A fall detection method and system combining ECG and inertial sensing data
A technology of inertial sensing and detection methods, applied in inertial sensors, sensors, diagnostic recording/measurement, etc., can solve the problems of accuracy affected by wearing position, small size, etc., to improve fall detection accuracy, comprehensive information, and avoidance of falls. The effect of defects
Inactive Publication Date: 2021-09-24
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF16 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Wearable devices are mainly inertial sensors, which are small in size and can be worn anywhere. They are widely used in the field of fall detection, but their accuracy is affected by the wearing position
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0092] Such as figure 1 , figure 2 As shown, a fall detection method combining ECG and inertial sensing data, including:
[0093] S1: Use a wrist wearable device including ECG and inertial sensing unit to collect fall data and daily movement data during daily human activities;
[0094] S2: dividing the collected fall data and daily action data into the same time period;
[0095] S3: respectively extracting the features of the segmented fall data and daily action data to obtain inertial sensor data features and ECG data features;
[0096] S4: Perform normalization processing on the inertial sensing data features and ECG data features to obtain normalized sample data features;
[0097] S5: Using a principal component analysis algorithm to perform dimensionality reduction processing on the normalized sample data features to obtain dimensionality reduction data features, and using a support vector machine algorithm to classify the dimensionality reduction data features to obta...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fall detection method and system combining ECG and inertial sensing data, comprising: using equipment including ECG and inertial sensing units to collect fall data and daily action data in the process of human daily activities; After the fall data and daily action data are divided according to the same time period, the inertial sensor data features and ECG data features are extracted respectively, and the normalized sample data features are obtained by normalization processing; the principal component analysis algorithm is used to analyze the Perform dimensionality reduction processing on the normalized sample data features to obtain the dimensionality reduction data features, use the support vector machine algorithm to classify the dimensionality reduction data features, and obtain the support vector machine classification model; input the newly collected data into the support vector machine classification model Get the fall detection result. Reflect the changes in the human fall process from two different dimensions of human physiological activity and posture, avoid the inaccurate defect of a single type of data, and improve the accuracy of fall detection.
Description
technical field [0001] The invention relates to the field of human body fall detection, in particular to a fall detection method and system combining electrocardiogram and inertial sensing data. Background technique [0002] Falling can cause psychological and physical harm to the elderly, and is one of the important factors that threaten the health of the elderly. Fall detection refers to the collection of human activity data and the detection of falls through data analysis. Devices used for human activity data collection are divided into environment sensing devices and wearable devices. Environmental sensing devices do not need to be worn by the human body, but the monitoring range is limited. Wearable devices are mainly inertial sensors, which are small in size and can be worn anywhere. They are widely used in the field of fall detection, but their accuracy is affected by the wearing position. [0003] In recent years, studies have used wearable electrocardiogram (ECG)...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/318A61B5/366A61B5/355A61B5/353A61B5/11A61B5/00
CPCA61B5/725A61B5/1117A61B5/1116A61B5/7264A61B5/7267A61B2562/0219
Inventor 刘勇国陶文元杨尚明李巧勤
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA