A manifold learning approach for gesture recognition from micro-Doppler radar measurements. (August 2022)

• Record Type: Journal Article
• Authors: Mason, E.S.; Mhaskar, H.N.; Guo, Adam
• Is Part Of: Neural networks. Volume 152(2022)
• Page Start: 353
• Page End: 369
• Publication Date: 2022-08
• Subjects: Machine learning -- Kernel methods -- Micro-Doppler radar gesture recognition; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2022.04.024
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: A recent paper (Mhaskar (2020)) introduces a straightforward and simple kernel based approximation for manifold learning that does not require the knowledge of anything about the manifold, except for its dimension. In this paper, we examine how the pointwise error in approximation using least squares optimization based on similarly localized kernels depends upon the data characteristics and deteriorates as one goes away from the training data. The theory is presented with an abstract localized kernel, which can utilize any prior knowledge about the data being located on an unknown sub-manifold of a known manifold. We demonstrate the performance of our approach using a publicly available micro-Doppler data set, and investigate the use of different preprocessing measures, kernels, and manifold dimensions. Specifically, it is shown that the localized kernel introduced in the above mentioned paper when used with PCA components leads to a near-competitive performance to deep neural networks, and offers significant improvements in training speed and memory requirements. To demonstrate the fact that our methods are agnostic to the domain knowledge, we examine the classification problem in a simple video data set. Highlights: We examine the pointwise error in approximation using least squares optimization based on the kernel presented in Mhaskar (2020). The approximation error depends upon the data characteristics and deteriorates as one goes away from the training data. The theory is presented with an abstract localized kernel, which can utilize any prior knowledge about the data being located on an unknown sub-manifold of a known manifold. We demonstrate the performance of this kernel using a publicly available micro-Doppler data set, investigating the use of different preprocessing measures, kernels, and manifold dimension. It is shown that the proposed method offers nearcompetitive performance to deep neural networks and significant improvements to speed and accuracy.