Algorithms

Algorithms

Researchers Develop Novel Reinforcement Learning-Based Acceptance Criteria for Metaheuristic Algorithms

Researchers at Erciyes University have proposed a new approach to improving the performance of metaheuristic algorithms using reinforcement learning-based acceptance criteria. The study, published in the International Journal of Computational Intelligence Systems, found that metaheuristics with deep Q-learning-based offline acceptance criteria outperformed existing acceptance criteria and other variants. This breakthrough

Machine learning

Urban Flood Susceptibility Mapping Using Deep and Machine Learning Algorithms

Researchers from the University of Kurdistan have developed a family of new deep neural networks, namely 'deep abstract networks' (DANet), to produce reliable urban flood susceptibility maps. The DANet algorithm was trained using Sanandaj City, Iran, as an example, and was compared to five state-of-the-art benchmark learning algorithms.

Machine learning

Improving Pest Control with Explainable Artificial Intelligence in Agriculture

Researchers at the Swedish University of Agricultural Sciences have developed an innovative approach to mitigating damage caused by insect pests, which is a significant challenge for farmers worldwide. Traditional methods of using insecticides have led to high synthetic chemical usage, with a large portion of the applied insecticide not reaching

Machine learning

Predicting COVID-19 Severity in Pediatric Patients using Machine Learning

A new study from Tehran, Iran, has unveiled a significant breakthrough in predicting COVID-19 severity in pediatric patients. The research, conducted by a team from the Tehran University of Medical Sciences, employed machine learning algorithms to analyze the clinical characteristics of 588 pediatric patients with confirmed COVID-19. The findings suggest

Genetic research

Hybrid Approach for Predictive Mapping of Arsenic Pollution in Groundwater Resources

Researchers at the University of Guilan in Iran have developed a new methodology for modeling and mapping arsenic contamination in groundwater. The approach uses a coupled supervised self-organizing map (SSOM) and genetic algorithm (GA) to identify areas with high arsenic concentrations. By analyzing groundwater samples and variables that introduce arsenic

Genetic research

Breakthrough in Microwave Absorption Technology

Researchers at the Motilal Nehru National Institute of Technology Allahabad in Prayagraj, India, have made significant strides in developing a lightweight and thin microwave absorber that showcases exceptional performance in electromagnetic interference (EMI) shielding and stealth technologies. The innovative composite material, comprised of nickel-dispersed boron carbide, has been designed to

Genetic research

Simulation-Based Optimization for Complex Systems

Researchers at the University of Leeds have developed a novel framework for multi-objective simulation optimization, which involves using a combination of Genetic Algorithm and Linear Programming to explore a large design space and determine the trade-off between conflicting objectives. The technique has been successfully applied to a real-world problem, specifically

Machine learning

Advances in Chemicals and Chemistry: Improving Deposition Using Non-Dominant Sorting Genetic Algorithm-II

Researchers at the Department of Mechanical Engineering, Acad Technol, have made significant strides in improving the deposition of electroless nickel-copper-phosphorous coating using non-dominant sorting genetic algorithm-II. The team, led by Jhumpa De, aimed to develop predictive models using machine learning approaches to optimize the coating process. By varying the coating

Genetic research

Optimization of Centrifugal Fan Volute Parameters

Researchers from Kunming University of Science and Technology in China have conducted a study to enhance the operational effectiveness of centrifugal fans under specific operating conditions. Using a combination of machine learning and genetic algorithms, the team optimized three structural parameters of the fan volute, resulting in improved performance indicators

Machine learning

Artificial Intelligence Integration in Curriculum Evaluation: A Promising Frontier

Researchers at Igdir University have explored the potential of incorporating metaheuristic artificial intelligence (AI) optimization algorithms into curriculum evaluation, proposing a novel approach to enhance educational outcomes. The study reveals a scarcity of direct applications of AI optimization techniques in educational contexts, identifying a gap in research and an opportunity

Machine learning

Machine Learning Algorithm Accurately Predicts Risk of Type 2 Diabetes in Children with Obesity

A groundbreaking study by researchers from Tongji University in Shanghai, People's Republic of China, has developed and internally validated a machine learning (ML)-based model to predict the risk of type 2 diabetes mellitus (T2DM) in children with obesity. The research, published in Frontiers in Endocrinology, found that

Machine learning

Artificial Intelligence Research Reveals Insights into Predicting Relationship Dynamics

Research conducted by the School of Computer Science and Information Technology has shed light on the effectiveness of machine learning algorithms in predicting relationship dynamics during initial meetings. The study analyzed various models, including Light Gradient Boosting Classification (LGBC), in conjunction with the Henry Gass Solubility Optimization Algorithm (HGSOA), Flying