Android手持裝置利用心率信號之睡意偵測系統

駕駛有睡意經常是造成交通事故之原因之一，但許多駕駛對自己產生睡意之狀況卻缺乏自覺性，因此有必要在駕駛困倦的狀態時適時發出警訊以提醒他注意。醫學相關研究發現：當駕駛有睡意時副交感神經會主導其它交感神經系統活動，由於心電圖的心率變異度中之高頻成份和副交感神經之活動有正相關，所以由心率心率變異度分析將可以有效探究駕駛是否產生睡意。本論文目的在建構一個睡意偵測之雛形系統，此系統會利用感測器取得人的心率資訊，將所得資料經由藍芽傳送至行動裝置作各種分析與呈現（例如：心跳狀況、電子心電圖），再由所得之電子心電圖做取樣降階(decimation)和漢明視窗(Hamming window)以降低運算複雜度，再分段執行快速傅立葉轉換做心率變異度之高低頻成份分析，若此頻譜分析結果證明「低頻/高頻功率比」有明顯下降趨勢，就可以代表此人已由清醒狀態轉移至瞌睡或睡著之狀態了。本雛形系統並在Android作業系統的智慧型手機上實現，也經過多次實際人體測試，最後由實驗結果推導出本論文之結論。

關鍵字

睡意偵測；心率變異度；心電圖；快速傅立葉轉換

並列摘要

Driver drowsiness is a major cause of traffic crashes. The problem lies in the fact that a driver is usually unaware of the on-set of drowsiness. It is therefore necessary to alert the driver when he goes into the drowsy state. Related researches have shown that drowsiness occurs when the parasympathetic nervous system predominates over others, since the high frequency (HF) components of heart rate variability (HRV) on an electrocardiogram (ECG) is closely related with the parasympathetic nervous activity, it is reasonable to evaluate drowsiness based on the HRV analysis. So in this research the driver’s drowsiness is detected using heart beat rate. This thesis is trying to build a prototype of drowsiness detection system. A sensor is used to detect the ECG signal of the driver and the signal will be sent to the android phone through the Bluetooth, with help of programmable application, developed using android SDK. The received ECG signals are processed in the android mobile. Signal-processing techniques such as Hamming window and FFT is applied. From the FFT the power spectrum is found and the low frequency (LF) to high frequency (HF) power ratio is calculated. The power ratio shows decreasing trends as the subject goes from awake to drowsy state.

並列關鍵字

Drowsiness detection ； heart beat variation ； ECG analysis ； FFT

參考文獻

1. O.Tuner, L. Guvence, F. Coskun and E. Karsligil, "Vision based lane keeping assistance control triggered by a driver inattention monitor," IEEE International Conference on Systems Man and Cybernetics (SMC), 2010, pp. 289-297.

6. Eclipse. [Online]. Available: http://www.eclipse.org/.

7. W. Qiong, Y. Jingyu, R. Mingwu and Z. Yujie, "Driver Fatigue Detection: A Survey," The Sixth World Congress on Intelligent Control and Automation, vol. 2, 2006, pp. 8587-8591.

8. A. Picot, S. Charbonnier and A. Caplier, "On-Line Detection of Drowsiness Using Brain and Visual Information," IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 42, no. 3, 2012, pp. 764-775.

9. G.D. Furman, A. Baharav, C. Cahan and S. Akselrod, "Early detection of falling asleep at the wheel: A Heart Rate Variability approach," Computers in Cardiology, vol. 35, 2008, pp. 1109-1112.

國際替代計量

Android手持裝置利用心率信號之睡意偵測系統

全文下載

主題瀏覽