A CSI-Based Human Activity Recognition Using Deep Learning

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.

SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing

“… 41 2021 human activity recognition LSTM Nexmon CSI Tool supervised learning Moshiri et al. 58 2021 human activity recognition CNN Nexmon CSI Tool supervised learning Ding et al. 59 2021 human activity recognition CNN Intel 5300 NIC few-shot learning Widar 37 2021 human identification, gesture recognition CNN-GRU Intel 5300 NIC supervised learning WiONE 60 2021 human identification CNN Intel 5300 NIC few-shot learning Ma et al.…”

CNN-Based Smoker Classification and Detection in Smart City Application

“…The proposed method used long short-term memory (LSTM) for classification of the feature pattern extracted from motion data. Another method [35] was proposed for human activity recognition using channel state information (CSI). In the proposed method, CSI data are converted into images and these images are used for human activity classification using a 2D-CNN classifier.…”

A Fast Deep Learning Technique for Wi-Fi-Based Human Activity Recognition

“…The intuition behind a CSI use for HAR is that each user's movement introduces a unique multi-path distortion in Wi-Fi data, which consequently generates specific patterns in the CSI time series. Research on HAR has mainly focused on the use of this technology for several real-time applications, from healthcare to military-related solutions, as well as in the context of smart homes [10][11][12][13]. Wi-Fi-based HAR systems can be easily integrated into pre-existing Wi-Fi infrastructures and offer satisfactory performances at reasonable costs compared to other sensing technologies, such as radar and laser-based systems.…”