This study investigates the acceptance of ChatGPT as an educational tool through the lens of the Technology Acceptance Model (TAM), a widely recognized theoretical framework for understanding technology adoption. The primary objective is to examine how primary school teachers perceive ChatGPT in terms of its usefulness and ease of use within educational settings. The TAM framework emphasizes two core dimensions: Perceived Usefulness (PU) and Perceived Ease of Use (PEOU). Additional factors, including attitude, behavioral intention, perceived credibility, and social influence, were incorporated to provide a comprehensive analysis.
Dermatological disorders constitute a significant global health burden, yet the accurate and timely diagnosis remains a challenge due to the subjective nature of visual inspections and the lack of specialists. Although deep learning (DL) has shown promise in automated classification, the black box nature of these models and their high computational costs often hinder clinical adoption. This study proposes a lightweight, interpretable Custom Convolutional Neural Network (CNN) for the multi-class classification of five distinct skin conditions: Acne, Vitiligo, Hyperpigmentation, Nail Psoriasis, and Stevens-Johnson syndrome/toxic epidermal necrolysis (SJS-TEN). Using a data set of 9,548 images, we implemented a comprehensive pipeline featuring a two-stage augmentation and balance strategy to mitigate class imbalance. The new proposed SkinNet model was benchmarked against four established architectures: ZooCNN, CNN, MobileNetV2, and DenseNet121. Experimental results demonstrate that SkinNet achieved superior performance with an overall accuracy of 86% and a macro-averaged F1-score of 0.85, outperforming transfer learning baselines. To address the critical need for transparency in medical AI, the model’s decision-making process was validated using four Explainable AI (XAI) techniques: Local Interpretable Model-agnostic Explanations (LIME), Gradient-weighted Class Activation Mapping (Grad-CAM), Integrated Gradients, and Diverse Counterfactual Explanations (DiCE). These visualizations confirmed that the model consistently focuses on relevant pathological features such as inflammatory papules, depigmented patches, and onycholysis rather than background noise. This research highlights the efficacy of task-specific, lightweight architectures to provide accurate, efficient, and reliable diagnostic support for dermatology
The Internet of Vehicles (IoV) faces critical cybersecurity challenges that require real-time intrusion detection on resource-constrained edge devices. This study proposes a Three-stage Variance-correlation Binary Grey Wolf Optimization (TVC-BGWO) feature selection framework integrated with ensemble learning. The framework combines Variance Threshold filtering, Correlation-based filtering, and Binary Grey Wolf Optimization to achieve 93.59% feature reduction (78→5 features) while maintaining competitive detection performance. Random Forest with TVC-BGWO achieved 99.91% binary accuracy and 99.87% multiclass accuracy 6 attack types plus benign traffic on Canadian Institute for Cybersecurity Intrusion Detection System (CIC-IDS2017). Statistical validation (McNemar’s χ2 = 82.01, p < 0.001) confirms a significant improvement. The framework provides 59.0% training time reduction and sub-millisecond inference latency meeting V2V communication requirements. Adversarial evaluation reveals exceptional resilience to data poisoning 99.98% robustness and moderate vulnerability to test-time perturbations. This work contributes to intelligent transportation security by demonstrating competitive intrusion detection performance while achieving substantial computational efficiency gains suitable for edge deployment.
In this paper, we propose a new exact method to optimize a stochastic linear function over an efficient set of a multi-objective stochastic integer linear programming (MOSILP) problem. The proposed method combines two approaches: the first is called the L method, while the second is an adaptation of the branch-andbound procedure. This adaptation is reinforced by efficient cuts and tests, enabling the method to eliminate many inefficient solutions in the search tree. A didactic example is provided to detail all steps of the method. This is followed by testing the method on a set of randomly generated instances and comparing the obtained results with the most recent method. The experimental study shows that the proposed method remains competitive and delivers satisfactory results.
In today’s digital ecosystem, there is a dominance of attention driven content platforms that promote sensationalism over informational quality. These platforms use various means to manipulate users. Clickbait is among them. It often uses misleading or exaggerated headlines to lure people to click on a link. This leaves them in discontent as the promises are never met. The aim is to gain user engagement by either routing them to a page with lots of advertisements that, in turn, boost their revenue or simply spreading misinformation. This necessitate the development of automatic clickbait detection models. This article serves as a systematic review of the work done in this domain, focusing on two important areas: existing datasets with their labeling techniques, and the evolution of various clickbait detection models from ML to DL to new pre-trained language models such as BERT and RoBERTa. This paper aims to serve academic researchers and industry professionals seeking an overview of clickbait detection methods with particular emphasis on ground truth datasets generation and their labeling strategies.
