Abstract Background Deep learning (DL) has attracted increasing attention in orthodontics, with many studies reporting high diagnostic and predictive accuracy. However, despite these promising results, routine clinical adoption remains limited. Objectives This scoping review aimed to explore the main barriers that restrict the translation of DL systems from research environments into everyday orthodontic practice. Methodology The review was conducted in accordance with PRISMA-ScR guidelines. Electronic searches were performed in PubMed, Scopus, Web of Science, and IEEE Xplore for English-language studies published between 2015 and June 2025. Studies reporting quantitative performance of DL-based orthodontic applications were included. Dat

The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.

Natural settings make it challenging to identify facial expressions since head position, illumination level, and ‎‎occlusion vary. Thus, developing a more generic model without front-facing images alone is quite crucial. This ‎research proposes a facial expression ‎recognition model based on pre-trained deep convolutional neural networks ‎with transfer learning. The model was trained ‎on several cases to classify face expressions into seven ‎classifications efficiently. The proposed system used the EfficientNetB0 model ‎that has one dense dropout layer. The model first rescales and norms the input dataset in the input ‎layer that takes images of a larger resolution to get better results. After entering 7 blocks sequential

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

E-learning seeks to create an interactive learning environment between the teacher and the learner through electronic media conveying in more than one direction, regardless of how the environment and its variables are identified. It also develops skills necessary to deal with technology in order to be able to take into account the individual differences between them and helps e-learning teacher and learner to achieve the goals set in advance and identify educational objectives in a clear manner. The research aims to identify e-learning in its benefits and management systems. It has three sections dealt with in the current research. Chapter II concentrates on the research Methodology, which consisted of three sections: The first s

The complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra

Genome sequencing has significantly improved the understanding of HIV and AIDS through accurate data on viral transmission, evolution and anti-therapeutic processes. Deep learning algorithms, like the Fined-Tuned Gradient Descent Fused Multi-Kernal Convolutional Neural Network (FGD-MCNN), can predict strain behaviour and evaluate complex patterns. Using genotypic-phenotypic data obtained from the Stanford University HIV Drug Resistance Database, the FGD-MCNN created three files covering various antiretroviral medications for HIV predictions and drug resistance. These files include PIs, NRTIs and NNRTIs. FGD-MCNNs classify genetic sequences as vulnerable or resistant to antiretroviral drugs by analyzing chromosomal information and id

Machine learning is considered a powerful technique in many applications such as classification, clustering, recognition and prediction. Deep learning is a modern, vital and superior machine learning that gives stunning performance, especially with huge data. Stock market price prediction is the process of determining the future value of a prospect of a financial instrument traded in the market, to gain a great profit a successful prediction must be conducted, in order to achieve that machine learning is used, in this article, two approaches are proposed to predict the stock market prices and movement using two datasets, the first approach employs two machine learning models (J48 & logistic regression) while the second approach based on rec