Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Small-Sample Passive Behavior Perception Method Based on Autoencoder Data Augmentation

A self-encoder, small sample technology, applied in the field of passive behavior perception, can solve the problems of single sample and insufficient data samples, and achieve the effect of increasing the number and diversity, improving the accuracy and improving the discrimination ability.

Active Publication Date: 2022-07-26
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above technical problems, the present invention provides a small-sample passive behavior perception method based on autoencoder data enhancement, and designs a deep autoencoder based on convolutional neural network, aiming to solve the problem of human behavior recognition in the prior art. Insufficient data samples and over-fitting problems caused by a single sample

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Small-Sample Passive Behavior Perception Method Based on Autoencoder Data Augmentation
  • A Small-Sample Passive Behavior Perception Method Based on Autoencoder Data Augmentation
  • A Small-Sample Passive Behavior Perception Method Based on Autoencoder Data Augmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Embodiments of the present invention will be disclosed in the drawings below, and for the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the invention. That is, in some embodiments of the invention, these practical details are unnecessary.

[0035] like figure 1 As shown, the present invention provides a small-sample passive behavior perception method based on autoencoder data enhancement, including CSI data acquisition, data processing and behavior recognition.

[0036] like figure 2 As shown, the specific steps of the method are as follows:

[0037] (1) Deploy commercial WiFi devices indoors to transmit WiFi signals. When the signal encounters the human body during the propagation process, phenomena such as reflection, refraction, diffraction and scattering will occur, which will disturb the normal propagation of the signal. ...

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

No PUM Login to View More

Abstract

The invention is a small sample passive behavior perception method based on self-encoder data enhancement, comprising the following steps: (1) collecting channel state information including human behavior information; (2) denoising the channel state information; (3) ) construct a neural network model based on data augmentation autoencoder; (4) use a small amount of real samples to train data augmentation autoencoder to generate a large number of reconstructed samples with different feature vectors; (5) construct a convolutional neural network based Based on the human behavior recognition model, the enhanced data samples and real samples are used as the input of the model, the network model is optimized, and the behavior recognition results are obtained according to the response values ​​of the classification network to the samples in different categories. The invention solves the model overfitting problem existing in passive behavior perception in the state of small sample training data, enhances the generalization and stability of the model, and ensures the accuracy of human behavior recognition.

Description

technical field [0001] The invention relates to the technical field of passive behavior perception, in particular to a small-sample passive behavior perception method based on self-encoder data enhancement. Background technique [0002] Human behavior is an intuitive and natural means of interaction between humans and machines, and human behavior recognition plays an important role in practical applications such as smart homes, healthcare, and fitness tracking. Passive sensing technology can utilize WiFi signals widely existing in the environment to analyze the influence of human behavior on channel state information, so as to realize sensing tasks, and has good universality and scalability. Compared with the traditional human behavior sensing technology, WiFi sensing technology has the advantages of non-line-of-sight, passive sensing that does not need to carry sensors, low cost, easy deployment, not limited by lighting conditions, and strong scalability. [0003] ZL202010...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/045G06F2218/04G06F2218/08
Inventor 盛碧云关翔宇肖甫李群沙乐天
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products