Issue 2 (December)

The Traveling Salesman Problem (TSP) is a classic combinatorial optimization problem that has significant implications in various fields, including logistics, routing, and scheduling. However, the problem becomes increasingly difficult as the number of cities increases, leading to the need for efficient and scalable solution approaches. This paper presents a novel hybrid metaheuristic algorithm designed to solve large-scale TSPs. The proposed algorithm combines the strengths of two distinct metaheuristic techniques—Genetic Algorithms (GAs) and Simulated Annealing (SA)—to exploit their complementary advantages in search space exploration and exploitation. The Genetic Algorithm is responsible for the initialization and mutation stages, while the Simulated Annealing is applied to refine the solutions through local search and global optimization. The hybrid metaheuristic is tested on a variety of benchmark instances with up to 1000 cities and demonstrates superior performance compared to the individual algorithms. The computational experiments demonstrate that the proposed hybrid algorithm can effectively reduce the running time and improve solution quality for large-scale TSPs, which is crucial for practical applications.

The rapid advancement in the healthcare sector has led to an exponential increase in the volume of patient data, which necessitates secure and efficient sharing mechanisms. Blockchain technology, renowned for its inherent security features, and deep learning algorithms, capable of processing complex data patterns, present promising solutions to address these challenges. This paper explores the integration of blockchain technology with deep learning to enhance the security and privacy of healthcare data sharing. By leveraging the decentralized nature of blockchain and the predictive power of deep learning, the proposed framework aims to create a robust system that can securely store, manage, and analyze healthcare data. The paper discusses the architecture of the integrated system, highlighting the critical components such as the blockchain ledger, smart contracts, and deep learning models. It also examines the potential benefits and limitations of this approach, focusing on its applicability in real-world scenarios. The findings suggest that the fusion of these technologies can significantly improve the integrity and confidentiality of healthcare data, fostering a more secure and efficient healthcare ecosystem.

The integration of intelligent systems in smart cities has revolutionized the management of urban infrastructure, with traffic flow prediction being a critical component of this transformation. This paper investigates the application of intelligent systems for real-time traffic flow prediction, aiming to enhance traffic efficiency and reduce congestion in urban environments. By leveraging advanced techniques such as machine learning, data analytics, and artificial intelligence, this research proposes a novel framework for predicting traffic patterns with high accuracy. The framework involves the collection of real-time data from various sources, including traffic cameras, sensors, and historical records, and uses these inputs to train predictive models. The effectiveness of the proposed system is evaluated through experimental analysis, demonstrating improved traffic flow prediction capabilities compared to traditional methods. The outcomes of this study provide valuable insights into the potential of intelligent systems in optimizing urban traffic management and contribute to the development of more efficient and sustainable smart cities.

This paper investigates the potential of Intelligent Tutoring Systems (ITS) in fostering adaptive learning environments. ITS are computer-based applications designed to assist learners in acquiring knowledge and skills by adapting to their individual needs and learning styles. The increasing use of technology in education has opened up new avenues for personalized learning experiences, and ITS play a crucial role in this transformation. The aim of this study is to explore the various features and functionalities of ITS, such as intelligent feedback, personalized learning paths, and self-regulation support, and to analyze their effectiveness in enhancing learning outcomes. By integrating artificial intelligence and machine learning techniques, ITS can dynamically adjust the learning content and pace according to the learners' progress and performance. The paper also discusses the challenges in implementing ITS and the potential benefits for both students and educators. The findings suggest that ITS can significantly improve the quality of education, making it more inclusive, efficient, and tailored to individual learners' needs.

The rapid advancement of machine learning techniques has revolutionized various fields, including remote sensing data analysis. This paper explores the applications of machine learning in the analysis of remote sensing data, highlighting its potential to enhance the accuracy and efficiency of data interpretation. Remote sensing data, collected from satellites and aerial platforms, offer vast amounts of information about Earth's surface, atmosphere, and oceans. However, the complexity of this data can make it challenging to process and extract meaningful insights. Machine learning algorithms have proven to be effective tools for addressing these challenges, by learning from patterns and relationships within the data. This paper discusses several key applications of machine learning in remote sensing, such as image classification, change detection, and object detection. Furthermore, it examines the limitations and future directions of incorporating machine learning techniques into remote sensing data analysis. By demonstrating the capabilities of machine learning, this paper aims to provide insights into how this technology can contribute to the advancement of Earth observation and monitoring.

This paper explores the application of machine learning models in predicting stock price movements within the financial markets. The study aims to investigate the effectiveness of various machine learning algorithms in forecasting stock prices, with a focus on accuracy, robustness, and adaptability. By analyzing historical stock price data, the research employs several machine learning techniques, including linear regression, decision trees, support vector machines, and neural networks. The results demonstrate that machine learning models, particularly neural networks, exhibit significant potential in predicting stock price movements. However, the research also highlights the challenges faced by these models, such as overfitting, data volatility, and the need for continuous model updating. The findings provide valuable insights into the utilization of machine learning in the financial sector, offering practitioners a more informed approach to investing and risk management.