Simulation and the monte carlo method

Time-Frequency Analysis.

Time-frequency features for pattern recognition using high-resolution TFDs

Deep Convolutional Neural Networks for mental load classification based on EEG data

Low-cost consumer radar integrated circuits combined with recent advances in machine learning have opened up a range of new possibilities in smart sensing. In this paper, we use a miniature radar sensor to capture Doppler signatures of 14 different hand gestures and train a deep convolutional neural network (DCNN) to classify these captured gestures. We utilize two receiving antennas of a continuous-wave Doppler radar capable of producing the in-phase and quadrature components of the beat signals. We map these two beat signals into three input channels of a DCNN as two spectrograms and an angle of arrival matrix. The classification results of the proposed architecture show a gesture classification accuracy exceeding 95% and a very low confusion between different gestures. This is almost 10% improvement over the single-channel Doppler methods reported in the literature.

Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural Networks

https://espace.library.uq.edu.au/view/UQ:352666/UQ352666_OA.pdf

Principles of time-frequency feature extraction for change detection in non-stationary signals

This letter presents a novel algorithm to compute the instantaneous frequency (IF) of a multicomponent nonstationary signal using a combination of fractional spectrograms (FS). A high resolution time frequency distribution (TFD) is defined by combining FS computed using windows of varying lengths and chirp rates. The IF of individual signal components is then computed by applying a peak detection and component extraction procedure. The mean square error (MSE) of IF estimates computed with the AFS is lower than the MSE of IF estimates obtained from other TFDs for SNR varying from -5 dB to 16 dB.

Instantaneous Frequency Estimation of Multicomponent Nonstationary Signals Using Multiview Time-Frequency Distributions Based on the Adaptive Fractional Spectrogram

This paper presents a locally adaptive time-frequency t,f method for estimating the instantaneous frequency IF of multi-component signals. A high-resolution adaptive directional time-frequency distribution ADTFD is defined by locally adapting the direction of its smoothing kernel at each t,f point based on the direction of the energy distribution in the t,f domain. The IF of signal components is then estimated from the ADTFD using an image processing algorithm. Using the mean square error between the original IF and estimated IF as a performance criterion, experimental results indicate that the ADTFD gives better IF estimation performance compared with other TFDs for a multi-component signal. For example, for signal-to-noise ratio of 12dB, the IF estimate obtained using the ADTFD achieves a mean square error of -42dB for a weak signal component, which is an improvement of -12dB compared with other TFDs. Copyright © 2015John Wiley & Sons, Ltd.

Nabeel Ali Khan

Papers

Time-frequency features for pattern recognition using high-resolution TFDs

Principles of time-frequency feature extraction for change detection in non-stationary signals

Instantaneous Frequency Estimation of Multicomponent Nonstationary Signals Using Multiview Time-Frequency Distributions Based on the Adaptive Fractional Spectrogram

Multi-component instantaneous frequency estimation using locally adaptive directional time frequency distributions

Cross-term elimination in Wigner distribution based on 2D signal processing techniques