Using GAN to Enhance the Accuracy of Indoor Human Activity Recognition

Indoor human activity recognition (HAR) explores the correlation between human body movements and the reflected WiFi signals to classify different activities. By analyzing WiFi signal patterns, especially the dynamics of channel state information (CSI), different activities can be distinguished. Gathering CSI data is expensive both from the timing and equipment perspective. In this paper, we use synthetic data to reduce the need for real measured CSI. We present a semi-supervised learning method for CSI-based activity recognition systems in which long short-term memory (LSTM) is employed to learn features and recognize seven different actions. We apply principal component analysis (PCA) on CSI amplitude data, while short-time Fourier transform (STFT) extracts the features in the frequency domain. At first, we train the LSTM network with entirely raw CSI data, which takes much more processing time. To this end, we aim to generate data by using 50% of raw data in conjunction with a generative adversarial network (GAN). Our experimental results confirm that this model can increase classification accuracy by 3.4% and reduce the Log loss by almost 16% in the considered scenario.

[1]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Yujie Wang,et al.  WiAct: A Passive WiFi-Based Human Activity Recognition System , 2020, IEEE Sensors Journal.

[3]  Mohammed Abdulaziz Aide Al-qaness,et al.  Device-free human micro-activity recognition method using WiFi signals , 2019, Geo spatial Inf. Sci..

[4]  Zhiguang Qin,et al.  CsiGAN: Robust Channel State Information-Based Activity Recognition With GANs , 2019, IEEE Internet of Things Journal.

[5]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[6]  Yinjing Guo,et al.  A Survey on CSI-Based Human Behavior Recognition in Through-the-Wall Scenario , 2019, IEEE Access.

[7]  Zhu Xiao,et al.  WiFiMap+: High-Level Indoor Semantic Inference With WiFi Human Activity and Environment , 2019, IEEE Transactions on Vehicular Technology.

[8]  Wei Cui,et al.  WiFi CSI Based Passive Human Activity Recognition Using Attention Based BLSTM , 2019, IEEE Transactions on Mobile Computing.

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[10]  Xiang Chen,et al.  DeepCount: Crowd Counting with WiFi via Deep Learning , 2019, ArXiv.

[11]  Mohammad Mehedi Hassan,et al.  A Hybrid Deep Learning Model for Human Activity Recognition Using Multimodal Body Sensing Data , 2019, IEEE Access.

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

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

[14]  Chen Wang,et al.  Wireless Sensing for Human Activity: A Survey , 2020, IEEE Communications Surveys & Tutorials.

[15]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[16]  Fei Wang,et al.  Joint Activity Recognition and Indoor Localization With WiFi Fingerprints , 2019, IEEE Access.