即時獨立成分分析演算法應用於無線嵌入式腦機介面

Abstract

為了增進腦機介面(Brain-Computer Interface, BCI)使其可適用於真實的生活環境，線上(online)人為校正、特徵擷取、圖像事別等訊號處理技術是不可或缺的。因此腦機介面系統必須是個便利的大小、堅固耐用、重量輕且低功率消耗來達到可穿戴、可攜性與持久性的需求。本論文提出一個視窗移動(Moving-Window)的獨立成分分析法(Independent Component Analysis)並應用於一個以電池供應電源、微小化的嵌入式腦機介面。本論文也藉由模擬訊號與真實腦波訊號測試此嵌入式腦機介面。且經由實驗結果指出視窗移動的獨立成分演算法的分離效果與同樣離線(offline)演算法，提出獨立成分分析演算法在腦機介面上即時分析的可行性。為了展示可穿戴式嵌入式腦機介面的可行性，本論文也實現了移動與平均(Moving-average)頻譜分析於獨分成分分析結果的成分作用來達到即時並連續偵測受測者的任務表現。

Online artifact correction, feature extraction, and pattern recognition are essential to advance the brain computer interface (BCI) technology so as to be practical for real-world applications. The BCI system should also be a convenient size, rugged, lightweight, and have low power consumption to meet the requirements of wearability, portability, and durability. This thesis proposes and implements a moving-windowed Independent Component Analysis (ICA) on a battery-powered, miniature, embedded BCI. This thesis also tests the embedded BCI on simulated and real EEG signals. Experimental results indicated that the efficacy of the window-based ICA decomposition is comparable with that of the offline version of the same algorithm, suggesting the feasibility of ICA for real-time analysis of EEG in a BCI. To demonstrate the feasibility of the wearable embedded BCI, this thesis also implements a moving-average spectral analysis to the resultant component activations to continuously estimate subject’s task performance in near real time.