WO2019169864A1 - Signal csi dans un mouvement du corps humain basé sur wi-fi et procédé et système de détection de respiration - Google Patents
Signal csi dans un mouvement du corps humain basé sur wi-fi et procédé et système de détection de respiration Download PDFInfo
- Publication number
- WO2019169864A1 WO2019169864A1 PCT/CN2018/110257 CN2018110257W WO2019169864A1 WO 2019169864 A1 WO2019169864 A1 WO 2019169864A1 CN 2018110257 W CN2018110257 W CN 2018110257W WO 2019169864 A1 WO2019169864 A1 WO 2019169864A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- csi
- csi signal
- human body
- breathing
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
- A61B5/0022—Monitoring a patient using a global network, e.g. telephone networks, internet
-
- 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
-
- 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
- A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the invention belongs to the field of smart home technology, and particularly relates to a method and a system for detecting human motion and breathing based on a CSI signal in Wi-Fi.
- CSI Channel State Information
- the 802.11n-based WiFi technology uses a MIMO-OFDM system. Using the tool software provided by Daniel Halperin of the University of Washington, it can acquire 30 subcarriers in a wireless communication channel. Finally, a standardized CSI matrix H—n*m* can be obtained. A complex matrix of 30, where n represents the number of transmit antennas, m represents the number of received antennas, and 30 is the number of subcarrier information.
- a modular matrix of 2*3*30 channel information is as follows:
- Chinese Patent Publication No. CN106108904A discloses a non-contact real-time measurement method for human respiratory parameters, which is characterized in that it comprises the following steps: (1) generating a Wi-Fi signal in the vicinity of a human body, and collecting a channel state in a Wi-Fi signal.
- Chinese Patent Publication No. CN105962946A discloses a non-contact human body sleeping posture safety detecting method, comprising the steps of: generating a Wi-Fi signal around a human body, collecting a channel state signal CSI in a Wi-Fi signal; and extracting a channel state signal.
- the cycle of the CSI, the cycle is input to the pre-trained classifier, and the classifier outputs the sleep posture type.
- the number of the Wi-Fi signals is plural, distributed around the upper limbs of the human body.
- the Wi-Fi The number of signals is at least three, one on the left side of the upper limb of the human body, the other on the right side of the upper limb of the human body, and the remaining one around the head of the human body.
- the detection of human breathing does not involve the posture of the human body movement, and thus the detection of the human body state cannot be achieved to a more precise degree.
- Embodiments of the present invention provide a method and system for detecting human motion and breathing based on a CSI signal in Wi-Fi, aiming at solving the prior art that only the breathing parameters are detected, and the accurate detection of the human body state cannot be satisfied.
- One embodiment of the present invention is a method for detecting multi-person motion and breathing based on a CSI signal in Wi-Fi, the detection method comprising the following steps:
- the CSI signal is extracted from the indoor Wi-Fi wireless signal, and the CSI signal of the indoor unmanned time and the CSI signal data of the different postures and breathing of the indoor human body at different positions are obtained;
- the motion data of the human body is marked for establishing a respiratory recognition model
- the data of the human body action posture is marked for establishing a behavior recognition model
- the monitoring area is divided by CSI changes at different locations, and a spatial monitoring model is established.
- the acquired CSI signals in Wi-Fi are used to identify indoor human body position, behavior, and breathing.
- the respiratory recognition model, behavior recognition model and spatial monitoring model are models established by using the full-link neural network as a deep learning method for the recognition of human behavior.
- the invention relates to the application of Wi-Fi CSI to the environment and the human body to realize home security, human body monitoring and extension applications.
- the present invention extracts a CSI signal from a Wi-Fi wireless signal by receiving a wireless signal from an indoor Wi-Fi router.
- the three AI models work together to identify indoor human behavior and breathing.
- the three models are:
- a spatial monitoring model that identifies if someone is present and where the human body is located.
- the behavior recognition model recognizes the behavior of the human body, such as walking, falling, sitting, lying, and the like.
- the respiratory recognition model recognizes the human body's call and aspiration signals, first identifies the extreme points of the call and the suction, and then connects through the curve to form a breathing curve.
- FCNN Fully Connected Neural Network
- the accuracy of the CSI signal used in the present invention is much higher than that of the RSSI signal, and the CSI can detect even smaller fluctuations such as heart rate, and can reach the millimeter level. At least 30 channel state fluctuations in each CSI data packet can be analyzed, and characteristic data related to respiratory fluctuation fluctuations can be extracted from the data due to multipath suppression;
- the present invention does not attempt to completely remove the noise data, and the AI model is established by the deep learning method while retaining the noise data. Therefore, in the actual application scenario, it shows higher accuracy. After all, in the actual scene, the noise data can not be completely removed. Only by putting noise together in the model can you achieve better accuracy in the actual environment;
- Multi-function It can monitor the owner's movements (walking, falling, breathing, etc.) and provide health monitoring. In addition, when the owner is not at home, the foreign invasion will be monitored and security services will be provided.
- FIG. 1 is a flow chart of creating an AI model in an embodiment of the present invention.
- FIG. 2 is a flow chart of the use of an AI model in an embodiment of the present invention.
- FIG. 3 is a flowchart of identifying an AI model in an embodiment of the present invention.
- FIG. 4 is a Wi-Fi CSI signal distribution diagram when no one is indoors in the embodiment of the present invention.
- FIG. 5 is a Wi-Fi CSI signal distribution diagram when a person walks indoors in an embodiment of the present invention.
- Figure 6 is a graph of the breathing curve resolved from the Wi-Fi signal in the embodiment of the present invention.
- a multi-person motion and breathing detection method based on a CSI signal in Wi-Fi the process mainly includes the following steps: 1. collecting data; 2. data integration; 3. filtering And standardization; 4. Establish models; 5. Apply models for human behavior and respiratory recognition.
- the steps for identifying the CSI signal are:
- the processed data is directly input to the model, and different models will have different classification outputs. Thereby achieving the recognition of behavior and breathing. See the multi-model workflow of Figure 3.
- the classification model will derive the current human behavior or breathing curve based on changes in the CSI signal.
- the CSI signal is extracted from the indoor Wi-Fi wireless signal, and the CSI signal of the indoor unmanned time and the CSI signal data of the different postures and breathing of the indoor human body at different positions are obtained;
- the motion data of the human body is marked for establishing a respiratory recognition model
- the data of the human body action posture is marked for establishing a behavior recognition model
- the CSI changes the monitoring area to establish a spatial monitoring model; using the established respiratory recognition model, behavior recognition model and spatial monitoring model, using the acquired Wi-Fi CSI signal to the indoor human body position and behavior Breathing for identification.
- the respiratory recognition model, behavior recognition model and spatial monitoring model are models established by using the full-link neural network as a deep learning method for the recognition of human behavior.
- the indoor CSI signal when there is no one including the door, the window, and the air conditioner opening and closing state.
- CSI signal data of different postures and respirations of indoor human body in different positions include:
- CSI signal data of a person's breathing in a standing, sitting still position including respiratory data of deep and rapid breathing
- the CSI signal data of the human body is in a moving posture of walking and squatting.
- preprocessing the CSI signal data includes:
- Butterworth filtering is performed twice.
- the filtering process is to first pass the signal sequence forward through the filter to obtain the output of the first filtering, and then perform the time domain inversion of the output sequence of the first filtering, and then flip the time domain.
- the sequence is subjected to secondary filtering by the same filter, and the output of the secondary filtering is again subjected to time domain inversion, thereby obtaining filtered CSI data;
- the Z-score standardization method is used to normalize the data by the mean and standard deviation of the original data.
- the processed data conforms to the standard normal distribution, that is, the mean value is 0, the standard deviation is 1, and the conversion function is:
- ⁇ is the mean of all sample data and ⁇ is the standard deviation of all sample data.
- the action processes of the call, the suction, and the breath holding in the CSI signal data are respectively marked 1, 2, and 3, and are used for the training sample of the respiratory recognition model, wherein
- the call and the suction action are recorded from the start of the action, and the whole process is recorded, including the highest (sucking) and minimum (call) points.
- the breath holding action is in the process of breathing action, and suddenly the breath is held, and the whole process of recording the entire breath is recorded;
- the human behavioral actions including standing, sitting, lying, walking, and squatting are marked as 4, 5, 6, 7, and 8, and training samples for the behavior recognition model;
- the CSI signal data describes the signal distribution in the room, and the monitoring area is divided by CSI changes at different locations to establish a spatial monitoring model
- a deep neural network is used to create a classification model including a respiratory recognition model, a behavior recognition model, and a spatial monitoring model, and a classification model is used to identify human body position, behavior, and breathing.
- the method in Figure 3 is a method in which multiple models work together.
- the spatial monitoring model identifies whether someone exists and then gives its location.
- the behavior recognition model identifies the action type of the human body (walking, falling, sitting, lying, falling, etc.) and identifies whether it is in a static state (standing, lying, sitting, etc.), and if it is stationary, the respiratory recognition model will give The breathing state that appears and depicts the breathing curve.
- the above AI model identification is based on changes in the indoor Wi-Fi CSI signal.
- FIG. 4 and FIG. 5 it is easier to understand that the unmanned person and the person walking in the room are displayed in the form of a Wi-Fi CSI signal change map.
- Figure 4 shows the distribution of Wi-Fi CSI signals when no one is indoors. It can be seen that the signal at this time is very stable and evenly distributed.
- Figure 5 when someone walks, the change in the Wi-Fi CSI signal can be clearly seen.
- the interference of human motion and breathing on the Wi-Fi CSI signal is the basis of the proposed method of the present invention.
- Fig. 6 is a breathing curve analyzed from a Wi-Fi signal.
- the breathing recognition model first recognizes the time point of the call and the suction, and then draws a curve by the method of connecting the lines.
- a multi-person motion and breathing detection system based on a CSI signal in Wi-Fi, the system comprising an indoor Wi-Fi router, a memory, and
- processors coupled to the memory, the processor being configured to execute instructions in the memory, the operations performed by the processor comprising:
- the CSI signal is extracted from the indoor Wi-Fi wireless signal, and the CSI signal of the indoor unmanned time and the CSI signal data of the different postures and breathing of the indoor human body at different positions are obtained;
- the motion data of the human body is marked for establishing a respiratory recognition model
- the data of the human body action posture is marked for establishing a behavior recognition model
- the monitoring area is divided into CSI changes at different locations, and a spatial monitoring model is established;
- the acquired CSI signals in Wi-Fi are used to identify indoor human body position, behavior, and breathing.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pulmonology (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
La présente invention concerne un signal CSI dans un mouvement du corps humain basé sur Wi-Fi et un procédé et un système de détection de respiration, le procédé de détection comprenant les étapes suivantes : extraction du signal CSI du signal Wi-Fi sans fil intérieur, et acquisition du signal CSI lorsque personne ne se trouve à l'intérieur et les données de signal CSI du corps humain d'intérieur à différentes positions et dans différentes postures et une respiration différente ; prétraitement de toutes les données de signal CSI acquises ; dans les données de signal CSI, marquage des données de mouvement de la respiration du corps humain pour établir un module de reconnaissance de respiration ; dans les données de signal CSI, marquage des données de la posture du corps humain pour établir un module de reconnaissance de comportement ; et division des zones de surveillance en fonction des changements de CSI à différentes positions dans les données de signal CSI pour établir un module de surveillance d'espace.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810177910.5A CN108553108B (zh) | 2018-03-05 | 2018-03-05 | 一种基于Wi-Fi中CSI信号的人体动作与呼吸的检测方法和系统 |
CN201810177910.5 | 2018-03-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019169864A1 true WO2019169864A1 (fr) | 2019-09-12 |
Family
ID=63531544
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/110257 WO2019169864A1 (fr) | 2018-03-05 | 2018-10-15 | Signal csi dans un mouvement du corps humain basé sur wi-fi et procédé et système de détection de respiration |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108553108B (fr) |
WO (1) | WO2019169864A1 (fr) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114916912A (zh) * | 2022-05-09 | 2022-08-19 | 大连理工大学 | 一种非接触式的睡眠呼吸暂停检测方法及装置 |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108553108B (zh) * | 2018-03-05 | 2020-04-14 | 上海百芝龙网络科技有限公司 | 一种基于Wi-Fi中CSI信号的人体动作与呼吸的检测方法和系统 |
CN109394229A (zh) * | 2018-11-22 | 2019-03-01 | 九牧厨卫股份有限公司 | 一种跌倒检测方法、装置及系统 |
EP3692898A1 (fr) * | 2019-02-11 | 2020-08-12 | Nokia Technologies Oy | Détermination de sommeil/mouvement basée sur des signaux wi-fi |
CN110176968B (zh) * | 2019-05-20 | 2021-04-06 | 桂林理工大学 | 一种用于WiFi人体行为识别中的跳变现象纠正方法 |
CN110301917B (zh) * | 2019-06-14 | 2020-09-08 | 北京大学 | 一种无接触呼吸检测方法及装置 |
CN110200610A (zh) * | 2019-07-04 | 2019-09-06 | 合肥工业大学 | 一种基于WiFi信号的增强呼吸及心率实时监测评估方法系统 |
CN110262278B (zh) * | 2019-07-31 | 2020-12-11 | 珠海格力电器股份有限公司 | 智能家电设备的控制方法及装置、智能电器设备 |
CN113116294A (zh) * | 2019-12-30 | 2021-07-16 | 上海际链网络科技有限公司 | 人员身体状况的监测方法及装置 |
CN111306716A (zh) * | 2020-03-03 | 2020-06-19 | 青岛海尔空调器有限总公司 | 空调器及其控制方法 |
CN111436939B (zh) * | 2020-03-17 | 2023-04-18 | 佛山市台风网络科技有限公司 | 基于深度学习的识别体征信号的方法、系统、设备及介质 |
CN112153736B (zh) * | 2020-09-14 | 2022-07-26 | 南京邮电大学 | 一种基于信道状态信息的人员动作识别和位置估计方法 |
US11998312B2 (en) | 2020-09-30 | 2024-06-04 | Nxp Usa, Inc. | Systems and methods for breathing detection and rate estimation using wireless communication signals |
CN112578726A (zh) * | 2021-01-06 | 2021-03-30 | 常州百芝龙智慧科技有限公司 | 一种自主学习人体行为习惯的人体异常监控设备 |
CN113054491B (zh) * | 2021-03-08 | 2022-07-05 | 常州百芝龙智慧科技有限公司 | 一种基于Wi-Fi人体移动侦测的AI插座系统 |
US11706008B2 (en) | 2021-04-29 | 2023-07-18 | Hewlett Packard Enterprise Development Lp | Adaptive channel sounding |
CN113907743B (zh) * | 2021-11-11 | 2022-06-17 | 四川大学 | Cgan和多尺度卷积神经网络实现呼吸检测的方法及系统 |
KR20230070849A (ko) * | 2021-11-15 | 2023-05-23 | 울산과학기술원 | Csi 패턴변화와 표준편차를 이용한 예측장치 및 그 방법 |
CN115795377B (zh) * | 2023-01-30 | 2023-08-08 | 深圳大学 | 呼吸状态分类器生成方法、呼吸状态监测方法及相关装置 |
CN117158924A (zh) * | 2023-08-08 | 2023-12-05 | 知榆科技有限公司 | 健康监测方法、装置、系统及存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951757A (zh) * | 2015-06-10 | 2015-09-30 | 南京大学 | 一种基于无线信号的动作检测和识别的方法 |
CN106446828A (zh) * | 2016-09-22 | 2017-02-22 | 西北工业大学 | 一种基于Wi‑Fi信号的用户身份识别方法 |
WO2017156492A1 (fr) * | 2016-03-11 | 2017-09-14 | Origin Wireless, Inc. | Procédés, appareil, serveurs et systèmes pour détection et surveillance de signes vitaux |
CN107331136A (zh) * | 2017-05-11 | 2017-11-07 | 深圳市斑点猫信息技术有限公司 | 基于WiFi的室内人体活动检测方法和系统 |
CN108553108A (zh) * | 2018-03-05 | 2018-09-21 | 叶伟 | 一种基于Wi-Fi中CSI信号的人体动作与呼吸的检测方法和系统 |
-
2018
- 2018-03-05 CN CN201810177910.5A patent/CN108553108B/zh active Active
- 2018-10-15 WO PCT/CN2018/110257 patent/WO2019169864A1/fr active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951757A (zh) * | 2015-06-10 | 2015-09-30 | 南京大学 | 一种基于无线信号的动作检测和识别的方法 |
WO2017156492A1 (fr) * | 2016-03-11 | 2017-09-14 | Origin Wireless, Inc. | Procédés, appareil, serveurs et systèmes pour détection et surveillance de signes vitaux |
CN106446828A (zh) * | 2016-09-22 | 2017-02-22 | 西北工业大学 | 一种基于Wi‑Fi信号的用户身份识别方法 |
CN107331136A (zh) * | 2017-05-11 | 2017-11-07 | 深圳市斑点猫信息技术有限公司 | 基于WiFi的室内人体活动检测方法和系统 |
CN108553108A (zh) * | 2018-03-05 | 2018-09-21 | 叶伟 | 一种基于Wi-Fi中CSI信号的人体动作与呼吸的检测方法和系统 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114916912A (zh) * | 2022-05-09 | 2022-08-19 | 大连理工大学 | 一种非接触式的睡眠呼吸暂停检测方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN108553108B (zh) | 2020-04-14 |
CN108553108A (zh) | 2018-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019169864A1 (fr) | Signal csi dans un mouvement du corps humain basé sur wi-fi et procédé et système de détection de respiration | |
Gu et al. | Paws: Passive human activity recognition based on wifi ambient signals | |
Geng et al. | Enlighten wearable physiological monitoring systems: On-body rf characteristics based human motion classification using a support vector machine | |
US11978256B2 (en) | Face concealment detection | |
Janssen et al. | Video-based respiration monitoring with automatic region of interest detection | |
Planinc et al. | Introducing the use of depth data for fall detection | |
Gjoreski et al. | Accelerometer placement for posture recognition and fall detection | |
Khan et al. | A deep learning framework using passive WiFi sensing for respiration monitoring | |
US20190012531A1 (en) | Movement monitoring system | |
CN109948472A (zh) | 一种基于姿态估计的非侵入式人体热舒适检测方法及系统 | |
CN111089604B (zh) | 基于可穿戴传感器的健身运动识别方法 | |
Fang et al. | Headscan: A wearable system for radio-based sensing of head and mouth-related activities | |
CN110012114B (zh) | 一种基于物联网的环境安全预警系统 | |
Zhu et al. | NotiFi: A ubiquitous WiFi-based abnormal activity detection system | |
CN109657572B (zh) | 一种基于Wi-Fi的墙后目标行为识别方法 | |
KR102134154B1 (ko) | 1-d cnn 기반의 uwb 호흡 데이터 패턴 인식 시스템 | |
CN112364769B (zh) | 基于商用Wi-Fi的人群计数方法 | |
CN114818788A (zh) | 基于毫米波感知的追踪目标状态识别方法和装置 | |
Ding et al. | Energy efficient human activity recognition using wearable sensors | |
Jia et al. | BeAware: Convolutional neural network (CNN) based user behavior understanding through WiFi channel state information | |
Shimokawara et al. | Estimation of basic activities of daily living using zigbee 3d accelerometer sensor network | |
Turetta et al. | Practical identity recognition using wifi's channel state information | |
Semenov et al. | Covid-19 social distance proximity estimation using machine learning analyses of smartphone sensor data | |
CN112364770B (zh) | 基于商用Wi-Fi人体活动识别与动作质量评估方法 | |
Sadhwani et al. | Non-collaborative human presence detection using channel state information of Wi-Fi signal and long-short term memory neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18908310 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18908310 Country of ref document: EP Kind code of ref document: A1 |