Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random Forests

• Published in: IEEE sensors journal Vol. 18; no. 23; pp. 9669 - 9681
• Main Authors: Yier Lin, Le Kernec, Julien, Shufan Yang, Fioranelli, Francesco, Romain, Olivier, Zhiqin Zhao
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classifiers; Computer simulation; convolution neural networks; Convolutional neural networks; deep learning; Feature extraction; Forestry; Human motion; Image classification; Machine learning; Micro-Doppler; Motion capture; Neural networks; Noise; Noise levels; radar; Radar imaging; Radar signatures; random forests; Random noise; Sensors; Walking
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2018.2872849

The accurate classification of activity patterns based on radar signatures is still an open problem and is a key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural network strategy with an autocorrelation pre-processing inste...