A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

Abstract—In this study, we present the experimental results of ultra-wideband (UWB) imaging oriented for detecting small malignant breast tumors at an early stage. The technique is based on radar sensing, whereby tissues are differentiated based on the dielectric contrast between the disease and its surrounding healthy tissues. The image reconstruction algorithm referred to herein as the enhanced version of delay and sum (EDAS) algorithm is used to identify the malignant tissue in a cluttered environment and noisy data. The methods and procedures are tested using MRI-derived breast phantoms, and the results are compared with images obtained from classical DAS variant. Incorporating a new filtering technique and multiplication procedure, t

The study aims to achieve several objectives, including follow-up scientific developments and transformations in the modern concepts of the Holistic Manufacturing System for the purpose of identifying the methods of switching to the entrances of artificial intelligence, and clarifying the mechanism of operation of the genetic algorithm under the Holonic Manufacturing System, to benefit from the advantages of systems and to achieve the maximum savings in time and cost of machines Using the Holistic Manufacturing System method and the Genetic algorithm, which allows for optimal maintenance time and minimizing the total cost, which in turn enables the workers of these machines to control the vacations in th

This paper proposes a better solution for EEG-based brain language signals classification, it is using machine learning and optimization algorithms. This project aims to replace the brain signal classification for language processing tasks by achieving the higher accuracy and speed process. Features extraction is performed using a modified Discrete Wavelet Transform (DWT) in this study which increases the capability of capturing signal characteristics appropriately by decomposing EEG signals into significant frequency components. A Gray Wolf Optimization (GWO) algorithm method is applied to improve the results and select the optimal features which achieves more accurate results by selecting impactful features with maximum relevance