一種新的基於高斯混合模型之行為塑模方法用於智慧型手錶之駕駛者識別

簡易檢索 / 詳目顯示

回結果列表

研究生：	楊青翰 Ching-Han Yang
論文名稱：	一種新的基於高斯混合模型之行為塑模方法用於智慧型手錶之駕駛者識別 A Novel GMM-Based Behavioral Modeling Approach for Smartwatch-Based Driver Recognition
指導教授：	梁德容 Deron Liang 張欽圳 Chin-Chun Chang
口試委員:
學位類別：	博士 Doctor
系所名稱：	資訊電機學院 - 資訊工程學系 Department of Computer Science & Information Engineering
論文出版年：	2018
畢業學年度：	106
語文別：	英文
論文頁數：	68
中文關鍵詞：	加速感測器、駕駛者認證、駕駛者識別、高斯混合模型、方位感測器、智慧型手錶
外文關鍵詞：	Accelerometer sensor, Driver authentication, Driver identification, Gaussian mixture model, Orientation sensor, Smartwatch
相關次數：	點閱：26 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

每位駕駛者都有屬於他們獨特的駕駛習慣，且通常在不同駕駛情境下，同一位駕駛者握住或操作方向盤的方式也不同。在本研究中，我們提出一種新的基於高斯混合模型塑模方法，此塑模方法可以改善傳統高斯混合模型在駕駛行為塑模上的問題。此外，我們提出的塑模方法可以應用在建構較佳的智慧型手錶感測器(如加速度計、方位感測器)之駕駛者認證系統或駕駛者識別系統上。為了驗證我們提出的方法之可行性，我們建構兩個實驗系統，分別為駕駛者認證系統與駕駛者識別系統。對於駕駛者認證系統的實驗結果顯示，在模擬環境中相等錯誤率(Equal Error Rate)可達4.46%；在真實駕駛環境中相等錯誤率達可11.35%。對於駕駛者識別系統而言，實驗結果顯示，在模擬環境中識別率可達87.16%；在真實環境中識別率可達73.07%。上述實驗結果皆比傳統高斯混合模型方法佳，因此，可以證實我們提出新的基於高斯混合模型塑模方法具有可用性。

All drivers have their own distinct driving habits, and usually hold and operate the steering wheel differently in different driving scenarios. In this study, we proposed a novel Gaussian mixture model (GMM)-based method that can improve the traditional GMM in modeling driving behavior. This new method can be applied to build a better driver authentication or identification system based on the accelerometer and orientation sensor of a smartwatch. To demonstrate the feasibility of the proposed method, we created two experimental systems that analyzes driving behavior using the built-in sensors of a smartwatch. The experimental results for driver authentication—an equal error rate (EER) of 4.46% in the simulated environment and an EER of 11.35% in the real-driving environment—confirm the feasibility of this approach. For driver identification, the experimental results indicated that the proposed approach had identification rates of 87.16% in a simulated environment and 73.07% in a real-driving environment.

摘要                                                 i
Abstract                                            ii
Table of Contents                                  iii
List of Figures                                      v
List of Tables                                     vii
1. Introduction                                      1
2. Related Work                                      5
  2.1 Driver Recognition by Driving Behavior         5
  2.2 Gaussian Mixture Model                         9
  2.3 Support Vector Machine                        10
  2.4 Stacked Generalization                        11
3. Data Collection Environments and Apparatus       13
  3.1 The Simulated Environment                     13
  3.2 The Real-driving Environment                  14
  3.3 Apparatus                                     15
4. The Proposed Driver Behavior Modeling Approach and Recognition Mechanism                               16
  4.1 Data Preprocessing                            17
  4.2 Feature Extraction                            22
    4.2.1 Base Learner 1: SVM Based on the IDM Log-
          likelihoods                               22
    4.2.2 Base Learner 2: SVM Based on Posterior
          Probabilities of Gaussian Components of
          the UDM                                   23
  4.3 Proposed Driver Behavior Model                26
  4.4 Smartwatch-based Driver Authentication and
      Identification Mechanisms                     27
    4.4.1 Application Scenario                      29
5. Experiments and Discussion                       31
  5.1 Experimental Setups                           32
    5.1.1 Data Acquisition                          32
    5.1.2 Evaluation and Performance Indices        33
  5.2 Experimental Results                          37
    5.2.1 Experiment 1: Analysis of the Number of
          Gaussian Components                       37
    5.2.2 Experiment 2: Weight Analysis of Each 
          Feature for Base Learner SIDM             38
    5.2.3 Experiment 3: Performance Evaluation of
          Driver Authentication in Both Environments40
    5.2.4 Experiment 4: Performance Evaluation of
          Driver Identification in Both Environments43
  5.3 Discussion                                    45
6. Conclusions and Future Works                     47
Appendix                                            49
Bibliography                                        51
                                

[1]FBI Uniform Crime Report, Motor Vehicle Theft, 2016. Available online: https://ucr.fbi.gov/crime-in-the-u.s/2016/crime-in-the-u.s.-2016/topic-pages/motor-vehicle-theft
[2]Shi, W.; Yang, J.; Jiang, Y.; Yang, F.; Xiong, Y. SenGuard: Passive user identification on smartphones using multiple sensors. In Proceedings of IEEE 7th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Wuhan, 2011; pp. 141-148.
[3]Clarke, N. L.; Furnell, S. M. Authenticating mobile phone users using keystroke analysis. Int. J. Inf. Security, 2006, 1-14.
[4]Saevanee, H.; Clarke, N. L.; and Furnell, S. M. Multi-modal behavioural biometric authentication for mobile devices. In Proceedings of IFIP International Information Security Conference, Heraklion, Crete, Greece, June 2012; pp. 465–474.
[5]Ribaric, S.; Ribaric, D.; Pavesic, N. Multimodal biometric user-identification system for network-based applications. IEE Proceedings - Vision, Image and Signal Processing, 15 Dec. 2003, 150, 409–416.
[6]Gartner Inc. Gartner says worldwide wearable device sales to grow 17 percent in 2017. 2017. Available online: https://www.gartner.com/newsroom/id/3790965
[7]Volvo Car Corporation. Remote S for Tesla. Available online: https://itunes.apple.com/us/app/volvo-on-call/id439635293?platform=appleWatch&
preserveScrollPosition=true#platform/appleWatch
[8]Hyundai Motor America. MyHyundai with Blue Link. Available online: https://itunes.apple.com/us/app/hyundai-blue-link/id893514610?platform=appleWatch&
preserveScrollPosition=true#platform/appleWatch
[9]Rego Apps. Remote S for Tesla. Available online: https://itunes.apple.com/us/app/remote-s-for-tesla/id991623777?platform=appleWatch&preserveScrollPosition=true&platform
=appleWatch#platform/appleWatch&platform=appleWatch
[10]Xu, C.; Pathak, P. H.; Mohapatra, P. Finger-writing with smartwatch: A case for finger and hand gesture recognition using smartwatch. In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications, Santa Fe, NM, USA, 12–13 February 2015; pp. 9–14.
[11]Gruenerbl, A.; Pirkl, G.; Monger, E.; Gobbi, M.; Lukowicz, P. Smart-watch life saver: Smart-watch interactive-feedback system for improving bystander CPR. In Proceedings of the 2015 ACM International Symposium on Wearable Computers, Osaka, Japan, 7-11 September 2015; pp. 19-26.
[12]Kalantarian, H.; Sarrafzadeh, M. Audio-based detection and evaluation of eating behavior using the smartwatch platform. Comput. Biol. Med. 2015, 65, 1–9.
[13]Pepple Smartwatch. Available online: https://www.pebble.com
[14]Fitbit. Available online: https://www.fitbit.com/au/home
[15]Liu, X.; Zhou, Z.; Diao, W.; Li, Z.; Zhang, K. When good becomes evil: Keystroke inference with smartwatch. In Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, Denver, Colorado, USA, 12-16 October 2015; pp. 1273-1285.
[16]Wang, C.; Guo, X.; Wang, Y.; Chen, Y.; Liu, B. Friend or foe?: Your wearable devices reveal your personal PIN. In Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security, Xi'an, China, 30 May - 03 June 2016; pp. 189-200.
[17]Gutierrez, M. A.; Fast, M. L.; Ngu, A. H.; Gao, B. J. Real-time prediction of blood alcohol content using smartwatch sensor data. In Proceedings of International Conference for Smart Health (ICSH 2015), Phoenix, Arizona, USA, 17-18 November 2015; pp. 175-186.
[18]Ngu, A.; Wu, Y.; Zare, H.; Polican, A.; Yarbrough, B.; Yao, L. Fall detection using smartwatch sensor data with accessor architecture. In Proceedings of International Conference for Smart Health (ICSH 2017), Hong Kong, China, 26-27 June 2017; pp. 81-93.
[19]Igarashi, K.; Takeda, K.; Itakura, F.; Abut, H. Is our driving behavior unique? In DSP for In-Vehicle and Mobile Systems; Springer, Boston, MA, 2005; pp. 257-274. ISBN 978-0-387-22978-2.
[20]Igarashi, K.; Miyajima, C.; Itou, K.; Takeda, K.; Itakura, F.; Abut, H. Biometric identification using driving behavioral signals. In Proceedings of IEEE International Conference on Multimedia and Expo, Taipei, Taiwan, 27–30 June 2004; 1, pp. 65–68.
[21]Miyajima, C.; Nishiwaki, Y.; Ozawa, K.; Wakita, T.; Itou, K.; Takeda, K.; Itakura, F. Driver modeling based on driving behavior and its evaluation on driver identification. Proc. IEEE 2007, 95, 427–437.
[22]Wahab, A.; Quek, C.; Tan, C.-K.; Takeda, K. Driving profile modeling and recognition based on soft computing approach. IEEE Trans. Neural Networks, April 2009, 20, 563–582.
[23]Qian, H.; Ou, Y.; Wu, X.; Meng, X.; Xu, Y. Support vector machine for behavior-based driver identification system. Journal of Robotics., 2010, 2010.
[24]Riener, A.; Ferscha, A. Supporting implicit human-to-vehicle interaction: driver identification from sitting postures. In Proceedings of the 1st Annual International Symposium on Vehicular Computing Systems (ISVCS 2008), Dublin, Ireland, 22-24 July 2008.
[25]Chen, R.; She, M. F.; Sun, X.; Kong, L.; Wu, Y. Driver recognition based on dynamic handgrip pattern on steering wheel. In Proceedings of 12th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, Sydney, Australia, July 2011.
[26]Yang, C.-H.; Liang, D.; Chang, C.-C.; Lin, C.-C. A new non-intrusive authentication method based on dynamics of driver's upper body joint angles. In Proceedings of 12th Annual IEEE Consumer Communications and Networking Conference (CCNC), Las Vegas, NV, 2015; pp. 341-346.
[27]Rawassizadeh, R.; Price, B.; Petre, M. Wearables: Has the age of smartwatches finally arrived? ACM Commun., 2015, 58, 45–47.
[28]Liang, X.; Kotz, D. AuthoRing: Wearable user-presence authentication. In Proceedings of the 2017 Workshop on Wearable Systems and Applications, Niagara Falls, New York, USA, 19 June 2017; pp. 5-10.
[29]Lewis, A.; Li, Y.; Xie, M. Real time motion-based authentication for smartwatch. In Proceedings of the 2016 IEEE Conference on Communications and Network Security, Philadelphia, PA, 17-19 October 2016; pp. 380-381.
[30]Lee, B.-G.; Lee, B.-L.; Chung, W.-Y. Wristband-type driver vigilance monitoring system using smartwatch. IEEE Sensors J., June 2015, 15, 5624–5633.
[31]Lee, B.-L.; Lee, B.-G.; Chung, W.-Y. Standalone wearable driver drowsiness detection system in a smartwatch. IEEE Sens. J., July 2016, 16, 5444–5451.
[32]Yang, C.-H.; Liang, D.; Chang, C.-C. A novel driver identification method using wearables. In Proceedings of the 13th IEEE Annual Consumer Communications & Networking Conference, Las Vegas, NV, 9-12 January 2016; pp. 1–5.
[33]Wolpert, D. Stacked generalization. Neural Networks, 1992, 5, 241–259.
[34]Kawaguchi, N.; Matsubara, S.; Takeda, K.; Itakura, F. Multimedia data collection of in-car speech communication. In Proceedings of the 7th European Conference on Speech Communication and Technology, September 2001; pp. 2027–2030.
[35]Douglas, J.L.; Junqua, J.C.; Kotropoulos, C.; Kuhn, R.; Perronnin, F.; Pitas, I. Recent Advantages in Biometric Person Authentication. In Proceedings of Acoustics, Speech, and Signal Processing (ICASSP), May 2002, pp.4060-4063.
[36]Reynolds D. A.; Rose, R. C. Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech and Audio Processing, Jan 1995, 3, 72-83.
[37]Vapnik, V. N. The nature of statistical learning theory. Springer-Verlag, 1995.
[38]Burges, C. J. C. A tutorial on support vector machines for pattern recognition. Knowledge Discovery and Data Mining, 1998, 2, 121–167.
[39]Cristianini, N.; Shawe-Taylor, J. Support vector machines and other kernel-based learning methods. Cambridge University Press, 2000.
[40]Müller, K. R.; Mika, S.; Rätsch, G.; Tsuda, K.; Schölkopf, B. An introduction to kernel-based learning algorithms. IEEE Trans. on Neural Networks, 2001, 12, 181–202.
[41]Schölkopf, B; Smola, A. J. Learning with Kernels. MIT Press, 2002.
[42]Herbrich, R. Learning Kernel Classifiers. MIT Press, 2002.
[43]Guyon, I.; Weston, J.; Barnhill, S.; Vapnik, V. Gene selection for cancer classification using support vector machines. J. Machine Learning Res., 2003, 3, 1439-1461.
[44]Forward Development Group LLC. City Car Driving - Car Driving Simulator, PC Game. Available online: http://citycardriving.com
[45]Google Inc. Google Map Street View. 2018. Available online: https://www.google.com.tw/maps/@24.9674195,121.1884624,3a,75y,91.68h,87.48t/data=!3m7!1e1!3m5!1sGZVySxRXvBuUBVLw1Esipg!2e0!3e11!7i13312!8i6656?hl=en&authuser=0
[46]Logitech International S.A. Logitech G27 racing wheel.
Available online: http://support.logitech.com/en_us/product/g27-racing-wheel/specs
[47]Logitech International S.A. Logitech steering wheel SDK.
Available online: https://www.logitechg.com/en-us/developers
[48]Android Developers. SensorEvent. Available online: https://developer.android.com/reference/android/hardware/SensorEvent.html
[49]Furui, S. Speaker independent isolated word recognition using dynamic features of the speech spectrum. IEEE Trans. Acoustics, Speech Signal Process, 1986, 34, 52-59.
[50]Wang, L.; Ning, H.; Tan, T.; Hu, W. Fusion of static and dynamic body biometrics for gait recognition. IEEE Trans. Circuits Syst. Video Technol., February 2004, 14, 149–158.
[51]Ayache, S.; Quénot, G.; Gensel, J. Classifier fusion for SVM-based multimedia semantic indexing. In Proceedings of the 29th European conference on IR research, Rome, Italy, 2-5 April 2007; pp. 494-504.
[52]Znaidia, A.; Shabou, A.; Popescu, A.; Le Borgne, H.; Hudelot, C. Multimodal feature generation framework for semantic image classification. In Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, Hong Kong, China, 5-8 June 2012.
[53]Chang, C.-C.; Lin, C.-J. LIBSVM: A library for support vector machines. ACM Trans. Intel. Syst. Technol. (TIST) 2011, 2.
[54]United Nations. Household size and composition around the world 2017. Available online: http://www.un.org/en/development/desa/population/publications/pdf/ageing/household_size_and_composition_around_the_world_2017_data_booklet.pdf
[55]Martin, A.; Doddington, G.R.; Kamm, T.; Ordowski, M.; Przybocki, M. The DET curve in assessment of detection task performance. In Proceedings of the 5th European Conference on Speech Communication and Technology, Rhodes, Greece, 22–25 September 1997; pp. 1895–1898.
[56]Fui, L.H.; Isa, D. Feature selection based on minimizing the area under the detection error tradeoff curve. In Modeling Applications and Theoretical Innovations in Interdisciplinary Evolutionary Computation; Hong, W.-C., Ed.; IGI Global: Hershey, PA, USA, 2013; pp. 16–31, ISBN 978-1-46663-628-6.
[57]Bimbot, F.; Bonastre, J.-F.; Fredouille, C.; Gravier, G.; Magrin-Chagnolleau, I.; Meignier, S.; Merlin, T.; Ortega-Garcia, J.; Petrovska-Delacretaz, D.; Reynolds, D.-A. A tutorial on text-independent speaker verification. J. Appl. Signal Process. 2004, 2004, 430–451.
[58]Thiffault, P.; Bergeron, J. Monotony of road environment and driver fatigue: A simulator study. Accid. Anal. Prevent 2003, 35, 381–391.
[59]Gafurov, D; Helkala, K; Søndrol, T. Biometric gait authentication using accelerometer sensor. J. Comput 2006, 1, 51–59.
[60]Bergadano, F.; Guneti, D.; Picardi, C. User authentication through keystroke dynamics. ACM Trans. Inf. Syst. Secur. 2002, 5, 367–397.
[61]Ahmed, A.A.E.; Traore, I. A new biometric technology based on mouse dynamics. IEEE Trans. Dependable Secure Comput. 2007, 4, 165–179.
[62]Lin, C.-C.; Chang, C.-C.; Liang, D. A novel non-intrusive user authentication method based on touchscreen of smartphones. In Proceedings of the 2013 International Symposium on Biometrics and Security Technologies, Chengdu, 2–5 July 2013; pp. 212–216.
[63]Tappert, C. C.; Cha, S.-H.; Villani, M.; Zack, R. S. A keystroke biometric system for long-text input. Int. J. Inf. Secur. Privacy, 2010, 4, 32-60.

簡易檢索 / 詳目顯示

相關論文