Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.) Filing date Publication date Priority to US14859799P priority Critical Priority to US60/148,597 priority Application filed by Automotive Systems Lab filed Critical Automotive Systems Lab Publication of WO2001013141A2 publication Critical patent/WO2001013141A2/en Publication of WO2001013141A3 publication Critical patent/WO2001013141A3/en Links ( en Inventor Michael E Farmer Craig S Jacobs Shan Cong Original Assignee Automotive Systems Lab Priority date (The priority date is an assumption and is not a legal conclusion. Google Patents WO2001013141A3 - Neural network radar processor Experimental results on measured data show that 1) the accuracy of classification using CVNNs on range-Doppler and range-spectrum-time radar formats is significantly higher than the real-valued counterpart, and that 2)Deep neural networks achieve the best classification accuracy on CVNNs while shallow neural networks do not.WO2001013141A3 - Neural network radar processor
A series of experiments determine the optimal approach and data format that achieves the highest classification accuracy. The range-time, range-Doppler, range-spectrum-time, and time-frequency spectrograms of micro-Doppler signatures are adopted as the input to CVNNs with different plural-handled approaches. This thesis proposes three complex-valued convolutional neural networks (CNNs) for human-motion classification based on monostatic radar. The complex-valued neural networks (CVNNs) have been only minimally explored, especially on complex-valued radar signals, and there is an outstanding question on whether CVNNs can contribute to improving classification performance. Nowadays, radar has been applied to human activity classification in the aging-in-place for health monitoring. Yang, Ximei (TU Delft Electrical Engineering, Mathematics and Computer Science TU Delft Microwave Sensing, Signals & Systems) Complex-Valued Neural Networks for Radar-based Human-Motion Classification