A Robust Frequency-domain-based Graph Adaptive Network for Parkinson's Disease Detection from Gait Data

• Published in: IEEE transactions on multimedia Vol. 25; pp. 1 - 14
• Main Authors: Zhong, Cankun, Ng, Wing W. Y.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Abnormalities; Adaptation models; Correlation; Deep learning; Diagnosis; Feature extraction; Foot; Frequency domain analysis; Frequency-domain; Gait; Generalization error; Geometric accuracy; Graph network; Parkinson's disease; Parkinson's disease detection; Robustness; Sensor phenomena and characterization; Sensors; Vertical forces; Vertical ground reaction force
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2022.3217392

Parkinson's disease (PD) is a neurodegenerative disease with a high incidence rate. Effective early diagnosis of PD is critical to prevent further deterioration of a patient's condition, where gait abnormalities are important factors for doctors to diagnose PD. Deep learning (DL)-based methods for PD detection using gait information recorded by non-invasive sensors have emerged to assist doctors in accurate and efficient disease diagnosis. However, most existing DL-based PD detection models neglect information in the frequency domain and do not adaptively model the correlation of signals among sensors. Moreover, different people have different gait patterns. Therefore, the generalization capabilities of PD detection models on diversities of individuals' gaits are essential. This work proposes a novel robust frequency-domain-based graph adaptive network (RFdGAD) for PD detection from gait information (i.e., vertical ground reaction force signals recorded by foot sensors). Specifically, the RFdGAD first learns the frequency-domain features of signals from each foot sensor by a frequency representation learning block. Then, the RFdGAD utilizes a graph adaptive network block taking frequency-domain features as input to adaptively learn and exploit the interconnection between different sensor signals for accurate PD detection. Moreover, the RFdGAD is trained by minimizing the proposed Jensen-Shannon divergence-based localized generalization error to improve the generalization performance of RFdGAD on unseen subjects. Experimental results show that the RFdGAD outperforms existing DL-based models for PD detection on three widely used datasets in terms of three metrics, including accuracy, F1-score, and geometric mean.