臺灣博碩士論文加值系統

本論文以運用腦波偵測系統檢測駕駛者的腦波，探討專注、分心狀態及危險駕駛行為所造成的影響。實驗設計以六位駕駛騎乘摩托車進行直線行駛，繞錐，聽取不同類型的音樂和使用手機並量測駕駛員的腦波訊號，建立腦波數據資料，並透過快速傅立葉變換分析α和β頻帶波分析以獲得在腦電圖訊號的動態變化。為了進一步分析腦波狀態，本研究運用三種不同之特徵擷取方法來分析包括，R值、離散小波變換（DWT）以及短時傅立葉變換（STFT）以分析不同駕駛行為的EEG訊號來識別危險駕駛。另外本研究運用廣義回歸神經網路分類器（GRNN）和深層神經網絡（DNN）於連續之EEG訊號變化，此兩種分類器能被用於預測及分類，並於參數設置完成後透過分類可以辨識駕駛者之專注和分心的駕駛狀態，以確定危險和安全的駕駛行為。

This thesis, the use of an Electroencephalogram detection system is used to detect the driver's brain waves, explores the conditions of attention, distraction and their effects on dangerous driving behavior. Experiments designed to six test motorcycle riders were evaluated while driving straight ahead, cornering, listening to different types of music and using a cell phone. The driver's EEG signals were captured during these experiments and used to establish an EEG data and through Fast Fourier Transform (FFT) analyze alpha and beta band wave. It was used to obtain the dynamic changes in the EEG signal. In order to analyze brain waves state, this research using three different feature extraction methods analyze the signal characteristics, include R Value, Discrete Wavelet Transform (DWT), Short-Time Fourier Transform (STFT) were used to analyze the EEG signals from different driving behaviors to identify dangerous driving. Furthermore this thesis using General Regression Neural Networks (GRNN) and Deep Neuron Networks (DNN) for continuous EEG signal changes, these two classifiers can be applied for prediction and classification. After the parameters are set, the proposed classifier can categorize a driver’s concentration and distraction state behavior to identify dangerous and safe driving behavior.

ABSTRACT (CHINESE)--------------------------------------------------------- i
ABSTRACT (ENGLISH)-------------------------------------------------------- ii
ACKNOWLEDGEMENT------------------------------------------------------- iii
CONTENTS----------------------------------------------------------------------- iv
LIST OF TABLES----------------------------------------------------------------- vi
LIST OF FIGURES------------------------------------------------------------- vii
LIST OF SYMBOLS------------------------------------------------------------- ix

CHAPTER1
INTRODUCTION
1-1 Introduction of the Thesis -------------------------------------------------- 1
1-2 Literature Review------------------------------------------------------------ 3
1-3 Overview of this Thesis----------------------------------------------------- 6

CHAPTER2
PRINCIPLE OF SIGNAL ANALYSIS AND FEATURE EXTRACTION OVERVIEW
2-1 Principle of Short-time Fourier Transform------------------------------- 7
2-2 Principle of R Value--------------------------------------------------------- 9
2-3 Principle of Discrete Wavelet Transform-------------------------------- 10
CHAPTER 3
PRINCIPLE OF NEURAL NETWORK CLASSIFIERS
3-1 Principle of General Regression Neural Network--------------------- 15
3-2 Principle of Deep Neural Network--------------------------------------- 18

CHAPTER4
EXPERIMENTAL WORK AND ANALYSIS
4-1 Introduction of Experiment----------------------------------------------- 21
4-2 Experimental Arrangement and Setup----------------------------------- 25
4-3 Recognition of Extraction Feature using STFT------------------------ 30
4-4 Recognition of Extraction Feature using R value---------------------- 35
4-5 Recognition of Extraction Feature using DWT------------------------- 38
4-6 Experimental Result and Classification -------------------------------- 41

CHAPTER5
CONCLUSIONS---------------------------------------------49

REFERENCES----------------------------------------------51

[1] Amirtham, S. N., & Saraladevi, K. (2013). Analysis of attention factors and EEG brain waves of attention deficit and hyperactivity disorder (ADHD) - A Case Study Report, International Journal of Scientific and Research Publications, 3(3), 1-10.

[2] Sandra, K. L., & Barkley, R. A. (2005). Clinical utility of EEG in attention deficit hyperactivity disorder, Applied Neuropsychology, 12(2), 64-76.

[3] Bhattacharyya, S., Roy, A., Dogra, D. P., Biswas, A., Mukherjee, J., Majumdar, A. K., Majumdar, B., Mukherjee, S. & Singh, A. K. (2011). Summarization of neonatal video EEG for seizure and artifact detection, IEEE Third National Conference on Computer Vision, 134-137.

[4] Keiji, I., Takashi, M., Yasuyuki, K., & Shoogo, U. (2002). Effects of transcranial magnetic stimulation on EEG activity, IEEE Transactions on Magnetics, 38(5), 3347-3349.

[5] Rohan, H. (2015). Brain computer interface-controlling devices utilizing the alpha brain waves, International Journal of Scientific & Technology Research, 4(1), 281-285.

[6] Nishifuji, S., Sato, M., Maino, D., & Tanaka, S. (2010). Effect of acoustic stimuli and mental task on alpha, beta and gamma rhythms in brain wave, SICE Annual Conference, Taipei, 1548-1554.

[7] Crowley, K., Sliney, A., Pitt, I., & Murphy, D. (2010). Evaluating a brain-computer interface to categorize human emotional response, 10th IEEE International Conference on Advanced Learning Technologies, Cork, 276-278.

[8] Kadir, R. S. S. A., Ghazali, M. H., Murat, Z. H., Rahman, H. A. & Aris, S. A. M. (2010). The preliminary study on the effect of nasyid music and rock music on brainwave signal using EEG, 2nd International Congress on Engineering Education, Kuala Lumpur, 58-63.

[9] Yang, J. H., Mao, Z. H., Tijerina, L., Pilutti, T., Coughlin, J. F., & Feron, E. (2009). Detection of driver fatigue caused by sleep deprivation, IEEE Transactions on Systems, Man, and Cybernetics, 39(4), 694-705.

[10] Lin, C. T., Wu, R. C., Liang, S. F., Chao, W. H., Chen, Y. J., & Jung, T. P. (2005). EEG-based drowsiness estimation for safety driving using independent component analysis, IEEE Transactions on Circuits and Systems, 52(12), 2726-2738.

[11] Murugappan, M., & Murugappan, S. (2013). Human emotion recognition through short time Electroencephalogram (EEG) signals using Fast Fourier Transform (FFT), International Colloquium on Signal Processing and its Applications, Kuala Lumpur, 289-294.

[12] Verma, N. K., Rao, L. S. V. S., & Sharma, S. K. (2014). Motor imagery EEG signal classification on DWT and crosscorrelated signal features, IEEE Conference on Industrial and Information Systems, India, 13-18.
[13] Amarasinghe, K., Wijayasekara, D., & Manic, M. (2014). EEG based brain activity monitoring using Artificial Neural Networks, International Conference on Human System Interactions, Caparica, 61-66.

[14] Hasegawa, C., & Oguri, K. (2006). The effects of specific musical stimuli on driver’s drowsiness, IEEE Intelligent Transportation Systems Conference, Toronto, 17-20.

[15] Naito, K., Isioka, T., Takano, H., & Nakamura, K. (2012). Real time doze detection method using closed eye time during blink burst and isolated blinks, SICE Annual Conference, Akita, 20-23.
[16] Chen, C. H. (2014). Identification of drowsiness by detecting eye movement based on mindwave EEG signal, master’s thesis, National Taipei University of Technology, Graduate Institute of Automation Technology.

[17] Chang, B. C., Lim J. E., Kim H. J. and Seo, B. H. (2007). A study of classification of the level of sleepiness for the drowsy driving prevention, SICE Annual Conference, Kagawa, 3084-3089.

[18] Li, G., Lee, B. L., & Chung, W. Y. (2015). Smartwatch-based wearable EEG system for driver drowsiness detection, IEEE Sensors Journal, 15(12), 7169-7180.

[19] Lin, C. S. (2012). Drowsy driving detection and monitoring based on EEG signals and global position system, master’s thesis, National Chin-Yi University of Technology, Institute of Electronic Engineering.

[20] Kim, H. S., Hwang, Y., Yoon, D., Choi, W., & Park, C. H. (2014). Driver workload characteristics analysis using EEG data from an urban road, IEEE Transactions on Intelligent Transportation Systems, 15(4), 1844-1849.

[21] Lin, C. T., Chuang, C. H., Huang, C. S., Tsai, S. F., Lu, S. W., Chen, Y. H., & Ko, L. W. (2014). Wireless and wearable EEG system for evaluating driver vigilance, IEEE Transactions on Biomedical Circuits and Systems, 8(2), 165-176.

[22] Daubechies, I., Grossmann, A. & Meyer, Y. (1986). Painless non-orthogonal expansions. Journal of Mathematical Physics, 27(5) 1271-1283.

[23] Specht, D. F. (1991). A general regression network. Neural Network, 568-576.

[24] Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. & Kingsbury, B. (2012). Deep Neural Networks for acoustic modeling in speech recognition, IEEE Signal Processing Magazine, 82-97.

[25] Katona, J., Farkas, I., T. Ujbanyi, Dukan, P. & Kovari, A. (2014). Evaluation of the Neurosky mind flex EEG headset brain waves data, IEEE 12th International Symposium on Applied Machine Intelligence and Informatics, Slovakia, 23-25.

[26] NeuroSky , http://www.neurosky.com.tw/