
The traveling salesman problem (TSP) remains challenging for metaheuristic algorithms, especially as the number of cities increases. This study proposes the particle-guided adaptive grey wolf optimizer (PMGHWO), which combines grey wolf optimizer (GWO)-based leadership guidance with crossover, particle-guided perturbation, and adaptive local refinement. PMGHWO was evaluated on ten TSPLIB instances and compared with grey wolf optimizer (GWO), genetic algorithms (GA), particle swarm optimization (PSO), whale optimization algorithm (WOA), and Harris Hawks optimization (HHO) under the same experimental conditions. The proposed method achieved shorter average tours on all tested instances, with reductions of 18.75% compared with GWO, 19.77% with HHO, 23.30% with GA, 39.08% with WOA, and 57.51% with PSO. Friedman and Wilcoxon tests confirmed significant differences between PMGHWO and the compared methods. The ablation study showed that adaptive refinement had the strongest effect on solution quality, while the influence of particle-guided perturbation and crossover varied across the benchmark instances. Although PMGHWO required more computation than the original GWO, its runtime remained competitive with several of the other methods. Overall, the results show that PMGHWO is a promising approach for TSP optimization and warrants further evaluation on larger and more complex combinatorial problems.
The discounted 0-1 knapsack problem (D0-1KP) generalizes the classical knapsack problem by partitioning items into groups of three, in which the third item of every group represents a discounted bundle of the first two and at most one item per group may be loaded. This grouping constraint enlarges the search space and makes the problem markedly harder than its classical counterpart. This paper presents BBAT, a binary bat algorithm for the D0-1KP. Bat velocities are mapped to selection probabilities through a sigmoid transfer function, and a greedy repair-and-optimization operator restores feasibility while raising the profit of every candidate solution. The algorithm keeps the small parameter set of the original bat metaheuristic, which limits the tuning effort required before deployment. BBAT was assessed on 14 benchmark instances drawn from the inverse strongly correlated and strongly correlated families, with 30 independent runs per instance. Against two elite genetic algorithms, BBAT improved the best profit found on 12 of the 14 instances and improved the mean profit on 7 of them. The gain in mean profit is concentrated on the inverse strongly correlated family, whereas on strongly correlated instances BBAT attains better peaks at the cost of higher run-to-run variance. These results identify BBAT as a competitive but variance-sensitive solver for the D0-1KP.
Ranking functionally similar cloud services by their quality of service (QoS) is essential for selecting the best option, yet current ranking methods generally handle only one QoS objective at a time and give up robustness once several conflicting criteria are in play. We propose a multi-objective ranking framework built on grey wolf optimization (GWO) to close this gap, pairing similarity computation via the Kendall Rank Correlation Coefficient (KRCC) with an optimization-driven prioritization step. Testing the resulting MOGWO-based method against several baseline algorithms on a cloud service dataset shows clear gains in both ranking accuracy and efficiency. The framework offers a scalable way to support decision-making in complex cloud environments and a clear structure for prioritizing services across multiple QoS dimensions at once.
Universities nowadays rely on digital platforms for organizing and sharing their institutional courses data. However, institutional information is scattered across different learning management systems, administrative databases, and research repositories, and there is no common system connecting them. Data were extracted from the relevant major academic database Springer Link, Scopus and IEEE for the year ranging from 2015 to 2025. Initially, 248 researches were observed out of which 30 studies review by expert were selected after filtering. The studies were analyzed for the cloud technologies in system design, the ontologies for the structured representation of knowledge and the knowledge graphs for the connected data systems. 22 out of 30 studies reported measurable improvements in knowledge accessibility. However, 78% of the reviewed systems lacked scalable reasoning mechanisms to handle large datasets, and fewer than 30% provided practical implementation guidance. Our research has three contributions: (i) literature synthesis of ontology-driven systems and cloud-based knowledge management in higher education; (ii) a system architecture that integrates cloud service models (IaaS, PaaS, SaaS), SPARQL-based knowledge graphs, and semantic technologies (OWL, RDF ontologies), grounded in a deployment scenario at Jazan University, Saudi Arabia; and (iii) a step-by-step implementation framework.
Early detection of work fatigue is a major challenge in industrial settings due to the lack of non-invasive, accessible, and low-cost systems capable of operating in real time. In this context, this research proposes a multimodal real-time fatigue detection system using facial vision and artificial intelligence, aimed at risk prevention and promoting occupational health. The system integrates geometric and behavioral parameters, such as eye aspect ratio (EAR), head tilt, and mouth opening, processed on a Raspberry Pi 5 using MediaPipe and a hybrid convolutional neural network (CNN) MobileViT model. Visual and audible alerts are managed by an ESP32 microcontroller using the message queuing telemetry transport (MQTT) protocol, while a graphical interface developed in Tkinter allows real-time monitoring of operator status. Experimental results, evaluated in a simulated work environment using AI-generated synthetic videos, show an accuracy greater than 97% and a latency of less than 250 ms, confirming the system's effectiveness in the early detection of signs of drowsiness and attention deficit. In conclusion, the proposal represents a non-invasive, scalable, and efficient solution that combines computer vision, deep learning, and the Internet of Things (IoT) to strengthen workplace safety and well-being.