Optic disc (OD) detection is a main step while developing automated screening systems for diabetic retinopathy. We present in this paper a method to automatically detect the position of the OD in digital retinal fundus images. The method starts by normalizing luminosity and contrast through out the image using illumination equalization and adaptive histogram equalization methods respectively. The OD detection algorithm is based on matching the expected directional pattern of the retinal blood vessels. Hence, a simple matched filter is proposed to roughly match the direction of the vessels at the OD vicinity. The retinal vessels are segmented using a simple and standard 2-D Gaussian matched filter. Consequently, a vessels direction map of the segmented retinal vessels is obtained using the same segmentation algorithm. The segmented vessels are then thinned, and filtered using local intensity, to represent finally the OD-center candidates. The difference between the proposed matched filter resized into four different sizes, and the vessels' directions at the surrounding area of each of the OD-center candidates is measured. The minimum difference provides an estimate of the OD-center coordinates. The proposed method was evaluated using a subset of the STARE project's dataset, containing 81 fundus images of both normal and diseased retinas, and initially used by literature OD detection methods. The OD-center was detected correctly in 80 out of the 81 images (98.77%). In addition, the OD-center was detected correctly in all of the 40 images (100%) using the publicly available DRIVE dataset.

Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesses and improving overall health. However, a notable global challenge stems from the shortage of professional physiotherapists, particularly acute in some developing countries, where the ratio can be as low as one physiotherapist per 100,000 individuals. To address these challenges and elevate patient care, the field of physical rehabilitation is progressively integrating Computer Vision and Human Activity Recognition (HAR) techniques. Numerous research efforts aim to explore methodologies that assist in rehabilitation exercises and evaluate patient movements, which is crucial as incorrect exercises can potentially worsen conditions. This study investigates applying various deep-learning models for classifying exercises using the benchmark KIMORE and UI-PRMD datasets. Employing Bi-LSTM, LSTM, CNN, and CNN-LSTM, alongside a Random Search for architectural design and Hyper-parameter tuning, our investigation reveals the (CNN) model as the top performer. After applying cross-validation, the technique achieves remarkable mean testing accuracy rates of 93.08% on the KIMORE dataset and 99.7% on the UI-PRMD dataset. This marks a slight improvement of 0.75% and 0.1%, respectively, compared to previous techniques. In addition, expanding beyond exercise classification, this study explores the KIMORE dataset’s utility for disease identification, where the (CNN) model consistently demonstrates an outstanding accuracy of 89.87%, indicating its promising role in both exercises and disease identification within the context of physical rehabilitation.

Software vulnerabilities are among the significant causes of security breaches. Vulnerabilities can severely compromise software security if exploited by malicious attacks and may result in catastrophic losses. Hence, Automatic vulnerability detection methods promise to mitigate attack risks and safeguard software security. This paper introduces a novel model for automatic vulnerability detection of source code vulnerabilities dubbed DB-CBIL using a hybrid deep learning model based on Distilled Bidirectional Encoder Representations from Transformers (DistilBERT). The proposed model considers contextualized word embeddings using the language model for the syntax and semantics of source code functions based on the Abstract Syntax Tree (AST) representation. The model includes two main phases. First, using a vulnerable code dataset, the pre-trained DistilBert transformer is fine-tuned for word embedding. Second, a hybrid deep learning model detects which code functions are vulnerable. The hybrid model is built on two Deep Neural Networks (DNN). The first model is the Convolutional Neural Network (CNN), which is used for extracting features. The second model is Bidirectional-LSTM (BiLSTM), which has been used to maintain the sequential order of the data as it can handle lengthy token sequences. The utilized source code dataset is derived from the Software Assurance Reference Database (SARD) benchmark dataset. Final experimental findings show that the proposed model outperforms the state-of-the-art approaches’ performance by improving precision, recall, F1-score, and False Negative Rate (FNR) by 2.41%-8.95%, 4.0%-16.28%, 1.85%-12.74%, and 18% respectively. The proposed model reports the lowest FNR in the literature, a significant achievement given the cost-based nature of vulnerability detectors.

Artificial Intelligence is increasingly being employed in education, specifically through machine learning techniques, to improve the quality of education and refine teaching and learning methods. Despite its positive impacts on education quality and social life, machine learning technology poses ethical and practical concerns, especially in predicting student performance. To address these concerns, this study conducts a systematic literature review on machine learning technology for predicting student performance, analysing 51 relevant articles from Scopus and Science Direct databases between 2019 and 2023 using the PRISMA method. The findings reveal that the primary motivation for employing machine learning in educational institutions is to improve predictive accuracy, identify early interventions, and optimise decision-making processes. Supervised machine learning approaches such as Decision Trees, Linear Models, and Neural Networks are commonly used. However, machine learning techniques encounter challenges such as overfitting, scalability, and generalizability, which may impact education practices' fairness, accountability, and transparency. The study provides valuable insights into the benefits of machine learning, ethical considerations, and practical recommendations to guide stakeholders, including educators, researchers, policymakers, and administrators, in navigating the convergence of artificial intelligence and education. These insights emphasise the critical need for equitable model implementation, data collection, and decision-making to mitigate bias in real-world educational settings.