Adaptive boundary-aware artificial immune recognition system for data classification

In this paper, we introduce AIBARS (Adaptive Immune Boundary-Aware Recognition System), a novel learning algorithm designed to improve upon the traditional Artificial Immune Recognition System (AIRS). AIBARS addresses key limitations of AIRS by integrating a boundary-aware stimulation measure, an antigen-specific stopping criterion, and a more directed mutation approach. These innovations enable AIBARS to effectively navigate complex decision boundaries and reduce time complexity, particularly in high-dimensional datasets. Experimental results show that AIBARS achieves a 5-10% improvement in classification accuracy compared to AIRS. Additionally, AIBARS reduces memory cells by 20-30%, leading to more efficient data representation and a 15-25% reduction in computational costs. The algorithm also reduces processing time by 10-20%, making it a more efficient approach overall. Evaluations were conducted using a variety of datasets, including public domain datasets from the UCI Machine Learning Repository and synthetic datasets. The results indicate that AIBARS offers significant performance and efficiency gains over AIRS, while substantially reducing computational expenses. • AIBARS improves accuracy, enhances decision boundary detection, and reduces memory cells by 20-30% for efficiency. • AIBARS outperforms AIRS, cuts costs by 15-25%, reduces time by 10-20%, and is validated on UCI and synthetic datasets. • AIBARS adapts to complex tasks, with efficient stimulation and mutation strategies for handling high-dimensional datasets. • AIBARS enhances generalization, reducing overfitting and ensuring reliable performance from training to real-world data. • AIBARS: Adaptive immune-inspired system improving data classification by 5-10% over AIRS with robust, adaptive features.