A CSI-Based Human Activity Recognition Using Deep Learning.

Parisa Fard Moshiri,Mohammad Nabati,Seyed Ali Ghorashi,Reza Shahbazian

doi:10.3390/s21217225

Abstract

The Internet of Things (IoT) has become quite popular due to advancements in Information and Communications technologies and has revolutionized the entire research area in Human Activity Recognition (HAR). For the HAR task, vision-based and sensor-based methods can present better data but at the cost of users’ inconvenience and social constraints such as privacy issues. Due to the ubiquity of WiFi devices, the use of WiFi in intelligent daily activity monitoring for elderly persons has gained popularity in modern healthcare applications. Channel State Information (CSI) as one of the characteristics of WiFi signals, can be utilized to recognize different human activities. We have employed a Raspberry Pi 4 to collect CSI data for seven different human daily activities, and converted CSI data to images and then used these images as inputs of a 2D Convolutional Neural Network (CNN) classifier. Our experiments have shown that the proposed CSI-based HAR outperforms other competitor methods including 1D-CNN, Long Short-Term Memory (LSTM), and Bi-directional LSTM, and achieves an accuracy of around 95% for seven activities.

Highlights

The Internet of Things (IoT) is a dynamic global information network consisting of internet-connected devices [1]
Due to the ubiquity of WiFi devices, Human Activity Recognition (HAR) based on wireless signals, including Channel State Information (CSI), has witnessed more interest in smart house health monitoring systems
A few CSI datasets for the HAR task collected with 5300 NIC or Atheros PCI chips, are currently available

Summary

Introduction

The Internet of Things (IoT) is a dynamic global information network consisting of internet-connected devices [1]. Due to the recent advancements in communication systems and wireless technology over the last decade, IoT has become a vibrant research field [2]. The concept is straightforward; things or objects are connected to the internet and exchange data or information with each other over the network. Applications of IoT improve the quality of life [3]. As one of the main IoT applications, smart houses allow homeowners to monitor everything, including the health, especially for those with disabilities and elderly people, by exerting Human Activity Recognition (HAR) techniques [4]. The joint task of HAR and indoor localization can be exerted in smart house automation [4]

Methods

Results

Conclusion