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

An intrusion detection system (IDS) is key to having a comprehensive cybersecurity solution against any attack, and artificial intelligence techniques have been combined with all the features of the IoT to improve security. In response to this, in this research, an IDS technique driven by a modified random forest algorithm has been formulated to improve the system for IoT. To this end, the target is made as one-hot encoding, bootstrapping with less redundancy, adding a hybrid features selection method into the random forest algorithm, and modifying the ranking stage in the random forest algorithm. Furthermore, three datasets have been used in this research, IoTID20, UNSW-NB15, and IoT-23. The results are compared with the three datasets men

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 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.

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

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

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

The proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters indifferent directions and then feed them to a binary CNN classifier instead of using the red-green-blue