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

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

Diagnosing heart disease has become a very important topic for researchers specializing in artificial intelligence, because intelligence is involved in most diseases, especially after the Corona pandemic, which forced the world to turn to intelligence. Therefore, the basic idea in this research was to shed light on the diagnosis of heart diseases by relying on deep learning of a pre-trained model (Efficient b3) under the premise of using the electrical signals of the electrocardiogram and resample the signal in order to introduce it to the neural network with only trimming processing operations because it is an electrical signal whose parameters cannot be changed. The data set (China Physiological Signal Challenge -cspsc2018) was ad

A new human-based heuristic optimization method, named the Snooker-Based Optimization Algorithm (SBOA), is introduced in this study. The inspiration for this method is drawn from the traits of sales elites—those qualities every salesperson aspires to possess. Typically, salespersons strive to enhance their skills through autonomous learning or by seeking guidance from others. Furthermore, they engage in regular communication with customers to gain approval for their products or services. Building upon this concept, SBOA aims to find the optimal solution within a given search space, traversing all positions to obtain all possible values. To assesses the feasibility and effectiveness of SBOA in comparison to other algorithms, we conducte

Machine Learning (ML) algorithms are increasingly being utilized in the medical field to manage and diagnose diseases, leading to improved patient treatment and disease management. Several recent studies have found that Covid-19 patients have a higher incidence of blood clots, and understanding the pathological pathways that lead to blood clot formation (thrombogenesis) is critical. Current methods of reporting thrombogenesis-related fluid dynamic metrics for patient-specific anatomies are based on computational fluid dynamics (CFD) analysis, which can take weeks to months for a single patient. In this paper, we propose a ML-based method for rapid thrombogenesis prediction in the carotid artery of Covid-19 patients. Our proposed system aims

    In this article, the research presents a general overview of deep learning-based AVSS (audio-visual source separation) systems. AVSS has achieved exceptional results in a number of areas, including decreasing noise levels, boosting speech recognition, and improving audio quality. The advantages and disadvantages of each deep learning model are discussed throughout the research as it reviews various current experiments on AVSS. The TCD TIMIT dataset (which contains top-notch audio and video recordings created especially for speech recognition tasks) and the Voxceleb dataset (a sizable collection of brief audio-visual clips with human speech) are just a couple of the useful datasets summarized in the paper that can be used to test A

The hydrological process has a dynamic nature characterised by randomness and complex phenomena. The application of machine learning (ML) models in forecasting river flow has grown rapidly. This is owing to their capacity to simulate the complex phenomena associated with hydrological and environmental processes. Four different ML models were developed for river flow forecasting located in semiarid region, Iraq. The effectiveness of data division influence on the ML models process was investigated. Three data division modeling scenarios were inspected including 70%–30%, 80%–20, and 90%–10%. Several statistical indicators are computed to verify the performance of the models. The results revealed the potential of the hybridized s

Cryptography algorithms play a critical role in information technology against various attacks witnessed in the digital era. Many studies and algorithms are done to achieve security issues for information systems. The high complexity of computational operations characterizes the traditional cryptography algorithms. On the other hand, lightweight algorithms are the way to solve most of the security issues that encounter applying traditional cryptography in constrained devices. However, a symmetric cipher is widely applied for ensuring the security of data communication in constraint devices. In this study, we proposed a hybrid algorithm based on two cryptography algorithms PRESENT and Salsa20. Also, a 2D logistic map of a chaotic system is a