College of Engineering

A PH.D dissertation was discussed in Department of Computer Engineering / College of Engineering at University of Mosul entitled “Signal Restoration Based On Hybrid Intelligent Inferences” submitted by (Omar Hatif Mohammed) on Tuseday, April 05, 2022.The dissertation aims to present a new algorithm to restore the images and sound signals suffering from different types of distortion, including blurring, noise, and other degradation processes. The degradation process is identified using the convolutional neural network VGG16 with an accuracy of 94.44%, while the conditional-GAN network is used for restoration due to the type of the identified distortion; more than one type of distortion can be identified and processed for restoration.The algorithm also successfully restored audio signals by improving the segmental signal-to-noise ratio (SNR) by an average of 4.231 dB. The procedure is done by converting the 1D audio signal to 2D image-like by using the short-time Fourier transform (STFT) supported with an encoding approach, then restoring the signal as an image that is converted to audio signal format reconstructed from STFT magnitudes.