Yongsen Ma, S. Arshad, Swetha Muniraju, E. Torkildson, Enrico Rantala, K. Doppler, Gang Zhou
{"title":"WiFi,深度神经网络和强化学习的位置和人独立活动识别","authors":"Yongsen Ma, S. Arshad, Swetha Muniraju, E. Torkildson, Enrico Rantala, K. Doppler, Gang Zhou","doi":"10.1145/3424739","DOIUrl":null,"url":null,"abstract":"In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":"{\"title\":\"Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning\",\"authors\":\"Yongsen Ma, S. Arshad, Swetha Muniraju, E. Torkildson, Enrico Rantala, K. Doppler, Gang Zhou\",\"doi\":\"10.1145/3424739\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.\",\"PeriodicalId\":29764,\"journal\":{\"name\":\"ACM Transactions on Internet of Things\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2021-01-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"29\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Transactions on Internet of Things\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3424739\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Internet of Things","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3424739","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 29
摘要
近年来,WiFi测量的信道状态信息(Channel State Information, CSI)被广泛用于人体活动识别。在本文中,我们提出了一种基于WiFi的独立于位置和个人的活动识别的深度学习设计。提出的设计由三个深度神经网络(dnn)组成:二维卷积神经网络(CNN)作为识别算法,一维卷积神经网络作为状态机,以及用于神经结构搜索的强化学习代理。该识别算法从CSI数据的不同角度学习与位置和人无关的特征。状态机从历史分类结果中学习时间依赖信息。强化学习智能体使用具有长短期记忆(LSTM)的递归神经网络(RNN)优化识别算法的神经结构。在不同的WiFi设备位置、天线方向、坐/站/行走位置/方向和多人的实验室环境中对所提出的设计进行了评估。当训练期间没有看到测试设备和人员时,所提出的设计的平均准确率为97%。该设计还通过两个公共数据集进行了评估,准确率分别为80%和83%。所提出的设计需要很少的人力来进行地面真值标记、特征工程、信号处理以及学习参数和超参数的调整。
Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning
In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.