Hierarchical Fuzzy Stochastic Configuration Network Based on Canonical Correlation Analysis for Multiview Pulse Signal Fusion

Pulse-based diagnostic (PBD) is a crucial noninvasive approach for disease diagnosis which acquires multiview pulse signals through various sensors for disease classification. Takagi–Sugeno–Kang (TSK) fuzzy systems and multiview methodologies are extensively employed for multiview pulse signal fusion in PBD systems. However, problem still exists in integrating multiview learning mechanism and classical fuzzy systems. The most critical challenges involve effectively utilizing multiview information while improving computational efficiency and ensuring universal approximation property. Consequently, we proposed a hierarchical fuzzy stochastic configuration network based on canonical correlation analysis (HFSCN-CCA) method to enhance the performance of TSK fuzzy systems on multiview datasets. Specially, we replaced the deep canonical correlation analysis framework with data-independent incremental HSCN-CCA method to increase the computational efficiency and ensure universal approximation property while maximizing the correlation. In addition, we optimized the traditional TSK fuzzy system with a novel joint membership function to capture sample-specific multiview information for higher representation capability. Furthermore, we conducted multiple experiments on diverse disease datasets to validate the performance of HFSCN-CCA and successfully demonstrated the complementarity of the two signals in multiple disease classification tasks.