Advancing Biotechnological Research with a Multi-Source Somatosensory Information Fusion Method for Folk Dance Movement Recognition

Abstract

This paper presents a groundbreaking method for recognizing dance movements using a multi-source somatosensory information fusion approach, tailored specifically for applications in biotechnological research. By integrating diverse somatosensory inputs, our method addresses the complex dynamics of folk dance movements, enhancing the accuracy and reliability of motion classification. The effectiveness of our adaptive fusion algorithm was validated through experimental tests involving 30 participants across two distinct dance performances. Results demonstrate that our approach not only outperforms existing state-of-the-art methods in terms of performance but also achieves high levels of accuracy. This study underscores the potential of multi-sensor fusion in biotechnological applications, particularly in areas requiring precise movement recognition and analysis, such as the study of muscular or neurological responses during physical activities. The findings highlight the practical benefits of harnessing multiple somatosensory signals to refine motion classification systems, suggesting a significant advancement in biotechnological methodologies.