CSI Human Activity

Using Wi-Fi IEEE 802.11 standard, radio frequency waves are mainly used for communication on various devices such as mobile phones, laptops, and smart televisions. Apart from communication applications, the recent research in wireless technology has turned Wi-Fi into other exploration possibilities such as human activity recognition (HAR). HAR is a field of study that aims to predict motion and movement made by a person. There are numerous possibilities to use the Wi-Fi-based HAR solution for human-centric applications in intelligent surveillance, such as in the health care sector for human fall detection, smart homes for temperature control, a light control application, motion detection applications, and human fall detection for older people nursing homes. This paper's focal point is to classify human activities such as WALK, SIT, SIT-DOWN, STAND,STAND-UP, FALL, LYING, and EMPTY with deep neural network long-term short memory (LSTM) and support vector machine (SVM). Special care was taken to address practical issues such as using available commodity hardware. Therefore, the open-source tool Nexmon was used for the channel state information (CSI) extraction on inexpensive hardware (Raspberry Pi 3B+, Pi 4B, and Asus RT-AC86U routers). We conducted three different types of experiments using different algorithms, which all demonstrated a similar accuracy in prediction for HAR with an accuracy between 97% to 99.7% which is superior to previously published results. We also disclose details about the experimental setup.

Wi-Fi遵循IEEE 802.11标准，主要依托射频电波实现手机、笔记本电脑、智能电视等各类设备间的通信。除常规通信应用外，无线技术领域的近期研究还将Wi-Fi拓展至人体活动识别（Human Activity Recognition, HAR）等新兴探索方向。HAR是一门旨在识别人体动作与运动状态的研究学科。基于Wi-Fi的HAR解决方案可广泛应用于以人为中心的智能监控场景，例如医疗保健领域的人体跌倒检测、智能家居中的温控、灯光控制、运动检测，以及养老机构的老年人跌倒监测等。本文的核心研究目标是利用深度神经网络长短期记忆网络（Long Short-Term Memory, LSTM）与支持向量机（Support Vector Machine, SVM），对WALK、SIT、SIT-DOWN、STAND、STAND-UP、FALL、LYING及EMPTY等人体活动类别进行分类。研究充分考量了商用现有硬件的实际落地问题，因此采用开源工具Nexmon，在低成本硬件（树莓派3B+、树莓派4B及华硕RT-AC86U路由器）上完成信道状态信息（Channel State Information, CSI）的提取工作。我们开展了三种不同算法的对比实验，所有算法的HAR预测准确率均处于97%至99.7%区间，优于此前已发表的同类研究成果。此外，本文还公开了本次实验设置的全部细节。

搜集汇总

背景与挑战

背景概述

CSI Human Activity是一个基于Wi-Fi IEEE 802.11标准的人体活动识别（HAR）数据集，主要用于通过信道状态信息（CSI）和深度学习模型（如LSTM和SVM）分类多种人体活动（如行走、坐下、跌倒等）。数据集包含三个实验的数据和脚本，使用低成本硬件（如Raspberry Pi和Asus路由器）采集，分类准确率高达97%-100%。