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

Water pollution as a result of contamination with dye-contaminating effluents is a severe issue for water reservoirs, which instigated the study of biodegradation of Reactive Red 195 and Reactive Blue dyes by E. coli and Bacillus sp. The effects of occupation time, solution pH, initial dyes concentrations, biomass loading, and temperature were investigated via batch-system experiments by using the Design of Experiment (DOE) for 2 levels and 5 factors response surface methodology (RSM). The operational conditions used for these factors were optimized using quadratic techniques by reducing the number of experiments. The results revealed that the two types of bacteria had a powerful effect on biodegradable dyes. The regression analysis reveale

Broyden update is one of the one-rank updates which solves the unconstrained optimization problem but this update does not guarantee the positive definite and the symmetric property of Hessian matrix.

In this paper the guarantee of positive definite and symmetric property for the Hessian matrix will be established by updating the vector  which represents the difference between the next gradient and the current gradient of the objective function assumed to be twice continuous and differentiable .Numerical results are reported to compare the proposed method with the Broyden method under standard problems.

  The aim of the research is to identify the extent of the ability to ensure the integrated reports by the auditor in verifying the credibility of these reports, and their implications for the benefit of all parties dealing with the economic unit, as well as measuring the impact of the assurance procedures followed by the auditors and their role in confirming these reports.

  The research methodology was designed after studying the previous literature related to the research variables, and then the relationship between these variables was tested, through the use of a questionnaire list. A questionnaire targeting the community of auditors in the local environment, and the results of the study wer

This paper presents a hybrid genetic algorithm (hGA) for optimizing the maximum likelihood function ln(L(phi(1),theta(1)))of the mixed model ARMA(1,1). The presented hybrid genetic algorithm (hGA) couples two processes: the canonical genetic algorithm (cGA) composed of three main steps: selection, local recombination and mutation, with the local search algorithm represent by steepest descent algorithm (sDA) which is defined by three basic parameters: frequency, probability, and number of local search iterations. The experimental design is based on simulating the cGA, hGA, and sDA algorithms with different values of model parameters, and sample size(n). The study contains comparison among these algorithms depending on MSE value. One can conc

Wireless sensor networks (WSNs) represent one of the key technologies in internet of things (IoTs) networks. Since WSNs have finite energy sources, there is ongoing research work to develop new strategies for minimizing power consumption or enhancing traditional techniques. In this paper, a novel Gaussian mixture models (GMMs) algorithm is proposed for mobile wireless sensor networks (MWSNs) for energy saving. Performance evaluation of the clustering process with the GMM algorithm shows a remarkable energy saving in the network of up to 92%. In addition, a comparison with another clustering strategy that uses the K-means algorithm has been made, and the developed method has outperformed K-means with superior performance, saving ener

With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se