即時無線瞌睡偵測腦機介面系統

Abstract

近年來，交通意外是一個造成駕駛死亡的至關重要原因，其中駕駛者的精神狀況不佳所造成車禍意外佔了絕大多數比例，所以開車駕駛瞌睡監控問題是我們嘗試克服之處，試著以人為方式來減少車禍發生。近年來相關的開車監控研究主要著重在使用者影像辨識上，瞳孔辨識、眨眼辨識或是偵測司機擺頭頻率，但是，這些影像相關研究存在著先天上的缺點，使用者必須正對鏡頭才能得到好的量測結果；此外為了克服此點，其他學者引進了生理參數來做為開車即時瞌睡狀況的比較依據，如心電圖、眼電圖、肌電圖或腦波圖等，較影像辨識來得直接與精確，使用者可以不必受影像定位之問題影響，本論文即對於此生理參數中腦波參數做進一步的探討，並且設計一套無線可攜式的腦波擷取系統與數位訊號處理平台並且搭配非監督式分析演算法做即時瞌睡判斷，其優勢在於可移除掉不同人、不同次測量中個別跟環境差異性。本論文藉由虛擬實境模擬環境所記錄下開車偏移量來當作瞌睡程度的參考，並與所發展的非監督式分析法的相互比對關係來證明此演算法對瞌睡程度偵測的功效與可行性，最後實現在數位訊號處理平台上。經由實際測試，可以成功在駕駛者有睡意時，利用聲音警示提醒駕駛保持清醒，確保開車時的安全。

In recent years, traffic accident is one of the critical reasons to cause deaths of drivers. Here, Drivers’ drowsiness has been implicated as a causal factor in many accidents because of the marked decline in drivers’ perception of risk and recognition of danger, and diminished vehicle handling abilities. Therefore, if the mental state of drivers can be real-time monitored directly, drowsiness detection and warning can effectively avoid disasters such as vehicle crashes in working environments. Some previous researches used non-physiological method, as eye closure with CCD image tracking, such as the pupil recognition, blink detection or identification the drivers head shaking frequency. However, for CCD image tracking, users couldn’t move for free, and the images detecting performance were easily be interfered by light. And others used physiological parameters to increase the accuracy of drowsy detection, like pulse wave analysis with neural network, the electrooculogram (EOG) and the electromyography (EMG) measurement, and the electroencephalogram (EEG). In this study, we proposed a real-time wireless brain computer interface for drowsiness detection. Here, a small, light, and portable EEG acquisition module was designed for long-time EEG monitoring. And a novel algorithm of drowsiness detection based on was also proposed to reduce the computation complexity, and was implemented in a portable DSP module. In order to estimate the level of drowsiness, a lane-keeping driving experiment was designed. The drowsiness level of drivers was indirectly assessed by the reaction time and driving trajectory under Virtual Reality Driving Simulation Environment. The advantage of this unsupervised algorithm can remove the differences between individual and environment in different people or measurements. In order to verify the accurate and feasibility of our proposed unsupervised algorithm, we compared drowsiness status estimated by driving performance with that obtained by our proposed unsupervised algorithm. The results showed that our proposed algorithm can detect driver’s drowsiness status. Finally, our system can successfully be applied in practice to prevent traffic accidents caused by drowsy driving.