Ensuring hygiene compliance in regulated environments—such as food processing facilities, hospitals, and public indoor spaces—requires reliable detection of personal protective equipment (PPE) usage, including gloves, face masks, and hairnets. Manual inspection is labor-intensive and unsuitable for continuous, real-time enforcement. This study benchmarks three lightweight object detection models—YOLOv8n, YOLOv10n, and YOLOv12n—for automated PPE compliance monitoring using a large curated dataset of over 31,000 annotated images. The dataset spans seven classes representing both compliant and non-compliant conditions: glove, no_glove, mask, no_mask, incorrect_mask, hairnet, and no_hairnet. All evaluations were conducted using both detection accuracy metrics (mAP@50, mAP@50–95, precision, recall) and deployment-relevant efficiency metrics (inference speed, model size, GFLOPs). Among the three models, YOLOv10n achieved the highest mAP@50 (85.7%) while maintaining competitive efficiency, indicating strong suitability for resource-constrained IoT-integrated deployments. YOLOv8n provided the highest localization accuracy at stricter thresholds (mAP@50–95), while YOLOv12n favored ultra-lightweight operation at the cost of reduced accuracy. The results provide practical guidance for selecting nano-scale detection models in real-time hygiene compliance systems and contribute a reproducible, deployment-aware evaluation framework for computer vision in hygiene-critical settings.

Reliance on social networks has become an integral part of modern daily activities. Social networks are crowded with vast numbers of comments, opinions, and beliefs about different aspects of people’s daily lives. Opinions can directly express positive or negative perspectives toward a specific entity or its aspects, or they can be comparative opinions that present the differences or similarities between two or more entities, such as “product A is better than product B.’’ Comparative opinions have significant potential to offer new opportunities across various fields such as marketing, education, and e-commerce. Thus, analyzing comparative opinions is essential. Indeed, comparative opinion mining has been applied in several languages, including Arabic. Nevertheless, comparative opinion mining in Arabic is still in its early stages and requires more contributions and investigations. Therefore, this work introduces the ACOM approach for Arabic Comparative Opinion Mining. First, we collected the ACOM corpus in Arabic from the X platform, focusing on comparative opinions in the technology domain. This paper provides a benchmark comparison of several deep-learning models by employing different approaches, including Long Short-Term Memory (LSTM), Bidirectional LSTMs (BiLSTM), and Convolutional Neural Networks (CNN). In the deep learning model, the generated representation vector was used to construct the embedding layer as the first layer. To this end, we adopted two pretrained word embedding techniques to investigate their effectiveness on the ACOM corpus: Word2vec and Bidirectional Encoder Representations from Transformers (BERT). The main highlight of this paper is leveraging the most advanced innovation in AI, the GPT-3 model, as a classifier model. Our experimental results show that BERT and BiLSTM achieved impressive performance on the ACOM task with 91% accuracy and a 90% F1-score. Additionally, this paper discusses the impact of fine-tuning specific hyperparameters by providing a comprehensive examination.

Due to the enormous data sizes involved in mobile computing and multimedia data transfer, it is possible that more data traffic may be generated, necessitating the use of data compression. As a result, this paper investigates how mobile computing data are compressed under all transmission scenarios. The suggested approach integrates deep neural networks (DNN) at high weighting functionalities for compression modes. The proposed method employs appropriate data loading and precise compression ratios for successful data compression. The accuracy of multimedia data that must be conveyed to various users is higher even though compression ratios are higher. The same data are transferred at significantly higher compression ratios, which save time while also minimizing data mistakes that may occur at the receiver. The DNN process also includes a visible parameter for handling high data-weight situations. The visible parameter optimizes the data results, allowing simulation tools to readily observe the compressed data. A comparison case study was created for five different scenarios in order to confirm the results, and it shows that the suggested strategy is significantly more effective than existing methods in roughly 63 percent of the cases.

People are increasingly concerned about their mental health wellness. Scientific studies suggest that online counselling for anxiety and depression is just as effective as in-person treatment. Additionally, journaling interventions have shown promise for individuals dealing with mental and psychological issues. In recent years, a growing number of mobile applications have been developed to improve people’s mental wellness and emotional communication. However, many of these applications are not available in Arabic but are available only in English or the native languages of their users, while other applications have feature limitations. This study presents a prototype of an interactive mental health mobile application, called Dawwen, to assist Arab individuals in freely expressing their feelings through online journaling, receiving recommendations for practices and activities, and locating nearby therapy centers based on their geolocation. Dawwen is augmented with an easy-to-use interface, a natural language processing (NLP) technique for analyzing the user input, and integrated features. The system is implemented using Android Studio and various cloud-based tools, making it adaptable for the integration of more advanced artificial intelligence (AI) technologies in the future. The System Usability Scale (SUS) scored an average of 88.25%, indicating high user satisfaction with the app’s functionality and ease of use. The study highlights Dawwen’s effectiveness in improving mental health support for Arabic-speaking users, filling a critical gap in existing digital mental health resources.

Machine learning has evolved from a lab curiosity to a widely used technology that is fundamentally reliant on ground truth data for model training and evaluation. This research addresses the challenges in obtaining accurate ground truth data due to limited domain expertise, sparse and unrepresentative datasets, and the high costs associated with data acquisition. The quality of this data significantly influences the reliability of machine learning models, prompting research into methods to improve ground-truth reliability. This research proposes a framework that utilize blockchain-based crowdsourcing for ground-truth data annotation. Blockchain technology, with its decentralized immutable ledger system, offers a secure method for data verification and collection from decentralized entities. The proposed framework was implemented in an Ethereum network environment using blockchain technology and smart contracts. Next, we evaluated the collected ground truth by measuring the inter-rater agreement among the participants. The experimental results indicate that blockchain can enhance annotation consistency, showing a higher reliability of crowd-sourced data compared to expert opinions. Most annotator pairs demonstrated moderate to strong agreement, confirming the potential of blockchain technology in improving ground truth data annotation.

One of the major challenges of academic institutions is the student dropout rate. It negatively impacts students, universities, and society by precluding student success, wasting time and financial resources, and reducing graduation rates. Previous studies have used machine learning (ML), deep learning (DL), and explainable artificial intelligence (XAI) techniques to predict dropout. However, most of these studies focused primarily on academic factors and were often limited to a single educational institution. Although national reports indicate that 40% to 50% of university students in Saudi Arabia do not complete their programs, few studies have examined dropout at various universities in the country or considered a broader set of factors. Therefore, this research aims to develop predictive models for academic dropout in Saudi universities using ML and DL techniques, taking into account various academic, personal, social, and cultural factors. Data were collected from 4,560 students and then processed and analyzed using twelve feature selection-based learning models. Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used as XAI models to identify the most influential features, including GPA, academic year, employment status, family/friends support, and prior major knowledge. The results indicate that the K-Nearest Neighbors (KNN)-based Recursive Feature Elimination (RFE) model achieves the best performance, with an accuracy of 97.6%. Additionally, the Local Explanation Evaluation Framework (LEAF) showed that LIME outperformed SHAP on all four metrics: fidelity, local concordance, prescriptivity, and stability. These findings provide insights into the key factors influencing student dropout at Saudi universities and support the development of early intervention strategies.