Signal Processing

The dataset has 150 three-second sampling motor current signals from each synthetically-prepared motors. There are five motors with respective fault condition - bearing axis deviation (F1), stator coil inter-turn short circuit (F2), rotor broken strip (F3), outer bearing ring damage (F4), and healthy (H). The motors are run under five coupling loads - 0, 25, 50, 75, and 100%. The sampling signals are collected and processed into frequency occurrence plots (FOPs). Each image has a label, for example F2_L50_130, where F2 is the fault condition, L50 is the coupling load condition.

The files contain the research data. The noisy unprocessed audio data and processed audio data using the proposed speech enhancement method are uploaded. 

The SWINSEG dataset contains 115 nighttime images of sky/cloud patches along with their corresponding binary ground truth maps The ground truth annotation was done in consultation with experts from Singapore Meteorological Services. All images were captured in Singapore using WAHRSIS, a calibrated ground-based whole sky imager, over a period of 12 months from January to December 2016. All image patches are 500x500 pixels in size, and were selected considering several factors such as time of the image capture, cloud coverage, and seasonal variations.

Our goal is to find whether a convolutional neural network (CNN) performs better than the existing blind algorithms for image denoising, and, if yes, whether the noise statistics has an effect on the performance gap. We performed automatic identification of noise distribution, over a set of nine possible distributions, namely, Gaussian, log-normal, uniform, exponential, Poisson, salt and pepper, Rayleigh, speckle and Erlang. Next, for each of these noisy image sets, we compared the performance of FFDNet, a CNN based denoising method, with noise clinic, a blind denoising algorithm.