MF-PNet: A Lightweight Multi-Frequency Progressive Neural Network for Depression Classification Deployed on Wearable EEG Sensors.

Low-channel wearable EEG offers a compact acquisition configuration for depression recognition, but its limited spatial coverage and the computational constraints of edge devices present challenges for representation learning and embedded inference. This paper presents MF-PNet, a multi-frequency progressive neural network designed for three-channel EEG. Five frequency-specific branches process the canonical EEG bands in parallel, while a full-band branch progressively aggregates their representations through layer-wise lateral transfer and squeeze-and-excitation-based channel recalibration. Temporal and channel attention are further incorporated to emphasize informative EEG segments and frontal channels. Subject-level leave-one-subject-out cross-validation was conducted on a balanced in-house cohort of 146 participants. Across five random seeds, MF-PNet achieved an accuracy and F1-score of 98.8% ± 1.0% under auditory stimulation. Within-dataset evaluation on the independent Figshare and MODMA cohorts yielded accuracies of 92.1%±2.0% and 66.4%±6.5%, respectively. For embedded implementation, MF-PNet was distilled into a MobileNetV3-based student containing 75.51K parameters. The student achieved an accuracy of 99.3% ± 1.2%, and its INT8 representation retained an accuracy of 98.5% ± 0.9%. On the STM32U575CGT6 MCU, the implementation required 217.15KB of ROM and 215.78KB of RAM, with an inference latency of 45.99ms per 2-s EEG window and a power consumption of 43.2mW. The resulting framework integrates progressive cross-band EEG representation learning, teacher-student compression, INT8 quantization, and MCU execution into a unified pipeline for three-channel wearable EEG depression recognition.