Current Research

Current research spans diverse areas of computational science, focusing on improving the efficiency and applicability of existing models and algorithms. Key areas include developing advanced machine learning techniques for tasks like malware detection, agricultural price prediction, and user modeling, often leveraging bio-inspired algorithms (e.g., evolutionary computation, harmony search) and novel architectures such as Kolmogorov-Arnold networks. This research aims to address challenges in model robustness, data limitations, and computational complexity, ultimately improving the accuracy and reliability of solutions across various fields. The impact of this work is significant, promising advancements in areas ranging from cybersecurity and healthcare to agriculture and computer vision.