Urban traffic congestion remains an ongoing issue that requires advanced traffic management solutions. Accurate traffic forecasting plays a crucial role in Intelligent Transportation Systems, helping to mitigate congestion and improve mobility. Traditional machine learning approaches have been widely used for prediction tasks, often relying on large volumes of historical data for training. However, real-time adaptability is essential for dynamic traffic conditions. In this study, we leverage real-time traffic data and employ ADAptive GRAdient Descent, an online learning method that adaptively adjusts learning rates, allowing efficient updates as new data become available. To evaluate its performance, we implemented our approach on traffic data from a network of streets in Muscat, Oman, demonstrating its ability to provide accurate and timely congestion forecasts.

Integrating Working Capital Requirement (WCR) into supply chain decision-making is essential for balancing operational efficiency with financial sustainability. This study presents an Inventory Routing Problem (IRP) model tailored to healthcare supply chains, incorporating WCR considerations to optimize overall costs. By aligning inventory levels with financial considerations, our approach provides a more integrated perspective on supply chain management. The results highlight the significant impact of WCR optimization on decision-making, offering a framework for developing cost-effective and financially sustainable supply chains.

For human mental and physical health, sleep is a fundamental restorative process. Sleep analysis is considered as a crucial task to identify the various abnormalities, given the risks that sleep disorders can present. The gold standard for human sleep analysis is sleep scoring. Sleep experts review the PSG recordings and visually identify the various sleep stages for each sleep epoch. Due to the massive volume of recordings acquired during a single sleep period, manual sleep scoring task is considered as a time-consuming and labor intensive task. In this paper we propose a new approach for an interpretable automatic sleep scoring model based on supervised deep learning method and learning classifier system. The effectiveness of our approach was investigated using real electroencephalography (EEG).

The increasing complexity of global supply chains, combined with the need for fast, cost-effective, and environmentally friendly deliveries, has reinforced the importance of multimodal freight transportation(MFT) as a key solution to meet modern demands. One of the main challenges in MFT is to develop an innovative optimization model to plan and manage the supply chain. In this work, we consider four modes of transportation (air, road, rail, and sea) and propose an innovative multi-objective optimization model, designed to simultaneously minimize transportation costs, transit times, and CO2emissions, while integrating the complex operational constraints inherent in current logistic systems. To address this problem, we adopt two well-known algorithms : Non-Dominated Sorting Genetic Algorithm III (NSGA-III) and Teaching-Learning Optimization (TLBO), through an experimental study demonstrating the effectiveness of these evolutionary solution methods in solving these complex optimization problem.The results show that TLBO optimization effectively reduces costs and environmental impact, while the NSGAIII algorithm improves delivery times.

Healthy sleep is essential for human well-being. Sleep analysis is a necessary process for the majority of sleep disorders diagnosis. In this work we propose to analyze brain activity through Electroencephalogram analysis in order to identify sleep stages variation. We focus on the classification phase. Most works in sleep stages classification are based on prior experts signal scoring which is a hard task. So many available unlabeled data remain unused. To explore more these data and enrich the study of sleep classification, we propose a hybrid approach based on learning classifier systems and artificial neural networks. The effectiveness of the proposed approach was investigated using real electroencephalography data. Good results were reached comparing to supervised learning methods usually used. The proposed approach provides also, an explicit model that could be analyzed a posteriori by experts.