Upper Limb Tremors Classification for Parkinson’s Disease Using W-Band (76–81 GHz) Doppler Millimeter-Wave Sensing and Deep-Learning-Based Classifier

Parkinson’s disease (PD) is a neurodegenerative disorder with an increasing incidence rate that significantly affects patients’ motor functions and quality of life. Involuntary upper limb tremors (ULTs) commonly manifest unilaterally, affecting either the left or right upper limb. Clinically, ULT frequencies can be categorized into three distinct classes: low-frequency (<4.0 Hz), mid-frequency (4.0–7.0 Hz), and high-frequency (>7.0 Hz) tremors. These tremor motions are characterized by oscillatory or rotational (angular displacement) movements, commonly referred to as the micro-Doppler effect (mDE). This study aims to develop a short-range (<1.0 m) and contactless sensing method for ULT detection based on Doppler millimeter-wave (mm-Wave) radar. The reflected electromagnetic waves indicate time-varying frequency characteristics, which can be analyzed by using time–frequency transform (TFT) methods, such as the Wigner–Ville distribution (WVD) and smoothed pseudo WVD (SPWVD). These TFT methods are employed to extract mDE features, which are subsequently visualized as color-coded spectrograms for ULT classification. Then, a two-dimensional (2D) convolutional neural network (CNN) is employed to automatically recognize the visual feature patterns for ULTs classification based on frequency and amplitude information. In the experimental setup, the W-band (76–81 GHz) Doppler mm-Wave biosensor is implemented for sensing and extracting feature patterns. The proposed classifiers based on “WVD + 2D CNN” and “SPWVD + 2D CNN” are trained and validated by using the collected datasets, with 60% randomly selected for training datasets and 40% for testing datasets in each fold validation. A 10-fold cross-validation method is applied to evaluate the classifier’s performances, achieving an average precision of 95.92 ± 0.60%, average recall of 95.89 ± 0.62%, average F1-score of 0.9588 ± 0.0060, and average accuracy of 95.89 ± 0.62%, respectively. The experimental results demonstrate the feasibility of the proposed classifier for real-time ULTs classification in PD patients using short-range (<1.0 m) and contactless sensing.