High Accuracy WiFi-Based Human Activity Classification System with Time-Frequency Diagram CNN Method for Different Places.

Lokesh Sharma,Chung-Hao Chao,Shih-Lin Wu,Mei-Chen Li

doi:10.3390/s21113797

Abstract

Older people are very likely to fall, which is a significant threat to the health. However, falls are preventable and are not necessarily an inevitable part of aging. Many different fall detection systems have been developed to help people avoid falling. However, traditional systems based on wearable devices or image recognition-based have many disadvantages, such as user-unfriendly, privacy issues. Recently, WiFi-based fall detection systems try to solve the above problems. However, there is a common problem of reduced accuracy. Since the system is trained at the original signal collecting/training place, however, the application is at a different place. The proposed solution only extracts the features of the changed signal, which is caused by a specific human action. To implement this, we used Channel State Information (CSI) to train Convolutional Neural Networks (CNNs) and further classify the action. We have designed a prototype to test the performance of our proposed method. Our simulation results show an average accuracy of same place and different place is 93.2% and 90.3%, respectively.

Highlights

According to the US Centers for Disease Control and Prevention, one out of every four elder people over the age of 65 years has fallen once in a year, and less than half of them have not informed their doctors
We first compare the difference between Convolutional Neural Networks (CNNs) use and Support Vector Machine (SVM) and Deep Neural Network (DNN) use, where Channel State Information (CSI) amplitude is used directly as the input at the same place
It demonstrates that our approach can retain excellent accuracy when measured in various places, showing that converting the CSI to the time-frequency diagram can minimize

Summary

Introduction

According to the US Centers for Disease Control and Prevention, one out of every four elder people over the age of 65 years has fallen once in a year, and less than half of them have not informed their doctors. The risk of falling again will be double if you have fallen once [1]. Falling is a dangerous situation for the elderly, and it can result in fractures, internal bleeding, and death in severe cases. The expenses of fall medical care are a major annual expenditure for a country. In 2015, the United States used more than 50 billion USD in medical expenses for falls [1]. Because of the above reasons, a precise and convenient fall detection system is essential

Objectives

Methods

Results

Discussion

Conclusion