Analyzing unstable gait patterns from Electroencephalography (EEG) signals is vital to develop real-time brain-computer interface (BCI) systems to prevent falls and associated injuries. This study investigates the feasibility of classification algorithms to detect walking instability utilizing EEG signals. A 64-channel Brain Vision EEG system was used to acquire EEG signals from 13 healthy adults. Participants performed walking trials for four different stable and unstable conditions: (i) normal walking, (ii) normal walking with medial-lateral perturbation (MLP), (iii) normal walking with dual-tasking (Stroop), (iv) normal walking with center of mass visual feedback. Digital biomarkers were extracted using wavelet energy and entropies from the EEG signals. Algorithms like the ChronoNet, SVM, Random Forest, gradient boosting and recurrent neural networks (LSTM) could classify with 67 to 82% accuracy. The classification results show that it is possible to accurately classify different gait patterns (from stable to unstable) using EEG-based digital biomarkers. This study develops various machine-learning-based classification models using EEG datasets with potential applications in detecting unsteady gait neural signals and intervening by preventing falls and injuries.
Keywords: ChronoNet; EEG; fall risk; machine learning; recurrent neural networks; unstable gait.