Abstract

Background Given the inadequacy of research in the realm of quality assessment (QA) for multimodal physiological signals, the current reliance on coarse-grained assessment based solely on unimodal signals has become manifestly insufficient. Within the domain of wearable devices, there is a particularly pressing need for refined QA results pertaining to multimodal physiological signals. This paper endeavors to introduce a real-time multimodal fine-grained QA algorithm and, through real-time application demonstrations, showcase its efficacy.

Methods We have devised an attention network capable of simulating localized to global dependency relationships. By training individually, a corresponding QA model is assigned to each pattern. Fine-grained labels for the signals are allocated through weakly supervised learning. The proposed lightweight model has undergone systematic deployment, accompanied by the development of an interactive interface.

Results The experiments indicate that the proposed fine-grained QA exhibits intuitive consistency with evaluations by human experts. Tests conducted on a mixed database demonstrate that the proposed methodology outperforms existing state-of-the-art methods. Furthermore, the algorithm has been deployed and integrated into practical applications, yielding outstanding results on self-constructed data. This study introduces a real-time multimodal fine-grained QA algorithm that exhibits a high level of visual consistency comparable to human experts, thereby enhancing the performance of multimodal information derivation tasks.

Conclusions The proposed system achieves real-time visualization in real-world environments, offering clinical experts a high-quality reference granularity for multimodal information.

LEAF-Net: A real-time fine-grained quality assessment system for physiological signals using lightweight evolutionary attention fusion

Recommended citation: Jian Liu, Shuaicong Hu, Yanan Wang, Qihan Hu, Daomiao Wang, Wei Xiang, Xujian Feng, and Cuiwei Yang. "LEAF-Net: A real-time fine-grained quality assessment system for physiological signals using lightweight evolutionary attention fusion" Expert Systems with Applications. (2025)
Download Paper