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

Face recognition is a crucial biometric technology used in various security and identification applications. Ensuring accuracy and reliability in facial recognition systems requires robust feature extraction and secure processing methods. This study presents an accurate facial recognition model using a feature extraction approach within a cloud environment. First, the facial images undergo preprocessing, including grayscale conversion, histogram equalization, Viola-Jones face detection, and resizing. Then, features are extracted using a hybrid approach that combines Linear Discriminant Analysis (LDA) and Gray-Level Co-occurrence Matrix (GLCM). The extracted features are encrypted using the Data Encryption Standard (DES) for security

An accurate assessment of the pipes’ conditions is required for effective management of the trunk sewers. In this paper the semi-Markov model was developed and tested using the sewer dataset from the Zublin trunk sewer in Baghdad, Iraq, in order to evaluate the future performance of the sewer. For the development of this model the cumulative waiting time distribution of sewers was used in each condition that was derived directly from the sewer condition class and age data. Results showed that the semi-Markov model was inconsistent with the data by adopting ( 2 test) and also, showed that the error in prediction is due to lack of data on the sewer waiting times at each condition state which can be solved by using successive conditi

Imaging by Ultrasound (US) is an accurate and useful modality for the assessment of gestational age (GA), estimation fetal weight, and monitoring the fetal growth during pregnancy, is a routine part of prenatal care, and that can greatly impact obstetric management. Estimation of GA is important in obstetric care, making appropriate management decisions requires accurate appraisal of GA. Accurate GA estimation may assist obstetricians in appropriately counseling women who are at risk of a preterm delivery about likely neonatal outcomes, and it is essential in the evaluation of the fetal growth and detection of intrauterine growth restriction. There are many formulas are used to estimate fetal GA in the world, but it's not specify fo

Aspect categorisation and its utmost importance in the eld of Aspectbased Sentiment Analysis (ABSA) has encouraged researchers to improve topic model performance for modelling the aspects into categories. In general, a majority of its current methods implement parametric models requiring a pre-determined number of topics beforehand. However, this is not e ciently undertaken with unannotated text data as they lack any class label. Therefore, the current work presented a novel non-parametric model drawing a number of topics based on the semantic association present between opinion-targets (i.e., aspects) and their respective expressed sentiments. The model incorporated the Semantic Association Rules (SAR) into the Hierarchical Dirichlet Proce

One of the recent significant but challenging research studies in computational biology and bioinformatics is to unveil protein complexes from protein-protein interaction networks (PPINs). However, the development of a reliable algorithm to detect more complexes with high quality is still ongoing in many studies. The main contribution of this paper is to improve the effectiveness of the well-known modularity density ( ) model when used as a single objective optimization function in the framework of the canonical evolutionary algorithm (EA). To this end, the design of the EA is modified with a gene ontology-based mutation operator, where the aim is to make a positive collaboration between the modularity density model and the proposed