Radar Data Cube Processing for Human Activity Recognition Using Multisubspace Learning

In recent years, radar has been employed as a fall detector because of its effective sensing capabilities and penetration through walls. In this paper, we introduce a multilinear subspace human activity recognition scheme that exploits the three radar signal variables: slow-time, fast-time, and Doppler frequency. The proposed approach attempts to find the optimum subspaces that minimize the reconstruction error for different modes of the radar data cube. A comprehensive analysis of the optimization considerations is performed, such as initialization, number of projections, and convergence of the algorithms. Finally, a boosting scheme is proposed combining the unsupervised multilinear principal component analysis (PCA) with the supervised methods of linear discriminant analysis and shallow neural networks. Experimental results based on real radar data obtained from multiple subjects, different locations, and aspect angles (0<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>, 30<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>, 45<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>, 60<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>, and 90<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>) demonstrate that the proposed algorithm yields the highest overall classification accuracy among spectrogram-based methods including predefined physical features, one- and two-dimensional PCA and convolutional neural networks.