ActRec: A Wi-Fi-Based Human Activity Recognition System

In this paper, we develop a Wi-Fi-based activity recognition system called ActRec, which can be used for the remote monitoring of elderly. ActRec comprises two parts: radio-frequency (RF) sensing and machine learning. In the RF sensing part, two laptops act as transmitter and receiver to record the channel transfer function of an indoor environment. This RF data is collected in the presence of seven human participants performing three activities: walking, falling, and sitting. The RF data containing the fingerprints of user activity is then pre-processed with various signal processing algorithms to reduce noise effects and to estimate the mean Doppler shift (MDS) of each data sample. We propose a feature extraction algorithm, which is applied to the MDS to obtain a feature vector used for activity classification. Moreover, we assess the activity recognition accuracy of three classification algorithms: K-nearest neighbors (KNN), naive Bayes, and decision tree. Our analysis reveals that the KNN, naive Bayes, and decision tree algorithms achieve an overall accuracy of 94%, 96.2%, and 98.9%, respectively.

[1]  G. Deco,et al.  An Information-Theoretic Approach to Neural Computing , 1997, Perspectives in Neural Computing.

[2]  David Wetherall,et al.  Tool release: gathering 802.11n traces with channel state information , 2011, CCRV.

[3]  Khaled A. Harras,et al.  WiGest: A ubiquitous WiFi-based gesture recognition system , 2014, 2015 IEEE Conference on Computer Communications (INFOCOM).

[4]  Frans C. A. Groen,et al.  Feature-based human motion parameter estimation with radar , 2008 .

[5]  Ronald Y. Chang,et al.  Device-Free Indoor Localization Using Wi-Fi Channel State Information for Internet of Things , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[6]  Yusheng Ji,et al.  Leveraging RF-channel fluctuation for activity recognition: Active and passive systems, continuous and RSSI-based signal features , 2013, MoMM '13.

[7]  Jiangchuan Liu,et al.  On Spatial Diversity in WiFi-Based Human Activity Recognition: A Deep Learning-Based Approach , 2019, IEEE Internet of Things Journal.

[8]  Dan Wu,et al.  FarSense , 2019, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[9]  Fadel Adib,et al.  Multi-Person Motion Tracking via RF Body Reflections , 2014 .

[10]  Jean Meunier,et al.  Comparative study of motion detection methods for video surveillance systems , 2017, J. Electronic Imaging.

[11]  Rob Miller,et al.  3D Tracking via Body Radio Reflections , 2014, NSDI.

[12]  Shahrokh Valaee,et al.  A Survey on Behavior Recognition Using WiFi Channel State Information , 2017, IEEE Communications Magazine.

[13]  Matthias Pätzold,et al.  A Machine Learning Approach for Fall Detection and Daily Living Activity Recognition , 2019, IEEE Access.

[14]  Tahmid Z. Chowdhury.  Using Wi-Fi channel state information (CSI) for human activity recognition and fall detection , 2018 .

[15]  Matthias Pätzold,et al.  A Framework for Activity Monitoring and Fall Detection Based on the Characteristics of Indoor Channels , 2018, 2018 IEEE 87th Vehicular Technology Conference (VTC Spring).

[16]  Boualem Boashash,et al.  Time-Frequency Signal Analysis and Processing: A Comprehensive Reference , 2015 .

[17]  Han Zou,et al.  Towards occupant activity driven smart buildings via WiFi-enabled IoT devices and deep learning , 2018, Energy and Buildings.

[18]  L. Jeannotte,et al.  The State of aging and health in America 2007 , 2007 .

[19]  Sung Hyun Kim,et al.  Human Activity Recognition and Prediction Based on Wi-Fi Channel State Information and Machine Learning , 2019, 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC).

[20]  Matthias Pätzold,et al.  Modelling of Non-WSSUS Channels with Time-Variant Doppler and Delay Characteristics , 2018, 2018 IEEE Seventh International Conference on Communications and Electronics (ICCE).

[21]  Inmaculada Plaza,et al.  Challenges, issues and trends in fall detection systems , 2013, Biomedical engineering online.

[22]  Yu Wang,et al.  Dynamic gesture recognition using wireless signals with less disturbance , 2018, Personal and Ubiquitous Computing.

[23]  Hao Jiang,et al.  DeepSense: Device-Free Human Activity Recognition via Autoencoder Long-Term Recurrent Convolutional Network , 2018, 2018 IEEE International Conference on Communications (ICC).

[24]  Matthias Pätzold,et al.  On the influence of walking people on the Doppler spectral characteristics of indoor channels , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[25]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[26]  Yusheng Ji,et al.  RF-Sensing of Activities from Non-Cooperative Subjects in Device-Free Recognition Systems Using Ambient and Local Signals , 2014, IEEE Transactions on Mobile Computing.