Segmenting images is one of the most essential problems in computer vision and finds use in many areas for example medical imaging, traffic analysis among others. The use of instance segmentation that brings together object detection and segmentation makes it more useful since it provides a holistic approach to recognizing and accurately outlining objects. In this paper, we concentrate on simple improved YOLOv8-Seg models for instance segmentation training with a focus on TrashCan dataset. The dataset being an instance-segmentation dataset specifically made for underwater environments addresses the problem of underwater garbage dumps. Two instance segmentation networks namely YOLOv8n-Seg and YOLOv8s-Seg are introduced and compared to detect underwater trash. The models were assessed based on their effectiveness in detecting and segmenting trash instances more so in difficult circumstances. These models can perform real-time instance segmentation of the TrashCan dataset with inference times of 2.3 ms and 2.4 ms with a precision of 75% and 70%, respectively. The results emphasize the contribution of improved YOLOv8-Seg towards environmental conservation across perfect identification of isolated marine undersea wastes through accurate instances’ discrimination.

Arabic Dialect Identification (ADI) is a challenging task in natural language processing applications due to its diversity and regional variations. Despite previous efforts, this task is still difficult. Therefore, this study aims to use transformers to address the issue of ADI on social media. A combination of two hybrid models is proposed in this study: one that combines Bidirectional Long Short-Term Memory (BiLSTM) with CAMeLBERT, and the second model that combines the BiLSTM model with AlBERT. In addition, a novel dataset comprising 121,289 user-generated comments from various social media network platforms and four major Arabic dialects (Egyptian, Jordanian, Gulf and Yemeni) was introduced. Several experiments have been conducted using conventional Machine Learning Classifiers (MLCs) and Deep Learning Models (DLMs) as baselines to measure the performance and effectiveness of the proposed models. In addition, binary classification is performed between two dialects to determine which are closest to each other. The performance of the model is measured using common metrics such as precision, recall, F-score and F-measure. Experiment results demonstrate the superior efficiency of the proposed hybrid models in ADI, CAMeLBERT with BiLSTM and ALBERT with BiLSTM, which both recorded an accuracy of 87.67 % and 86.51 %, respectively.

Nowadays, credit card transactions are exponentially increasing as a form of online payment. That creates technical pressure on the financial institution to incur losses due to credit card fraud. It is no wonder that credit card fraud is making people feel insecure and unsafe about using the services provided by banks. Data mining reasons on offline and online transactions can cause fraud detection. Number one is the changes in the behaviour of the frauds that are changing, and number two is the fraudulent dataset, which is asymmetric. In addition, the variables and techniques used by the researcher can impact fraud detection activities for credit cards. Therefore, the paper intends to investigate the suitability of the k-nearest-neighbour, decision tree, support vector machine, logistic regression, and Catboost. The data set has a total of 284807 transactions coming from the European credit card holder. Evaluation of the performance can be measured through the specificity, accuracy, sensitivity, precision, and lastly, the recall rate. After completing the comprehensive cross-validation, it was discovered that the catboost’s accuracy was extraordinary, which amounted to 93.39%, leaving the other classification matrix far behind.

Alzheimer's Disease (AD) is a chronic neurodegenerative disease that affects a large portion of the global population, and early and accurate diagnosis is the key component to proper management and treatment. This work presents the MAGNet model, a novel Deep Learning (DL) architecture for AD classification based on multi-modal imaging data. The MAGNet model uses multi-modal attention that is capable of hierarchically fusing structural MRI, functional MRI, and PET scans to obtain different kinds of information. The MAGNet model was tested on three datasets, with an overall accuracy of 96.2% when distinguishing between the AD, MCI, and CN groups. The proposed approach surpasses benchmark models by achieving 3.5% better accuracy and 5.2% higher sensitivity for early MCI diagnosis. Moreover, the MAGNet model offers interpretable results, employing attention visualization to support clinicians' decisions. MAGNet has the potential to predict cognitive scores and brain age with MMSE errors of 1.8 and a brain age of 2.3 years.

This paper presents a novel vision impairment assistive device to improve mobility and independence. This device consists of Arduino Nano microcontroller technology that powers the Satellite/GPS-based stick, which tracks and navigates in real-time. Arduino Nano’s adaptability and compactness enable our portable, affordable white cane replacement. Satellite signals let the stick locate the user, compute the best routes, and provide aural navigation cues through speakers or headphones. The obstacle detection sensors notify users of adjacent risks, improving safety. The proposed device is a stable and user-friendly technology that delivers a potential answer to visually impaired navigation issues after rigorous development and testing.

Cyberbullying is a remarkable issue in the Arabic-speaking world, affecting children, organizations, and businesses. Various efforts have been made to combat this problem through proposed models using machine learning (ML) and deep learning (DL) approaches utilizing natural language processing (NLP) methods and by proposing relevant datasets. However, most of these endeavors focused predominantly on the English language, leaving a substantial gap in addressing Arabic cyberbullying. Given the complexities of the Arabic language, transfer learning techniques and transformers present a promising approach to enhance the detection and classification of abusive content by leveraging large and pretrained models that use a large dataset. Therefore, this study proposes a hybrid model using transformers trained on extensive Arabic datasets. It then fine-tunes the hybrid model on a newly curated Arabic cyberbullying dataset collected from social media platforms, in particular Twitter. Additionally, the following two hybrid transformer models are introduced: the first combines CAmelid Morphologically-aware pre-trained Bidirectional Encoder Representations from Transformers (CAMeLBERT) with Arabic Generative Pre-trained Transformer 2 (AraGPT2) and the second combines Arabic BERT (AraBERT) with Cross-lingual Language Model - RoBERTa (XLM-R). Two strategies, namely, feature fusion and ensemble voting, are employed to improve the model performance accuracy. Experimental results, measured through precision, recall, F1-score, accuracy, and Area Under the Curve-Receiver Operating Characteristic (AUC-ROC), demonstrate that the combined CAMeLBERT and AraGPT2 models using feature fusion outperformed traditional DL models, such as Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM), as well as other independent Arabic-based transformer models.