The N-Queens puzzle, a classical combinatorial optimization problem, continues to serve as an effective benchmark for evaluating the performance of intelligent search and optimization algorithms. Traditional deterministic methods typically struggle with scalability as the problem size increases, making metaheuristic approaches a promising alternative. This study investigates the application of metaheuristic techniques such as genetic algorithms, particle swarm optimization, simulated annealing, and ant colony optimization, with a particular emphasis on the recently emerging BRADO (Balanced Random Drift Optimization) algorithm. BRADO's adaptive drift mechanism and balanced exploration-exploitation strategy are analyzed for their suitability in navigating the highly constrained solution space of the N-Queens puzzle. Experimental evaluations compare BRADO's performance with other metaheuristics based on convergence speed, success rate, computational efficiency, and robustness across multiple board sizes. Results indicate that BRADO outperforms several conventional metaheuristic methods by achieving faster convergence and higher solution consistency, especially in large-scale N-Queens instances. The findings highlight BRADO's potential as an efficient and scalable optimization technique for complex constraint-satisfaction problems.
Career planning and skill development for students have become increasingly complex due to rapidly evolving industry demands and fragmented learning resources. Existing career guidance systems largely rely on static and generic recommendations, offering limited personalization and adaptability. To address these challenges, this paper proposes an AI-driven career planning and self-development platform that delivers dynamic and personalized guidance tailored to individual students. The proposed system employs a hybrid recommendation framework that integrates collaborative filtering and content-based filtering, enhanced by neural networks for skill-gap analysis. Furthermore, Gemini API integration enables contextual academic project suggestions and adaptive career roadmaps aligned with students' interests and long-term career objectives. By analyzing academic history, learning behavior, and personal preferences, the platform recommends relevant projects, skill pathways, and curated free and paid learning resources. Experimental evaluation demonstrates improved recommendation accuracy and higher user relevance compared to traditional rule-based career guidance approaches. The results indicate that the proposed platform effectively bridges the gap between academic learning and industry readiness, providing a scalable and intelligent solution for student career planning and self-development.
This paper presents an Arabic letter encoding system for eye-tracking–based communication designed to assist individuals with locked-in syndrome. Using electrooculography (EOG), eye movements are translated into Arabic text based on an existing eye-movement database. The proposed approach assigns specific stroke combinations to Arabic characters, inspired by Katakana character formation. First, the characteristics of EOG signals are analyzed. Next, code- protocol–based eye-input systems for Katakana characters are reviewed. Based on these principles, a set of basic strokes for Arabic letters is defined, followed by a novel Arabic letter encoding scheme, which constitutes the main contribution of this work. A second contribution is the adaptation of this encoding scheme to extract the corresponding EOG signals. The proposed system adopts a semantic approach in which visually similar Arabic letters share related eye strokes, improving intuitiveness and ease of learning. The resulting dataset contains 2,500 records and enables accurate decoding of EOG data into Arabic text, demonstrating its potential as a non-verbal communication tool for individuals with severe physical disabilities.
Zambia has experienced recurrent cholera outbreaks since 1977, with the 2023-2024 epidemic recording over 10,887 cases and 432 deaths, the most severe in the nation's history. These outbreaks persist due to inadequate surveillance, delayed reporting, and a lack of predictive capacity regarding environmental triggers (like rain and temperature), resulting in slow detection and a delayed response. This paper proposes a hybrid AI-driven Early Warning System (EWS) that integrates the Random Forest (RF) for case classification and Long Short-Term Memory (LSTM) networks for temporal outbreak forecasting. The system combines community-based mobile reporting with environmental data analysis to facilitate real-time surveillance. Using a proxy dataset (YEM-CHOLERA-EOC-DIS-WEEK-20160424-20200621.csv) to simulate the outbreak dynamics in the absence of local digital records, the proposed RF-LSTM ensemble model has demonstrated superior performance compared to the standalone models. The hybrid model has achieved a classification F1-score of 86% and a forecasting Root Mean Squared Error (RMSE) of 0.134, significantly outperforming the individual RF and LSTM models. This study presents a scalable, proactive framework for mitigating future cholera epidemics in resource-constrained settings.
The rapid expansion of smart cities has led to the integration of Artificial Intelligence (AI) at the edge, enabling real-time decision-making for intelligent urban infrastructure. However, conventional centralized AI models pose critical challenges, including data privacy risks, security vulnerabilities, and high computational overhead. This paper investigates Federated Learning (FL) as a transformative paradigm to enhance security, privacy, and efficiency in edge AI systems for smart cities. Unlike traditional AI training methods, to cyber threats while ensuring compliance with data protection regulations. To address key challenges in heterogeneous smart city environments, a hybrid optimization framework is proposed that integrates differential privacy, secure multi-party computation (SMPC), and blockchain- based authentication. This approach strengthens resilience against adversarial attacks while ensuring secure model updates. Additionally, an adaptive aggregation mechanism is introduced, dynamically adjusting model updates based on device reliability, data distribution, and network conditions, optimizing both learning efficiency and energy consumption in edge AI networks. Extensive experimentation on real-world smart city datasets demonstrates that the proposed framework enhances model accuracy, robustness, and privacy preservation compared to conventional AI approaches. The findings establish Federated Learning as a cornerstone for secure, scalable, and privacy-aware AI in smart cities, facilitating trustworthy deployment of intelligent urban infrastructure. This research provides valuable insights for policymakers, researchers, and industry professionals, paving the way for next-generation AI-driven smart cities with enhanced security, privacy, and efficiency.
