherwise fall
.
2. the Falls Among Old People detection method according to claim 1 based on three-axis sensor and EGC sensor, feature
It is:
In the step 1), during the EGC sensor gathered data, mainly acquisition has tumble stress reaction
State, including dump forward, topple over backward and daily behavior active state under normal circumstances, including as walked, running, sat, lain
Electrocardio sample data;
In the step 2), sample data is pre-processed, mainly carries out denoising using common signal antinoise method,
Whether denoising is labeled sample after completing and falls;
In the step 3), R wave positioning is carried out to ecg signal data first, determines the data point of phase between RR, then root
According to the wave characteristics of the RR interval series of electrocardiosignal, extracts several and best embody RR interval series in heartbeat stress reaction
Mathematical statistics feature.
3. the Falls Among Old People detection method according to claim 1 based on three-axis sensor and EGC sensor, feature
It is:
In the step 4), using sorter model such as machine learning algorithm or deep learning algorithm to whether falling carry out two
Classification, i.e., be input to the feature of obtained each sample and mark in sorter model and be trained, and training is completed
Sorter model for detecting electrocardiosignal with the presence or absence of the heartbeat stress reaction fallen in real time;
The step) in, it is desirable that old man in human body shirtfront cardia body-worn three-axis sensor and EGC sensor, with
Just EGC sensor will acquire electrocardiogram (ECG) data in real time;Three-axis sensor is corrected according to wearing mode before the use, was being used
Gathered data in real time is needed in journey, and EGC sensor can cache each 10 seconds data before and after certain moment, utilize in this way
During electrocardiosignal judges whether stress reaction, judged using front and back 10 seconds data.
In the step 6), pretreatment calculates the acceleration change rate of three-axis sensor in real time and peak value judges whether to surpass
Specific threshold is crossed, judges that electrocardio with the presence or absence of the stress reaction fallen, is otherwise judged to not falling in next step if it exceeds being put into
;In the process, there is noise jamming due to sensor in gatherer process, it is therefore desirable to enter to filter out to noise, can make
It is filtered with filter;Acceleration change rate (RAC) and three-axis sensor vector peak value (SVM) are defined as follows:
Wherein, Xn、YnAnd ZnIt is X, Y, Z 3-axis acceleration amplitude after denoising respectively;
In the step 7), front and back each 10 seconds data this moment are extracted in EGC sensor, data are pre-processed, are extracted
Feature is simultaneously input to trained grader, judges to whether there is tumble stress reaction in the process, if there is just
It is judged as falling, is not otherwise to fall.
4. a kind of for the Falls Among Old People detection side based on three-axis sensor and EGC sensor as described in claims 1 or 2 or 3
The detecting system of method, it is characterised in that the system is realized using the framework of B/S, includes mainly three axis acceleration sensors, three
Axis gyroscope and core signal sensor module, smart mobile phone, server, monitoring platform software sharing;Three axis add
Fast sensor, three-axis gyroscope and core signal sensor module are correctly worn on old man front and correct sensor assembly,
The sensor assembly is by bluetooth connection smart mobile phone APP, and the smart mobile phone real-time reception sensor die after successful connection
The data of block acquisition, smart mobile phone upload the data to server in real time by mobile network, the monitoring platform in server
Software display data and is calculated in real time according to collected data in real time, and detects whether to fall, will if fallen
Guardian or the caregiver of old man are alarmed and sent messages to immediately, and the monitoring personnel on side can also make an immediate response and take first aid
Measure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710755632.2A CN108354610A (en) | 2017-08-29 | 2017-08-29 | A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710755632.2A CN108354610A (en) | 2017-08-29 | 2017-08-29 | A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108354610A true CN108354610A (en) | 2018-08-03 |
Family
ID=63009989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710755632.2A Pending CN108354610A (en) | 2017-08-29 | 2017-08-29 | A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108354610A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109805936A (en) * | 2019-01-18 | 2019-05-28 | 深圳大学 | Falling over of human body detection system based on ground vibration signal |
CN111657918A (en) * | 2020-06-12 | 2020-09-15 | 电子科技大学 | Falling detection method and system combining electrocardio and inertial sensing data |
CN111763958A (en) * | 2020-08-24 | 2020-10-13 | 沈阳铝镁设计研究院有限公司 | Anode effect detection method based on anode guide rod vibration |
WO2021008073A1 (en) * | 2019-07-15 | 2021-01-21 | 南京医科大学 | Method, system, and apparatus for monitoring water drinking of laboratory mouse |
CN112699744A (en) * | 2020-12-16 | 2021-04-23 | 南开大学 | Fall posture classification identification method and device and wearable device |
WO2021233725A1 (en) * | 2020-05-20 | 2021-11-25 | Koninklijke Philips N.V. | Fall detector incorporating physiological sensing |
WO2023142707A1 (en) * | 2022-01-25 | 2023-08-03 | 英华达(上海)科技有限公司 | Physiological feature detection apparatus, physiological feature detection system and care system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080294019A1 (en) * | 2007-05-24 | 2008-11-27 | Bao Tran | Wireless stroke monitoring |
US20110181422A1 (en) * | 2006-06-30 | 2011-07-28 | Bao Tran | Personal emergency response (per) system |
CN104382582A (en) * | 2014-11-10 | 2015-03-04 | 哈尔滨医科大学 | Device for classifying dynamic electrocardio data |
CN104783782A (en) * | 2015-04-13 | 2015-07-22 | 深圳市飞马与星月科技研究有限公司 | Automatic detection method and device for electrocardiosignals |
CN106037749A (en) * | 2016-05-18 | 2016-10-26 | 武汉大学 | Old people falling monitoring method based on smart mobile phone and wearable device |
CN106407996A (en) * | 2016-06-30 | 2017-02-15 | 华南理工大学 | Machine learning based detection method and detection system for the fall of the old |
-
2017
- 2017-08-29 CN CN201710755632.2A patent/CN108354610A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110181422A1 (en) * | 2006-06-30 | 2011-07-28 | Bao Tran | Personal emergency response (per) system |
US20080294019A1 (en) * | 2007-05-24 | 2008-11-27 | Bao Tran | Wireless stroke monitoring |
CN104382582A (en) * | 2014-11-10 | 2015-03-04 | 哈尔滨医科大学 | Device for classifying dynamic electrocardio data |
CN104783782A (en) * | 2015-04-13 | 2015-07-22 | 深圳市飞马与星月科技研究有限公司 | Automatic detection method and device for electrocardiosignals |
CN106037749A (en) * | 2016-05-18 | 2016-10-26 | 武汉大学 | Old people falling monitoring method based on smart mobile phone and wearable device |
CN106407996A (en) * | 2016-06-30 | 2017-02-15 | 华南理工大学 | Machine learning based detection method and detection system for the fall of the old |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109805936A (en) * | 2019-01-18 | 2019-05-28 | 深圳大学 | Falling over of human body detection system based on ground vibration signal |
CN109805936B (en) * | 2019-01-18 | 2021-08-13 | 深圳大学 | Human body tumbling detection system based on ground vibration signal |
WO2021008073A1 (en) * | 2019-07-15 | 2021-01-21 | 南京医科大学 | Method, system, and apparatus for monitoring water drinking of laboratory mouse |
WO2021233725A1 (en) * | 2020-05-20 | 2021-11-25 | Koninklijke Philips N.V. | Fall detector incorporating physiological sensing |
US11410521B2 (en) | 2020-05-20 | 2022-08-09 | Koninklijke Philips N.V. | Fall detector incorporating physiological sensing |
US11749086B2 (en) | 2020-05-20 | 2023-09-05 | Koninklijke Philips N.V. | Fall detector incorporating physiological sensing |
CN111657918A (en) * | 2020-06-12 | 2020-09-15 | 电子科技大学 | Falling detection method and system combining electrocardio and inertial sensing data |
CN111763958A (en) * | 2020-08-24 | 2020-10-13 | 沈阳铝镁设计研究院有限公司 | Anode effect detection method based on anode guide rod vibration |
CN112699744A (en) * | 2020-12-16 | 2021-04-23 | 南开大学 | Fall posture classification identification method and device and wearable device |
WO2023142707A1 (en) * | 2022-01-25 | 2023-08-03 | 英华达(上海)科技有限公司 | Physiological feature detection apparatus, physiological feature detection system and care system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108354610A (en) | A kind of Falls Among Old People detection method and detecting system based on three-axis sensor and EGC sensor | |
CN205041401U (en) | Equipment is worn detection device and is had and wears guardianship device that detects function | |
EP3355784B1 (en) | Biometric information monitoring system | |
CN102138789B (en) | Dynamic electrocardiogram and motion recording and analyzing system | |
Pannurat et al. | A hybrid temporal reasoning framework for fall monitoring | |
CN105561567B (en) | A kind of meter step and motion state apparatus for evaluating | |
CN105118236B (en) | Paralysis falls to monitor and preventing mean and its processing method | |
CN103337132B (en) | Tumble detection method for human body based on 3-axis acceleration sensor | |
Cole et al. | Detecting freezing-of-gait during unscripted and unconstrained activity | |
Roy et al. | A combined sEMG and accelerometer system for monitoring functional activity in stroke | |
CN110420019A (en) | A kind of depth recurrence heart rate estimation method of ballistocardiography signal | |
CN106937808A (en) | A kind of data collecting system of intelligent mattress | |
CN106618965A (en) | Wearable extremity rehabilitation training system and control method | |
CN105125206B (en) | A kind of intelligent cardiac monitoring method and device | |
EP2734104B1 (en) | System for detecting the onset of seizures | |
CN106781283B (en) | A kind of method for detecting fatigue driving based on soft set | |
CN101164496A (en) | Method for carry-on monitoring human physiological parameter and safety state | |
CN103177530B (en) | Human fall detection method based on triaxial acceleration | |
Dong et al. | Wearable diet monitoring through breathing signal analysis | |
CN110415825A (en) | A kind of old man's safe condition intelligent evaluation method and system based on machine learning | |
CN110801212A (en) | BCG signal heart rate extraction method based on neural network | |
CN110313917A (en) | It is the tumble sensor-based system and its method for judging benchmark with activities of daily life | |
CN112016619A (en) | Fall detection method based on insoles | |
CN109805935A (en) | A kind of intelligent waistband based on artificial intelligence hierarchical layered motion recognition method | |
Lv et al. | Information collection system for fall detection of stroke patients under cascade algorithm in the context of multi‐modal information fusion and e‐health |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180803 |
|
RJ01 | Rejection of invention patent application after publication |