No abstract

The operation of microwave Doppler radar for sensing physiological motion signals is heavily compromised under sensor motion. To that end, we investigate the feasibility of applying empirical mode decomposition method in this context, and demonstrate its effectiveness in removing sensor motion artifacts. This method is shown to be effective in canceling unwanted sensor motion with precision sufficient to enable accurate heart rate extraction. Theoretical analysis and simulation results illustrate the potential of the proposed approach for a wide range of frequency separation and amplitude ratios of physiological signals and motion artifacts. Experimental results confirm that separation success is not very sensitive to amplitude ratio. A heart rate is extracted with RMSE within 1 beat per minute even in the presence of mechanical motion and order of magnitude larger in amplitude than that of the heart signal.

No abstract

We propose a hand gesture recognition technique using a convolutional neural network applied to radar echo inphase/quadrature (I/Q) plot trajectories. The proposed technique is demonstrated to accurately recognize six types of hand gestures for ten participants. The system consists of a low-cost 2.4-GHz continuous-wave monostatic radar with a single antenna. The radar echo trajectories are converted to low-resolution images and are used for the training and evaluation of the proposed technique. Results indicate that the proposed technique can recognize hand gestures with average accuracy exceeding 90%.

No abstract

No abstract

No abstract

No abstract