The 'Cold Start' problem, characterized by insufficient transaction history leading to inefficient personalization, represents one of the frequent challenges encountered in e-commerce systems. This issue, along with data sparsity resulting from limited product interactions, further complicates the reliability of conventional recommendation engines. The objective of this research is to design a novel hybridized recommendation system that enhances both security and suggestion accuracy by dynamically adapting to user interactions in digital environments. By leveraging contextual information and sequential user behavior patterns, the proposed method addresses gaps left by traditional recommender... More >

The potential loss of traditional Tunisian dishes threatens the sustainability of valuable cultural and nutritional traditions. To help preserve this rich heritage, a conversational AI system has been developed that employs advanced language processing and machine learning techniques to bring Tunisia’s culinary traditions to life in a digital space. Multilingual transformer models have been adapted to understand Tunisian dialects and combined with a detailed Food Heritage Knowledge Graph, allowing personalized, interactive access to authentic recipes and the stories behind them. A hybrid dialogue system operated by a chatbot has been implemented to ensure smooth, meaningful conversations t... More >

Agriculture plays a fundamental role in sustaining the global economy and ensuring food security, yet farmers often rely on intuition and traditional practices for crop selection, leading to inefficiencies in yield and resource utilization. This research proposes a machine learning-based system for smart crop prediction and recommendation, aimed at enhancing precision agriculture through data-driven decision-making. The study integrates historical datasets containing soil parameters (pH, nitrogen, phosphorus, potassium) and climatic factors (temperature, humidity, rainfall) with real-time environmental data fetched via APIs. Multiple machines learning models, including Decision Trees, Suppor... More >

This study presents an AI-powered approach to enhance quality control and traceability in the agri-food sector, focusing on the automated detection and classification of two Tunisian date varieties: Deglet Nour and "Bsir". The main objective is to develop a smart system that can quantitatively and qualitatively determine the proportion of any contamination of one variety by the other within a batch. To achieve this, state-of-the-art object detection YOLO models, v8 and v12, have been employed, trained on a custom annotated dataset which includes a wide range of real-world images, capturing the variability in the studied date fruit size, shape, and presentation. Both YOLO models were fine-tun... More >

The integration of sixth-generation (6G) networks with Wireless Sensor Networks (WSNs) creates unprecedented opportunities for developing secure and scalable smart city infrastructures. However, the proliferation of heterogeneous devices and exponential data growth demand more robust security solutions. While existing hybrid deep learning approaches combining convolutional, recurrent, and attention-based architectures show promise in attack detection, they face limitations including high false-positive rates, inadequate modeling of topological dependencies, and vulnerability to adversarial attacks. This paper presents an enhanced intrusion detection framework that integrates Graph Neural Net... More >

Getting feedback from the students in education is the key to improving the learning experience in education, but reading through hundreds of feedback forms can be overwhelming. Sentiment Analysis (SA), which is a NLP (Natural Language Processing) technique, comes in interprets the emotions and opinions behind their feedback. This review explores how various technologies like machine learning and NLP are being used to understand student opinions about teaching quality, course materials, assignments, exams, instructional behavior and overall learning experience. Sentiment analysis helps educators understand student concerns, thereby improving the learning experience and promoting a student-ce... More >

The electric vehicle (EV) manufacturing industry rapidly progresses from Industry 4.0 to Industry 5.0, next-generation computing technologies are emerging as disruptive enablers. This paper explores about the advanced computing paradigms to improve efficiency, robustness and adaptation across EV manufacturing ecosystems in the revolved vehicle industry in order to satisfy the increasing needs of intelligent automation, real-time decision-making and sustainable production. Through the integration of industrial case studies, literature reviews and rigorous technology mapping, the paper work validates the potential of these technologies to optimize resource utilization, speed up computer operat... More >