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

The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) caused a pandemic of coronavirus disease 2019 (COVID-19) which represents a global public health crisis. Based on recent published studies, this review discusses current evidence related to the transmission, clinical characteristics, diagnosis, management and prevention of COVID-19. It is hoped that this review article will provide a benefit for the public to well understand and deal with this new virus, and give a reference for future researches.

Some genetic factors are not only involved in some autoimmune diseases but also interfere with their treatment, Such as Crohn's disease (CD), Rheumatoid Arthritis (RA), ankylosing spondylitis (AS), and psoriasis (PS). Tumor Necrosis Factor (TNF) is a most important pro-inflammatory cytokine, which has been recognized as a main factor that participates in the pathogenesis and development of autoimmune disorders. Therefore, TNF could be a prospective target for treating these disorders, and many anti-TNF were developed to treat these disorders. Although the high efficacy of many anti-TNF biologic medications, the Patients' clinical responses to the autoimmune treatment showed significant heterogeneity. Two types of TNF receptor (TNFR); 1 an

Until recently, researchers have utilized and applied various techniques for intrusion detection system (IDS), including DNA encoding and clustering that are widely used for this purpose. In addition to the other two major techniques for detection are anomaly and misuse detection, where anomaly detection is done based on user behavior, while misuse detection is done based on known attacks signatures. However, both techniques have some drawbacks, such as a high false alarm rate. Therefore, hybrid IDS takes advantage of combining the strength of both techniques to overcome their limitations. In this paper, a hybrid IDS is proposed based on the DNA encoding and clustering method. The proposed DNA encoding is done based on the UNSW-NB15

This paper proposes a hybrid artificial intelligence (AI) model that combines an Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) to predict the Quality of Service (QoS) in 5G networks. The model utilizes radio channel indicators such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), and Channel Quality Indicator (CQI) to forecast throughput and latency levels. These indicators are critical factors affecting network performance; however, the nonlinear relationship among them makes traditional analytical models inadequate for accurate QoS prediction. The importance of the current study lies in estimating QoS in 5G networks by combining

Objective: Evaluate the effects of different storage periods on flexural strength (FS) and degree of conversion (DC) of Bis-Acryl composite and Urethane dimethacrylate provisional restorative materials. Material and Methods: A total of 60 specimens were prepared from four temporary crown materials commercially available and assigned to four tested groups (n = 15 for each group): Prevision Temp, B&E CROWN, Primma Art, and Charm Temp groups. The specimens were stored in artificial saliva, and the FS was tested after 24 h, 7 d, and 14 d. A standard three-point bending test was conducted using a universal testing machine. Additionally, the DC was determined using a Fourier transform infrared spectroscopy (FTIR) device. The data were analyzed st

In this work, a new development of predictive voltage-tracking control algorithm for Proton Exchange Membrane Fuel Cell (PEMFCs) model, using a neural network technique based on-line auto-tuning intelligent algorithm was proposed. The aim of proposed robust feedback nonlinear neural predictive voltage controller is to find precisely and quickly the optimal hydrogen partial pressure action to control the stack terminal voltage of the (PEMFC) model for N-step ahead prediction. The Chaotic Particle Swarm Optimization (CPSO) implemented as a stable and robust on-line auto-tune algorithm to find the optimal weights for the proposed predictive neural network controller to improve system performance in terms of fast-tracking de

An automatic text summarization system mimics how humans summarize by picking the most ‎significant sentences in a source text. However, the complexities of the Arabic language have become ‎challenging to obtain information quickly and effectively. The main disadvantage of the ‎traditional approaches is that they are strictly constrained (especially for the Arabic language) by the ‎accuracy of sentence feature ‎functions, weighting schemes, ‎and similarity calculations. On the other hand, the meta-heuristic search approaches have a feature tha

Clostridioides difficile is an emerging pathogen of One Health significance. Its highly variable genome contains mobile genetic elements (MGEs) such as transposons and prophages that influence its biology. Systematic deletion of each genetic element is required to determine their precise role in C. difficile biology and contribution to the wider mobilome. Here, Tn5397 (21 kb) and ϕ027 (56 kb) were deleted from C. difficile 630 and R20291, respectively, using allele replacement facilitated by CRISPR-Cas9. The 630 Tn5397 deletant transferred PaLoc at the same frequency (1 × 10⁻⁷