Presentation is loading. Please wait.

Presentation is loading. Please wait.

Presented by : Bo-Yang Hou Adviser : Shih-Chung Chen Chairman : Hung-Chi Yang Date : 2012/12/19 Mervyn V.M. Yeo, Xiaoping Li, Kaiquan Shen, Einar P.V.

Similar presentations


Presentation on theme: "Presented by : Bo-Yang Hou Adviser : Shih-Chung Chen Chairman : Hung-Chi Yang Date : 2012/12/19 Mervyn V.M. Yeo, Xiaoping Li, Kaiquan Shen, Einar P.V."— Presentation transcript:

1 Presented by : Bo-Yang Hou Adviser : Shih-Chung Chen Chairman : Hung-Chi Yang Date : 2012/12/19 Mervyn V.M. Yeo, Xiaoping Li, Kaiquan Shen, Einar P.V. Wilder-Smith M.V.M. Yeo et al. / Safety Science 47 (2009) 115–124 2012/12/191

2 The objective of this study is to establish an automatic method of distinguishing between alert and drowsy states by using a recently established signal pattern recognition technology to develop a reliable detection system of drowsiness for driving safety. 2012/12/192

3 3 引用於:支持向量機教學文件 ( 中文版 ) 李根逸 台灣大學通訊與多媒體實驗室

4 1. Support Vector Machines (SVM)  To understand the essence of SVM classification, one needs only to grasp four basic concepts: (I) The separating hyperplane (II) The maximum-margin hyperplane (III) The soft margin (IV) The kernel function 2012/12/194

5 2. Participants  The recruitment of human subjects for this study was approved by the National University of Singapore (NUS) ethical committee.  The Epworth Sleepiness Scale was used to prescreen and determine the level of daytime sleepiness. 2012/12/195

6 3. EEG equipment and data collection  The EEG equipment used was a 32-channel Medtronic PL-Winsor 2.35 system, with a sampling frequency of 256 Hz, an integrated low pass (cut-off frequency of 35 Hz) and a time constant of 0.30 s.  Full head mapping was done using the standard 10/20 system of electrode placement (Jasper, 1958). 2012/12/196

7 The SVM program was also able to predict the transition from alertness to drowsiness reliably in over 90% of data samples. This study shows that automatic analysis and detection of drowsiness EEG is possible by SVM and SVM is a good candidate for developing pre-emptive automatic drowsiness detection systems for driving safety. 2012/12/197

8 [1] Mervyn V.M. Yeo, Xiaoping Li, Kaiquan Shen, Einar P.V. Wilder- Smith, Can SVM be used for automatic EEG detection of drowsiness during car driving?, M.V.M. Yeo et al. / Safety Science 47 (2009) 115–124 [2] William S Noble, What is a support vector machine?, NATURE BIOTECHNOLOGY VOLUME 24 NUMBER 12 DECEMBER 2006 1565-1567 [3] Kristin P.Bennett & Colin Campbell,Support Vector Machines: Hype or hallelujh?,SIGKDD Explorations.Copyright ©2000ACM SIGKDD,December2000,Volune 2,Issue – page13 [4] 支持向量機教學文件 ( 中文版 ) 李根逸 台灣大學通訊與多 媒體實驗室 [5] 勞工安全衛生研究所, 認識睡眠呼吸中止症, http://www.iosh.gov.tw/Print.aspx?cnid=12&P=528 2012/12/198


Download ppt "Presented by : Bo-Yang Hou Adviser : Shih-Chung Chen Chairman : Hung-Chi Yang Date : 2012/12/19 Mervyn V.M. Yeo, Xiaoping Li, Kaiquan Shen, Einar P.V."

Similar presentations


Ads by Google