基於腦波建置一通用型瞌睡預測系統

Abstract

本論文主要提供一套自組織式模糊類神經網路技術(Self-organizing Neural Fuzzy Inference Network)，使用腦波建構一通用型瞌睡預測系統與應用。近年來，證據顯示疲勞駕駛是造成車禍發生的重大原因之一。因此，許多關於如何監測駕駛者精神狀態，並提供警示的輔助系統(Assistant Monitoring System) ，包含人機介面(Brain Computer Interface, BCI)等研究應運而生。而開發這些輔助系統的最大難題，首在如何取得最即時(Real Time)、直接(Direct)且明顯(Significant)與駕駛者精神狀態相關的指標(Index)，以作為該系統判別瞌睡程度的依據；另外並需要同時克服在動態的實際駕駛環境中，所帶來的雜訊干擾 (Noise Disturbance)。本論文利用虛擬實境技術之動態駕車裝置，來模擬真實之駕車環境，透過高速公路行車場景的設計，結合腦電波(Electroencephalogram, EEG)分析來取得駕駛者在疲勞駕車行為下，人類的腦部認知功能與反應變化。研究發現，駕駛者的疲勞程度與其腦波的Occipital Component的能量分布(Power Spectra)有極大的關聯，並與駕駛者在高速公路行車場景所設計的車輛偏移事件實驗(Event-Related Lane Departure Experiment)的反應時間(Reaction Time)有直接的相關性。在本論文中，我們將六個參與高速公路行車場景所設計的車輛偏移事件實驗的駕駛者的腦波，透過獨立成份分析演算法(Independent Component Analysis, ICA)，分離出多個獨立訊號源後，採用Occipital Component的能量分布，加上相對應的駕駛反映時間，作為四種腦波瞌睡預測系統的模型建置(Model Construction)依據。研究發現，當使用相同駕駛者的腦波及反應時間所建立的四種反應時間估測模型(RT Estimation Models)，其系統的運作性能(Performance)運用在相同駕駛者的反應時間預測上，皆可以達到相當好的效果；然而當使用不同駕駛者的腦波所建立的四種反應時間估測模型，其系統的運作性能運用在不同駕駛者的反應時間預測上，只有所提出的自組織式模糊類神經網路的架構，仍能保持一定的性能。此獨特的優勢(p-value < 0.038)，可將此基於腦波建置的通用化瞌睡預測系統，廣泛應用在一般的生活當中。

A generalized EEG-based Neural Fuzzy system to predict driver’s drowsiness was proposed in this study. Driver’s drowsy state monitoring system has been implicated as a causal factor for the safety driving issue, especially when the driver fell asleep or distracted in driving. However, the difficulties in developing such a system are lack of significant index for detecting the driver’s drowsy state in real-time and the interference of the complicated noise in a realistic and dynamic driving environment. In our past studies, we found that the electroencephalogram (EEG) power spectrum changes were highly correlated with the driver’s behavior performance especially the occipital component. Different from presented subject-dependent drowsy state monitor systems, whose system performance may decrease rapidly when different subject applies with the drowsiness detection model constructed by others, in this study, we proposed a generalized EEG-based Self-organizing Neural Fuzzy system (SONFIN) to monitor and predict the driver’s drowsy state with the occipital area. Two drowsiness prediction models, subject-dependent and generalized cross-subject predictors, were investigated in this study for system performance analysis. Correlation coefficients and root mean square errors are showed as the experimental results and interpreted the performances of the proposed system significantly better than using other traditional Neural Networks (p-value < 0.038). Besides, the proposed EEG-based Self-organizing Neural Fuzzy system can be generalized and applied in the subjects’ independent sessions. This unique advantage can be widely used in the real-life applications.