CN114079859A - Monitoring device and monitoring method based on CSI - Google Patents
Monitoring device and monitoring method based on CSI Download PDFInfo
- Publication number
- CN114079859A CN114079859A CN202111298868.0A CN202111298868A CN114079859A CN 114079859 A CN114079859 A CN 114079859A CN 202111298868 A CN202111298868 A CN 202111298868A CN 114079859 A CN114079859 A CN 114079859A
- Authority
- CN
- China
- Prior art keywords
- csi
- wifi
- identification
- monitored person
- monitored
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 19
- 238000012806 monitoring device Methods 0.000 title claims abstract description 8
- 238000002955 isolation Methods 0.000 claims abstract description 44
- 230000005021 gait Effects 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 239000000284 extract Substances 0.000 claims abstract description 6
- 230000033001 locomotion Effects 0.000 claims description 19
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 230000000241 respiratory effect Effects 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 230000011514 reflex Effects 0.000 claims description 2
- 238000012512 characterization method Methods 0.000 claims 1
- 238000012216 screening Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 abstract 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract 1
- 230000002265 prevention Effects 0.000 abstract 1
- 230000006806 disease prevention Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004080 punching Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005541 medical transmission Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a monitoring device and a monitoring method based on CSI.A WiFi signal is transmitted in real time through WiFi transmitting equipment, and a WiFi receiving terminal receives the WiFi signal and extracts CSI data; the system firstly identifies the monitored personnel through a gait identification algorithm, and if the identification is successful, the monitored personnel is in a normal isolation state; if the identification fails, considering that the monitored personnel is possibly in a rest state, and further identifying the monitored personnel by utilizing a breath identification algorithm; and if the identification is successful, the identification is in a normal isolation state, and if the identification is failed, the identification is in an abnormal isolation state. The invention can accurately monitor the dynamic state of the monitored personnel, accurately master whether the monitored personnel is in the isolation area, prevent the monitored personnel from hiding or falsifying the isolation state and other behaviors, and has important effect on the prevention and control of diseases.
Description
Technical Field
The invention relates to a monitoring device and a monitoring method, in particular to a monitoring device and a monitoring method based on CSI, and belongs to the technical field of monitoring.
Background
Effective isolation measures can block disease transmission ways to the maximum extent and guarantee personnel circulation. At present, the existing isolation means is mainly that monitored personnel punch a card to report or staff make a visit to the ward at a fixed point through modes such as mobile phone APP, and the existence of loopholes such as a card punching record or an easily forged card punching place is reported through mobile phone APP card punching, and the loopholes depend on the consciousness of the monitored personnel, and the workload of the staff is increased through the staff making a visit to the ward at a fixed point.
Disclosure of Invention
In view of the problems in the prior art, the invention provides a monitoring device and a monitoring method based on CSI, which can accurately monitor the dynamics of monitored personnel, accurately grasp whether the monitored personnel are in an isolation area, and play an important role in disease prevention and control.
In order to achieve the above object, the present invention provides a CSI-based monitoring apparatus, which includes a WiFi transmitting device for transmitting a WiFi signal to an activity range of a monitored person and a WiFi receiving terminal for receiving and processing the WiFi signal.
A monitoring method based on CSI comprises the following specific steps:
s1, the WiFi sending equipment sends WiFi signals to the moving range of the monitored personnel in real time;
s2, the WiFi receiving terminal receives the WiFi signals in real time and extracts CSI data;
s3, according to the extracted CSI data, the identity information of the monitored person is identified through a gait identification algorithm:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in a rest state or in an abnormal isolation state, and the step S4 is entered;
s4, identity information of the monitored person is identified through a respiration identification algorithm:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in an abnormal isolation state.
Compared with the prior art, the method and the device have the advantages that the WiFi signals are received, the CSI data are extracted, the monitored personnel in the isolation area are identified through a gait identification algorithm and a respiration identification algorithm according to the obtained CSI data, and whether the isolation personnel are in a normal isolation state or not is judged. The invention realizes passive, accurate, simple, convenient and real-time isolation monitoring of monitored personnel, effectively prevents the monitored personnel from hiding or falsifying isolation states and other behaviors, and is beneficial to disease prevention and control.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of a gait recognition algorithm of the invention;
FIG. 3 is a flow chart of the breath identification algorithm of the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
In the embodiment, 3-4 persons in an isolation area are monitored, a WiFi sending device is used for sending WiFi signals to the activity range of the monitored person, a commercial WiFi router supporting an IEEE 802.11n protocol is adopted, and the deployment position should select the position where the transmitted WiFi signals can completely cover the monitored person; the WiFi receiving equipment is used for receiving and processing WiFi signals, a computer provided with an Intel 5300 wireless network card is adopted, the capacity of a hard disk is larger than 128GB, the running memory is larger than 4GB, and the specific monitoring method is as follows:
s1, the WiFi sending equipment sends WiFi signals to the moving range of the monitored personnel in real time;
s2, the WiFi receiving terminal receives the WiFi signals in real time and extracts CSI data;
s3, identifying the monitored person through a gait recognition algorithm according to the extracted CSI data:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in a rest state or in an abnormal isolation state, and the step S4 is entered;
s4 identifying the monitored person through a breath identification algorithm:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in an abnormal isolation state, and the staff or medical staff needs to go to an isolation site in time to check whether the monitored person is in the isolation area.
The normal isolation state is that the monitored person is in the isolation area; the abnormal isolation state is that the monitored person is not in the isolation area any more.
In some embodiments, the gait recognition algorithm in step S3 includes the following steps:
s31, after the WiFi receiving terminal extracts the CSI data, firstly extracting a principal component from the extracted CSI data through a principal component analysis method, and reducing uncorrelated noise in different subcarriers; then, converting the extracted principal components into an original spectrogram by using fast Fourier transform; finally, removing noise in the original spectrogram through background noise subtraction to obtain a noise-reduced spectrogram;
s32, predicting two major motion characteristics of gait cycle time and motion speed of the trunk and the legs by a gait cycle time prediction method and a limb motion speed prediction method according to the denoised spectrogram;
s33, taking the gait cycle time and the movement speed of the trunk and the legs obtained through prediction as input values of a trained classifier based on the deep neural network, and identifying the identity information of the monitored person by using the trained classifier based on the deep neural network:
if the identification is successful, the monitored person is in a normal isolation state, and the monitored person is in the isolation area;
if the identification fails, the monitored person is in a rest state or an abnormal isolation state, which indicates that the monitored person may rest and therefore has no limb movement, or may not be in the isolation region, and the step S4 is performed, that is, the identity information of the monitored person is further identified by the respiration identification algorithm.
The moving speeds of the trunk and the legs comprise a trunk moving speed and a leg moving speed.
The gait cycle time prediction method in the step S33 includes the steps of:
s331 estimating gait cycle time using upper contour of torso reflex, torso contour frequency fct(t) is defined as:
wherein F (F, t) is the amplitude at time t and frequency F after fast Fourier transform,
is a frequency range of 0 to fmaxThe total energy between, gamma, is 5%.
S332 obtaining the trunk contour frequency fct(t) obtaining the moving speed v of the trunk outline by using the following formulatc(t)：
vtc(t)＝ftc(t)ε/2
Wherein epsilon is the wavelength of the WiFi signal;
s333 estimates a gait cycle time R (τ) from the movement velocity of the torso contour by using autocorrelation of the torso contour curve:
where μ is the mean velocity of the torso contour and τ is the time offset of the torso contour curve;
the method estimates the gait cycle time by utilizing the autocorrelation of the trunk contour curve, intersects with the traditional methods such as wavelet transformation and the like, and has higher perception accuracy.
The limb movement speed prediction method comprises the following steps:
s334 estimates torso and leg velocities using a percentile method developed for doppler radars, the percentile for a given frequency f being defined as:
wherein P (f, t) is the cumulative percentage of energy with frequency below f to the total energy of the FFT result at time t;
s335 the forecast of the trunk movement speed is the lowest frequency value in the range of P (f, t) > 50%, and the forecast of the leg movement speed is the lowest frequency value in the range of P (f, t) ≧ 95%.
The breath identification algorithm in step S4 includes the following steps:
s41, after the CSI data are extracted by the WiFi receiving terminal, removing environmental noise through a filter based on empirical mode decomposition to obtain noise-reduced CSI data;
s42, comparing the variances of the CSI measurement after noise reduction, and selecting the CSI with the largest variance as the subcarrier most sensitive to the tiny human body movement;
s43, calculating the distance between every two adjacent waveform peaks in the CSI data of the most sensitive subcarrier, selecting the maximum distance value as a respiration period, and extracting respiration characteristics by using a morphological characteristic method.
S44, the extracted breathing features are used as input values of a trained classifier based on the deep neural network, and the trained classifier based on the deep neural network is used for identifying the identity information of the monitored person:
if the identification is successful, the monitored person is in a normal isolation state, and the monitored person is in the isolation area;
if the identification fails, the monitored person is in an abnormal isolation state, and the monitored person is not in the isolation area.
Compared with the traditional method which needs to use all subcarriers, the method has the advantages that the subcarriers are screened at one time, the calculated amount is reduced, the processing speed is higher, and the accuracy is higher.
Training a deep neural network-based classifier by:
and taking the identity information of the monitored person, namely gait cycle time, the movement speed of the trunk and legs and breathing characteristics, as input values of a classifier based on the deep neural network, and then repeatedly training the neural network until the accuracy of identifying the monitored person by using the classifier based on the deep neural network is over 95 percent, and considering that the training is finished. And then, the identity information of the monitored person can be identified by using a trained classifier based on the neural network.
Since the training method of the classifier based on the deep neural network is a well-established prior art, it is not described herein again.
The morphological feature method in S43 includes the following steps:
during a respiratory cycle, with HtRepresenting the difference between the maximum amplitude of respiration and the minimum amplitude of respiration, using
Height representing p% position from the breath minimum amplitude point:
wherein p represents a parameter of position; if someone is 5% of 20 meters, i.e. 1 meter, where p% is 5%; by using
Is shown in position
Intercept of the respiratory waveform at time, and therefore, respiratory characteristics at the p% position
Expressed as:
in some specific embodiments, the invention can also be provided with an alarm module, if the monitored person is in an abnormal isolation state, an alarm signal is sent to the alarm module, the alarm module sends an alarm sound after receiving the alarm signal, and reminds the monitoring personnel that the monitored person is in the abnormal isolation state, and the monitoring personnel can check whether the monitored person is in the isolation region in time on site, thereby providing great convenience for disease prevention and control, and effectively saving time cost and labor cost during the disease prevention and control.
Claims (8)
1. The monitoring device based on the CSI is characterized by comprising WiFi sending equipment and a WiFi receiving terminal, wherein the WiFi sending equipment is used for sending WiFi signals to the moving range of monitored personnel, and the WiFi receiving terminal is used for receiving and processing the WiFi signals.
2. The CSI-based monitoring device according to claim 1, wherein the WiFi sending equipment is a commercial WiFi router supporting IEEE 802.11n protocol; the WiFi receiving equipment is a computer provided with an Intel 5300 wireless network card, the capacity of a hard disk is larger than 128GB, and the running memory is larger than 4 GB.
3. A monitoring method based on CSI is characterized by comprising the following specific steps:
s1, the WiFi sending equipment sends WiFi signals to the moving range of the monitored personnel in real time;
s2, the WiFi receiving terminal receives the WiFi signals in real time and extracts CSI data;
s3, according to the extracted CSI data, the identity information of the monitored person is identified through a gait identification algorithm:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in a rest state or in an abnormal isolation state, and the step S4 is entered;
s4, identity information of the monitored person is identified through a respiration identification algorithm:
if the identification is successful, the monitored person is in a normal isolation state;
if the identification fails, the monitored person is in an abnormal isolation state.
4. The CSI-based monitoring method according to claim 3, wherein the gait recognition algorithm in the step S3 includes the following steps:
s31, after the WiFi receiving terminal extracts the CSI data, firstly extracting a principal component from the extracted CSI data through a principal component analysis method, and reducing uncorrelated noise in different subcarriers; then, converting the extracted principal components into an original spectrogram by using fast Fourier transform; finally, removing noise in the original spectrogram through background noise subtraction to obtain a noise-reduced spectrogram;
s32, predicting two major motion characteristics of gait cycle time and motion speed of the trunk and the legs by a gait cycle time prediction method and a limb motion speed prediction method according to the denoised spectrogram;
s33 identifies the monitored person identity information using a deep neural network-based classifier using the gait cycle time and the moving speeds of the trunk and leg including the trunk moving speed and the leg moving speed as inputs.
5. The CSI-based monitoring method according to claim 4,
the gait cycle time prediction method in step S33 includes the steps of:
s331 estimating gait cycle time using upper contour of torso reflex, torso contour frequency fct(t) is defined as:
wherein F (F, t) is the amplitude at time t and frequency F after fast Fourier transform,
is a frequency range of 0 to fmaxThe total energy between the two is 5 percent;
s332 obtaining the trunk contour frequency fct(t) obtaining the moving speed v of the trunk outline by using the following formulatc(t)：
vtc(t)＝ftc(t)ε/2
Wherein epsilon is the wavelength of the WiFi signal;
s333 estimates a gait cycle time R (τ) from the movement velocity of the torso contour by using autocorrelation of the torso contour curve:
where μ is the mean velocity of the torso contour and τ is the time offset of the torso contour curve;
the limb movement speed prediction method comprises the following steps:
s334 estimates torso and leg velocities using a percentile method developed for doppler radars, the percentile for a given frequency f being defined as:
wherein P (f, t) is the cumulative percentage of energy with frequency below f to the total energy of the FFT result at time t;
s335 the forecast of the trunk movement speed is the lowest frequency value in the range of P (f, t) > 50%, and the forecast of the leg movement speed is the lowest frequency value in the range of P (f, t) ≧ 95%.
6. The CSI-based monitoring method according to claim 3, wherein the respiration recognition algorithm in the step S4 comprises the following steps:
s41, after the CSI data are extracted by the WiFi receiving terminal, removing environmental noise through a filter based on empirical mode decomposition to obtain noise-reduced CSI data;
s42, screening out CSI data with the largest variance as a subcarrier most sensitive to the tiny human body movement by comparing the variances of the CSI measurements after noise reduction;
s43, calculating the distance between every two adjacent waveform peaks in the CSI data of the most sensitive subcarrier, selecting the maximum distance value as a respiration period, and extracting respiration characteristics by using a morphological characteristic method;
s44 identifies identity information of the monitored person using a trained deep neural network based classifier using the extracted respiratory features as input.
7. The CSI-based monitoring method according to claim 6, wherein the morphological characterization method in step S43 includes the following steps:
during a respiratory cycle, with HtRepresenting the difference between the maximum amplitude of respiration and the minimum amplitude of respiration, using
Height representing p% position from the breath minimum amplitude point:
wherein p represents a parameter of position;
by using
Is shown in position
Intercept of the respiratory waveform at time, and therefore, respiratory characteristics at the p% position
Expressed as:
8. the CSI-based monitoring method according to claim 3, further comprising an alarm module, wherein if the monitored person is in an abnormal isolation state, an alarm signal is sent to the alarm module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111298868.0A CN114079859A (en) | 2021-11-04 | 2021-11-04 | Monitoring device and monitoring method based on CSI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111298868.0A CN114079859A (en) | 2021-11-04 | 2021-11-04 | Monitoring device and monitoring method based on CSI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114079859A true CN114079859A (en) | 2022-02-22 |
Family
ID=80283580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111298868.0A Pending CN114079859A (en) | 2021-11-04 | 2021-11-04 | Monitoring device and monitoring method based on CSI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114079859A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106658590A (en) * | 2016-12-28 | 2017-05-10 | 南京航空航天大学 | Design and implementation of multi-person indoor environment state monitoring system based on WiFi channel state information |
| CN106971474A (en) * | 2017-04-10 | 2017-07-21 | 南京苗米科技有限公司 | Intrusion detection method and system based on WIFI wireless signals |
| US20170354349A1 (en) * | 2016-06-10 | 2017-12-14 | The Regents Of The University Of California | Wifi-based person-identification technique for use in smart spaces |
| CN109587645A (en) * | 2018-11-12 | 2019-04-05 | 南京邮电大学 | Personnel's recognition methods under indoor environment based on channel state information |
| CN110059633A (en) * | 2019-04-19 | 2019-07-26 | 西北工业大学 | A kind of body gait based on ultrasound perception and its personal identification method |
| CN110123328A (en) * | 2019-06-26 | 2019-08-16 | 南京苗米科技有限公司 | A kind of respiratory rate detection method based on wireless identification |
| CN110337066A (en) * | 2019-05-21 | 2019-10-15 | 西安电子科技大学 | Based on channel state information indoor occupant activity recognition method, man-machine interactive system |
| CN112333653A (en) * | 2020-09-22 | 2021-02-05 | 西安电子科技大学 | Identity intelligent identification method and system based on WiFi channel state information |
-
2021
- 2021-11-04 CN CN202111298868.0A patent/CN114079859A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170354349A1 (en) * | 2016-06-10 | 2017-12-14 | The Regents Of The University Of California | Wifi-based person-identification technique for use in smart spaces |
| CN106658590A (en) * | 2016-12-28 | 2017-05-10 | 南京航空航天大学 | Design and implementation of multi-person indoor environment state monitoring system based on WiFi channel state information |
| CN106971474A (en) * | 2017-04-10 | 2017-07-21 | 南京苗米科技有限公司 | Intrusion detection method and system based on WIFI wireless signals |
| CN109587645A (en) * | 2018-11-12 | 2019-04-05 | 南京邮电大学 | Personnel's recognition methods under indoor environment based on channel state information |
| CN110059633A (en) * | 2019-04-19 | 2019-07-26 | 西北工业大学 | A kind of body gait based on ultrasound perception and its personal identification method |
| CN110337066A (en) * | 2019-05-21 | 2019-10-15 | 西安电子科技大学 | Based on channel state information indoor occupant activity recognition method, man-machine interactive system |
| CN110123328A (en) * | 2019-06-26 | 2019-08-16 | 南京苗米科技有限公司 | A kind of respiratory rate detection method based on wireless identification |
| CN112333653A (en) * | 2020-09-22 | 2021-02-05 | 西安电子科技大学 | Identity intelligent identification method and system based on WiFi channel state information |
Non-Patent Citations (3)
| Title |
|---|
| SANGYOUN LEE: "Design and implementation of monitoring system for breathing and heart rate pattern using WiFi signals", 《2018 15TH IEEE ANNUAL CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE (CCNC)》, 15 January 2018 (2018-01-15) * |
| WEI WANG: "Gait Recognition Using WiFi Signals", 《PROCEEDINGS OF THE 2016 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING》, 30 September 2016 (2016-09-30), pages 3 - 6 * |
| 范鑫鑫: "基于无线感知的人体属性识别方法研究", 《中国优秀硕士学位论文全文数据库(电子期刊)》, 15 February 2020 (2020-02-15), pages 2 - 5 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111481184B (en) | Multi-target respiration heart rate monitoring method and system based on millimeter wave radar technology | |
| Brodie et al. | Wearable pendant device monitoring using new wavelet-based methods shows daily life and laboratory gaits are different | |
| WO2019169864A1 (en) | Csi signal in wi-fi-based human body movement and respiration detection method and system | |
| Doukas et al. | Advanced patient or elder fall detection based on movement and sound data | |
| EP3803709B1 (en) | Detecting abnormalities in ecg signals | |
| CN113925475B (en) | Non-contact human health monitoring system and monitoring method | |
| CN112998701A (en) | Vital sign detection and identity recognition system and method based on millimeter wave radar | |
| US20090312660A1 (en) | Recognition and localisation of pathologic animal and human sounds | |
| CN107822617B (en) | Heartbeat anomaly detection method based on WiFi signals | |
| CN109009125B (en) | Driver's fine granularity monitoring of respiration method and system based on audio frequency of mobile terminal | |
| Huang et al. | G-fall: device-free and training-free fall detection with geophones | |
| EP3692898A1 (en) | Sleep/motion determination based on wi-fi signals | |
| CN113435283B (en) | Ultra-wideband radar identity recognition method based on breath sample space | |
| CN112998689B (en) | Non-contact multi-person real-time respiration condition evaluation system, device and storage medium | |
| Valero et al. | Vibration sensing-based human and infrastructure safety/health monitoring: A survey | |
| CN110717461A (en) | Fatigue state identification method, device and equipment | |
| CN209032422U (en) | A kind of cardiechema signals detection device | |
| KR20210058676A (en) | Apparatus and method for cardiac signal processing, monitoring system comprising the same | |
| KR102281420B1 (en) | Smart toilet system for bio signal measurement capable of user authentication and monitoring of fall | |
| KR102395937B1 (en) | Health state prediction method and system based on gait time-frequency analysis | |
| CN114079859A (en) | Monitoring device and monitoring method based on CSI | |
| CN116439690A (en) | Ballistocardiogram signal extraction method, ballistocardiogram signal extraction device, ballistocardiogram signal extraction equipment and storage medium | |
| Lopez et al. | Walk and jog characterization using a triaxial accelerometer | |
| Wu et al. | Unobtrusive monitoring of sedentary behaviors with fusion of bluetooth and ballistocardiogram signals | |
| Valero et al. | Reprint of: Vibration sensing-based human and infrastructure safety/health monitoring: A survey |
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 |