Human Activity Recognition from Wi-Fi CSI Data Using Principal Component-Based Wavelet CNN

Human Activity Recognition (HAR) is an emerging technology with several applications in surveillance, security, and healthcare sectors. Noninvasive HAR systems based on Wi-Fi Channel State Information (CSI) signals can be developed leveraging the quick growth of ubiquitous Wi-Fi technologies, and the correlation between CSI dynamics and body motions. In this paper, we propose Principal Component-based Wavelet Convolutional Neural Network (or PCWCNN) -- a novel approach that offers robustness and efficiency for practical real-time applications. Our proposed method incorporates two efficient preprocessing algorithms -- the Principal Component Analysis (PCA) and the Discrete Wavelet Transform (DWT). We employ an adaptive activity segmentation algorithm that is accurate and computationally light. Additionally, we used the Wavelet CNN for classification, which is a deep convolutional network analogous to the well-studied ResNet and DenseNet networks. We empirically show that our proposed PCWCNN model performs very well on a real dataset, outperforming existing approaches.

A Multi-View Discriminant Learning Approach for Indoor Localization Using Bimodal Features of CSI

With the growth of location-based services, indoor localization is attracting great interests as it facilitates further ubiquitous environments. Specifically, device free localization using wireless signals is getting increased attention as human location is estimated using its impact on the surrounding wireless signals without any active device tagged with subject. In this paper, we propose MuDLoc, the first multi-view discriminant learning approach for device free indoor localization using both amplitude and phase features of Channel State Information (CSI) from multiple APs. Multi-view learning is an emerging technique in machine learning which improve performance by utilizing diversity from different view data. In MuDLoc, the localization is modeled as a pattern matching problem, where the target location is predicted based on similarity measure of CSI features of an unknown location with those of the training locations. MuDLoc implements Generalized Inter-view and Intra-view Discriminant Correlation Analysis (GI$^{2}$DCA), a discriminative feature extraction approach using multi-view CSIs. It incorporates inter-view and intra-view class associations while maximizing pairwise correlations across multi-view data sets. A similarity measure is performed to find the best match to localize a subject. Experimental results from two cluttered environments show that MuDLoc can estimate location with high accuracy which outperforms other benchmark approaches.