Electronics · 2020 · 37 citations · 36 references
ComputingComputer ScienceComputer VisionMachine LearningMovement AnalysisDimension ReductionDimensionality ReductionPattern RecognitionPrincipal Component AnalysisRadar Signal ProcessingSignal ProcessingFeature Dimensionality ReductionHuman Movement ClassificationMovement RecognitionRadar SensingRange-doppler ProcessingT-distributed Stochastic Neighbor Embedding
Automotive radars are able to guarantee high performances at the expenses of a relatively low cost, and recently their application has been extended to several fields in addition to the original one. In this paper we consider the use of this kind of radars to discriminate different types of people’s movements in a real context. To this end, we exploit two different maps obtained from radar, that is, a spectrogram and a range-Doppler map. Through the application of dimensionality reduction methods, such as principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) algorithm, and the use of machine learning techniques we prove that is possible to classify with a very good precision people’s way of walking even employing commercial devices specifically designed for other purposes.
36
Laurens van der Maaten, Geoffrey E. Hinton · Journal of Machine Learning Research · 2008 · 35.7K citations
Svante Wold, Kim H. Esbensen, Paul Geladi · Chemometrics and Intelligent Laboratory Systems · 1987 · 11.5K citations
MIMO Radar with Colocated Antennas
Jian Li, Petre Stoica · IEEE Signal Processing Magazine · 2007 · 2.5K citations
Gait analysis for recognition and classification
L. Lee, W. Eric L. Grimson · 2003 · 738 citations
Remote Monitoring of Human Vital Signs Using mm-Wave FMCW Radar
Mostafa Alizadeh, George Shaker, João Carlos Almeida et al. · IEEE Access · 2019 · 518 citations · Full text
Engineering, Biomedical Engineering, Electrical Engineering +17