Computational modeling and pattern recognition of physiological characteristics of music-induced emotional responses

Introduction This study introduces an innovative computational framework for modeling and recognizing physiological characteristics linked to emotional responses induced by music. Traditional approaches to emotion recognition often rely on static feature extraction and linear classification methods, which fail to capture the temporal and dynamic nature of emotional states. Methods To address these limitations, the proposed MemorySparseRule framework integrates temporal dependency modeling with sparse representation learning, enabling a more nuanced analysis of the complex interactions between music and emotional responses. The framework is composed of three core modules: the Memory Stabilization Adapter, which ensures robust temporal data processing; the Sparse Interaction Filter, which isolates significant physiological patterns; and the Rule Grounded State Binder, which consolidates these patterns into interpretable emotional states. Results and Discussion Experimental evaluations demonstrate that the MemorySparseRule model achieves superior performance in emotion recognition tasks, with an accuracy improvement of 15% compared to existing methods. These findings underscore the potential of the framework to advance affective computing and deepen the understanding of music psychology, offering a computational lens through which the intricate relationship between auditory stimuli and human emotions can be explored. This research not only enhances the precision of emotion recognition systems but also contributes to the development of applications in therapeutic music interventions and personalized emotional analysis.