Human body activity identification method based on CSI signal and DenseNet network
A technology of human activity and recognition method, applied in the field of human activity recognition, can solve the problems of insufficient recognition, ignoring feature information, and low recognition effect, and achieves the effects of good feature extraction, low recognition cost, and good robustness.
Active Publication Date: 2021-10-29
NORTHWEST UNIV(CN)
View PDF3 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] (1) The features manually extracted by the machine learning classifier in the prior art are not enough for subsequent recognition, and the recognition effect is not high
[0011] (2) The method of using long-short-term memory network in the prior art takes a long time to train, and only mines information about actions in the time dimension of the CSI sequence
[0012] The difficulty in solving the above problems and defects is: CSI sequences are correlated in time and space. Although the existing methods use automatic extraction of CSI sequence features, they often ignore the feature information in the spatial dimension. Therefore, how to design a It is challenging to automatically extract CSI sequence features and be able to deeply mine the temporal and spatial correlation information of CSI sequences
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 Construction
[0069] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0070]Aiming at the problems existing in the prior art, the present invention provides a method for human body activity recognition based on CSI signals using a DenseNet network. The present invention will be described in detail below with reference to the accompanying drawings.
[0071] DenseNet provided by the present invention carries out the identification method of human body activity, and those of ordinary skill in the industry can also adopt other steps to implement, figure 1 The DenseNet provided by the present invention carries out the recognition method of human body activity only a specific embodiment. There are ot...
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 belongs to the technical field of human body activity identification, and discloses a human body activity identification method based on a CSI (Channel State Information) signal and a DenseNet network, which comprises the following steps: acquiring action data in two indoor environments, using two computers provided with Intel 5300 wireless network cards as transceivers, and setting corresponding parameters; in the communication process between the sending end and the receiving end of the equipment, adopting a linear interpolation method to supplement lost data; using a Butterworth low-pass filter for filtering out some high-frequency noise generated by internal power conversion of the transceiver, and using discrete wavelet transform for removing low-frequency noise on the whole bandwidth; performing dimension reduction processing on the data by using principal component analysis, retaining some most important features of the high-dimensional data, and removing noise and unimportant features to achieve the purpose of improving the data processing speed; and designing a network framework, and selecting related parameters for training. The method improves the recognition precision, and has good robustness and reliability.
Description
technical field [0001] The invention belongs to the technical field of human body activity recognition, and in particular relates to a method for human body activity recognition using a DenseNet network based on CSI signals. Background technique [0002] At present, with the rapid development of computer science, realizing high-level human-computer interaction is an important development direction in the future, including accurate perception and understanding of human behavior. Human activity recognition is of great significance in fall detection, physiological indicator perception, group perception, and identity authentication. At present, the technical means of human activity recognition mainly include the following methods: methods based on computer vision, methods based on wearing sensors and methods based on WiFi signals. S.Herath, M.Harandi and F.Porikli published the paper "Going deeper into action recognition: Asurvey Image and Vision Computing", based on the comput...
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 & AuthorityApplications(China)
IPC IPC(8): H04B17/309H04W4/33H04W4/021G08B21/04H04L9/32G06N3/04G06N3/08
CPCH04B17/309H04W4/33H04W4/021G08B21/043H04L9/3231G06N3/08G06N3/045
Inventor贺晨李月媛黄亮马存燕韩璐阳程艺璇王丹萍赵健
OwnerNORTHWEST UNIV(CN)