透過智慧手錶轉換提取駕駛行為信號的特徵以提升駕駛安全性

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：23

、訪客IP：3.149.24.115

姓名

款撒莉(Rekyan Regasari Mardi Putri) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

透過智慧手錶轉換提取駕駛行為信號的特徵以提升駕駛安全性
(Safety Driving Improvement Using Transformation to Extract Features on Smartwatch-based Driving Behavior Signals)

相關論文

★ 基於台灣上市公司長期和短期行為的財務困境預測	★ 非侵入式智慧型手機使用者生物識別機制之行為變化快速適應
★ 以穿戴單一智慧型手錶利用多種建模策略偵測操縱方向盤之手部位置	★ 透過特徵排名剔除弱特徵以防止智慧型手機的行為生物身分認證系統受到模擬攻擊

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2027-1-31以後開放)

摘要(中)

駕駛安全至今仍然是一個重要問題，尤其是在準確識別駕駛者手部位置和分類車輛運動以預防事故發生。本論文聚焦於兩項關鍵研究任務。第一項任務是探索如何利用單一智慧手錶捕捉雙手資訊的潛力，其困難點在於智慧手錶只能有效檢測佩戴它的那隻手。我們的目標是實現單一智慧手錶的手部位置準確檢測，達到與雙智慧手錶相當的表現。第二項任務是解決從模擬數據和真實數據中提取一致性特徵的難題，以建立適用於真實駕駛的車輛運動分類模型。雖然真實數據更能反映行為分析，但其收集過程具有一定危險性；相較之下，模擬數據更安全，但與真實數據之間存在差距。我們的目標是開發一種基於模擬且更安全的車輛運動分類方法，並縮小模擬數據與真實數據之間的差距。為實現這兩個目標，一個關鍵步驟是發現精確的特徵提取方法。我們提出的方法利用希爾伯特-黃轉換（HHT）從單一智慧手錶提取雙手的特徵，並結合主成分分析（PCA）和線性判別分析（LDA）從模擬數據中提取一致性特徵，用於車輛運動分類。本研究的兩大貢獻為：提升手部位置檢測準確率，讓單一智慧手錶達到98.29%的準確率，超過雙智慧手錶的97%；以及提出一種創新、安全且基於模擬模型的數據收集解決方案，並應用於真實數據，將車輛運動分類準確率相比原始模擬數據提升了29.74%。

摘要(英)

Driving safety remains a critical issue, especially in terms of accurately identifying hand positions and classifying car movements for accident prevention. This thesis presents two essential research assignments. First is motivated by the potential of a single smartwatch to capture both hands which is challenging because smartwatches are only effective on the hand wearing it. The objective is to achieve competitive hand position detection accuracy with a single smartwatch, comparable to the performance of dual smartwatch. The second is to address the challenge of extracting consistent features from simulation and real data to build a car movement classification model applicable to real-world driving. Real data is more relevant for behavior analysis, but it is dangerous to collect, whereas simulation data, though safer, introduces a gap with real-world consistency. The objective is to develop a safer, simulation-based approach for car movement classification. An important phase to achieve both objectives is to discover precise feature extraction. Our proposed method leverages Hilbert-Huang Transform (HHT) to extract features from both hands using a single smartwatch and uses PCA and LDA to derive consistent features from simulation data for car movement classification. The two contributions are: improvement in hand position detection accuracy, achieving 98.29% with one smartwatch, surpassing the 97% accuracy achieved with two smartwatches; a novel solution for safer data collection using simulation models applied to real data, improving car movement classification accuracy by 29.74% over raw simulation data.

關鍵字(中)

★ 特徵提取
★ 智慧手錶
★ 手部位置檢測
★ 車輛運動分類
★ 希爾伯特-黃轉換
★ 主成分分析
★ 線性判別分析

關鍵字(英)

★ feature extraction
★ smartwatch
★ hand position detection
★ car movement classification
★ Hilbert Huang Transform
★ Principal Component Analysis
★ Linear Discriminant Analysis

論文目次

Safety Driving Improvement Using Transformation to Extract Features on Smartwatch-based Driving Behavior Signals vi
摘要 vi
Safety Driving Improvement Using Transformation to Extract Features on Smartwatch-based Driving Behavior Signals vii
Abstract vii
Table of Content viii
List of Figures xi
List of Tables xiv
1 Introduction 1
1.1 Background 2
1.2 Motivation 12
1.3 Problem Definition 13
1.4 Contribution 15
2. Related Work 17
3 Propose I: Driver′s Hands Position Detection 21
3.1 Problem definition 21
3.2 Proposed Method 21
3.2.1 System Architecture 21
3.2.2 Data Collection 22
3.2.3 Pre-processing 24
3.2.4 Feature Extraction 26
3.2.5 Training and Testing Phase 28
3.3 Experiment Designs and Results 29
3.3.1 Experiment Design 1: Comparison of Stationary and Moving Environments 30
3.4.1.1 Experiment design 30
3.4.1.2 Experiment Results 31
3.3.2 Experiment Design 2: Performance Evaluation of Different Features Using Universal Model 34
3.4.2.1 Experiment Design 34
3.4.2.2 Experiment Result 35
3.3.3 Experiment Design 3: Data Distribution Analysis of the Hand Not Wearing Smartwatch 36
3.4.3.1 Experiment Design 36
3.4.3.2 Experiment Result 37
3.3.4 Experiment Design 4: Performance of the Individual Model 38
3.4.4.1 Experiment Design 38
3.4.4.2 Experiment Result 39
3.3.5 Experiment Design 5: Best feature analysis 44
3.4.5.1 Experiment Design 44
3.4.5.2 Experiment Result 45
3.3.6 Experiment Design 6: Comparison of Old-Car and New-Car Environment 45
3.4.6.1 Experiment Design 45
3.4.6.2 Experiment Result 46
4 Proposed II: Real Driving Behavior Classification Models Using Simulation Data 48
4.2 Problem Definition 48
4.3 Proposed Method 48
4.3.1 System Architecture 48
4.3.2 Data Collection 49
4.3.3 Preprocessing 51
Data cleansing 52
Data centering 53
4.3.4 Feature Extraction 54
Feature Extraction with Principal Component Analysis 54
Feature Extraction with Linear Discriminant Analysis 55
Feature extraction: How the Transformation Works 56
4.4 Experiment Design and Experiment Result 59
4.4.1 Experiment Design 1: PCA and LDA transformation signal distribution analysis 59
4.4.1.1 Experiment Design 59
4.4.1.2 Experiment Result 61
4.4.2 Experiment Design 2: Performance evaluation of the proposed method compared to baseline 62
4.4.2.1 Experiment Design 62
4.4.2.2 Experiment Result 64
4.4.3 Experiment Design 3: Performance comparison with similar purpose study 68
4.4.3.1 Experiment Design 68
4.4.3.2 Experiment Result 69
5 Conclusion, Limitation, and Future Work 71
5.2 Conclusion 71
5.3 Limitation 72
5.4 Future Works 72
References 74
Glossarium 81

參考文獻

[1] Kumar, Naveen (2024). Smartwatch Statistics (2024): Market & Sales Data, DemandSage, [online]. Available: https://www.demandsage.com/smartwatch-statistics/.
[2] Wang, Jianqiang & Wu, Jian & Li, Yang. (2015). The Driving Safety Field Based on Driver–Vehicle–Road Interactions. IEEE Transactions on Intelligent Transportation Systems. 16. 1-12. 10.1109/TITS.2015.2401837.
[3] Elsagheer, Samir & Alshalfan, Khaled & Al-Hagery, Mohammed & Othman, Mohamed. (2022). Safe Driving Distance and Speed for Collision Avoidance in Connected Vehicles. Sensors. 22. 7051. 10.3390/s22187051.
[4] Chen, H., et al. Drive Safe Inspector: A Wearable-Based Fine-Grained Technique for Driver Hand Position Detection. in 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, United Arab Emirates. 2018. IEEE.
[5] Gu, Y., et al. Driver Hand Activity Recognition using NIR Camera and Deep Neural Network. in 2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech). 2022. Osaka, Japan: IEEE.
[6] Bi, C., et al. SafeWatch: A Wearable Hand Motion Tracking System for Improving Driving Safety. in 2017 IEEE/ACM Second International Conference on Internet-of-Things Design and Implementation (IoTDI). 2017. Pittsburgh, PA, USA: IEEE. DOI. DOI: 10.1145/3054977.3054979.
[7] Li, Brian & Li, Emma & Li, Hui. (2021). Aggressive Driving Detection and Alert System Leveraging Current Signal Light Infrastructure. Journal of Student Research. 10. 10.47611/jsrhs. v10i4.1961.
[8] Bouhsissin, Soukaina & Sael, Nawal & Benabbou, Faouzia. (2023). Driver Behavior Classification: A Systematic Literature Review. IEEE Access. PP. 10.1109/ACCESS.2023.3243865.
[9] Siregar, Martha & Tjahjono, Tri & Nahry,. (2021). SPEED CHANGE AND TRAFFIC SAFETY POWER MODEL FOR INTER-URBAN ROADS. Journal of Applied Engineering Science. 19. 1-9. 10.5937/jaes0-29180.
[10] Jiang, L., et al., SafeDrive: Detecting Distracted Driving Behaviors Using Wrist-Worn Devices. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018. 1(4): p. 1-22.
[11] Gorzela?czyk, Piotr & Kliszewski, ?ukasz & Pi?tkowski, Piotr. (2023). Analysis of the impact of the technical condition of vehicles on road safety. 100. 2023. 10.14669/AM/168680.
[12] Rao, D. & Rao, M. & Rao, Vaddi. (2023). Assessment of Road Condition: Traffic Safety Requirement. EAI Endorsed Transactions on Energy Web. 10. 10.4108/ew.4472.
[13] Kumar, Ajay & Kumar, Pappu & Kumar, Vivek. (2023). Effects of Road Conditions, Traffic Patterns, and Human-Made Features on Road Safety: Review Article. 2. 20-27. 10.5281/zenodo.8220920.
[14] Setiawan, Budi & Kovacs, Mate & Serdult, Uwe & Kryssanov, Victor. (2022). Semantic Segmentation on Smartphone Motion Sensor Data for Road Surface Monitoring. Procedia Computer Science. 204. 346-353. 10.1016/j.procs.2022.08.042.
[15] Batrakova, Angelica & Gredasova, Olga. (2016). Influence of Road Conditions on Traffic Safety. Procedia Engineering. 134. 196-204. 10.1016/j.proeng.2016.01.060.
[16] Li S, Wang S, Wang P. a Small Object Detection Algorithm for Traffic Signs Based on Improved YOLOv7. Sensors. 2023; 23(16):7145. https://doi.org/10.3390/s23167145.
[17] Yugam Bajaj and Shallu Bashambu, “Traffic Signs Detection Using Machine Learning Algorithms”, International Journal for Modern Trends in Science and Technology, 6(11): 109-112, 2020.
[18] Liu Z, Yan J, Zhang J. Research on a Recognition Algorithm for Traffic Signs in Foggy Environments Based on Image Defogging and Transformer. Sensors. 2024; 24(13):4370.
[19] Transportation, D., Using Efficient Steering Techniques, in https://www.nhtsa.gov/document/using-efficient-steering-techniques. 2017, National Highway Traffic Safety Administration: Washington DC.
[20] US Department of Transportation, Transportation Statistics Annual Report 2017. 2017, Bureau of Transportation Statistics: Washington DC.
[21] Katya, Y., S. Alur, and S. Dwivedi, Safe Driving by Detecting Lane Discipline and Driver Drowsiness. IEEE International Conference on Advanced Communication Control and Computing Technologies (ICACCCT), 2014.
[22] Wathiq, O. and B.D. Ambudkar, Optimized Driver Safety through Driver Fatigue Detection Methods. International Conference on Trends in Electronics and Informatics (ICEI) 2017, 2017.
[23] Mantouka, E., et al., Smartphone sensing for understanding driving behavior: Current practice and challenges. International Journal of Transportation Science and Technology, 2021. 10(3): p. 266-282.
[24] Abosaq, H.A., et al., Unusual Driver Behavior Detection in Videos Using Deep Learning Models. Sensors (Basel), 2022. 23(1).
[25] Baek, J.W., et al. Real-Time Drowsiness Detection Algorithm for Driver State Monitoring Systems. in 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN). 2018. Prague, Czech Republic: IEEE.
[26] Ding, M., T. Suzuki, and T. Ogasawara, Estimation of Driver’s Posture using Pressure Distribution Sensors in Driving Simulator and On-Road Experiment, in IEEE International Conference on Cyborg and Bionic Systems. 2017, IEEE Xplore Beijing.
[27] Rahim, H.A., et al. Grasp hand approach to detect the attentiveness and fatigue of driver via vibration system. in 2010 6th International Colloquium on Signal Processing & its applications. 2010. Malacca, Malaysia: IEEE.
[28] X. Zhao, Y. Ju, H. Li, C. Zhang, and J. Ma, “Safety of raised pavement markers in freeway tunnels based on driving behavior,” Accident Analysis Prevention, 2020, https://doi.org/10.1016/j.aap.2020.105708.
[29] Shirazi, M.M. and A.B. Rad, Detection of Intoxicated Drivers Using Online System Identification of Steering Behavior. IEEE Transactions on Intelligent Transportation Systems, 2014. 15(4): p. 1738-1747.
[30] Kashevnik, A., I. Lashkov, and A. Gurtov, Methodology and Mobile Application for Driver Behavior Analysis and Accident Prevention. IEEE Transactions on Intelligent Transportation Systems, 2020. 21(6): p. 2427-2436.
[31] Hu, J., et al., Abnormal Driving Detection Based on Normalized Driving Behavior. IEEE Transactions on Vehicular Technology, 2017. 66(8): p. 6645-6652.
[32] Ji, Y. and H. Lee, Event-Based Anomaly Detection Using a One-Class SVM for a Hybrid Electric Vehicle. IEEE Transactions on Vehicular Technology, 2022. 71(8): p. 6032-6043.
[33] Sama, K., et al., Extracting Human-Like Driving Behaviors from Expert Driver Data Using Deep Learning. IEEE Transactions on Vehicular Technology, 2020. 69(9): p. 9315-9329.
[34] Liu, P., X. Qiu, and X. Huang, Adversarial Multi-task Learning for Text Classification, in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017. p. 1-10.
[35] Hossain, S.M.E. and G. Chetty, Human Identity Verification by Using Physiological and Behavioural Biometric Traits. International Journal of Bioscience, Biochemistry and Bioinformatics, 2011: p. 199-205.
[36] Bengio, S. and J. Mariethoz. Biometric Person Authentication Is a Multiple Classifier Problem. at 7th International Workshop, MCS 2007. 2007. Prague, Czech Republic: Springer.
[37] Alsaadi, Israa. (2021). Study On Most Popular Behavioral Biometrics, Advantages, Disadvantages and Recent Applications: A Review. International Journal of Scientific & Technology Research. 10. 15-21.
[38] Yampolskiy, Roman & Govindaraju, Venu. (2009). Taxonomy of Behavioural Biometrics. Behavioral Biometrics for Human Identification: Intelligent Applications. 10.4018/978-1-60566-725-6.ch001.
[39] Igarashi, K., et al., Biometric identification using driving behavioral signals, in 2004 IEEE International Conference on Multimedia and Expo (ICME). 2004, IEEE: Taipei, Taiwan. p. 65-68.
[40] Miyajima, C., et al., Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification. Proceedings of the IEEE, 2007. 95(2): p. 427-437.
[41] Wahab, A., et al., Driving profile modeling and recognition based on soft computing approach. IEEE Trans Neural Netw, 2009. 20(4): p. 563-82.
[42] Qian, H., et al., Support Vector Machine for Behavior-Based Driver Identification System. Journal of Robotics, 2010. 2010: p. 1-11.
[43] Lee, B.-G., B.-L. Lee, and W.-Y. Chung, Wristband-Type Driver Vigilance Monitoring System Using Smartwatch. IEEE Sensors Journal, 2015. 15(10): p. 5624-5633.
[44] Chen, R., et al., Driver Recognition Based on Dynamic Handgrip Pattern on Steeling Wheel, in 2011 12th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. 2011, IEEE. p. 107-112.
[45] Riener, A. and A. Ferscha, Supporting Implicit Human-to-Vehicle Interaction: Driver Identification from Sitting Postures, in Proceedings of the First Annual International Symposium on Vehicular Computing Systems. 2008.
[46] Lee, B.-L., B.-G. Lee, and W.-Y. Chung, Standalone Wearable Driver Drowsiness Detection System in a Smartwatch. IEEE Sensors Journal, 2016. 16(13): p. 5444-5451.
[47] Yang, C.H., C.C. Chang, and D. Liang, A Novel GMM-Based Behavioral Modeling Approach for Smartwatch-Based Driver Authentication. Sensors (Basel), 2018. 18(4).
[48] Li, Z., et al., Driver identification in intelligent vehicle systems using machine learning algorithms. IET Intelligent Transport Systems, 2018. 13(1): p. 40-47.
[49] Chen, J., Z.C. Wu, and J. Zhang, Driver identification based on hidden feature extraction by using adaptive nonnegativity-constrained autoencoder. Applied Soft Computing, 2019. 74: p. 1-9.
[50] Wang, W., J. Xi, and J.K. Hedrick, A Learning-Based Personalized Driver Model Using Bounded Generalized Gaussian Mixture Models. IEEE Transactions on Vehicular Technology, 2019. 68(12): p. 11679-11690.
[51] Rahim, M.A., et al., Who is Driving? Event-Driven Driver Identification and Impostor Detection Through Support Vector Machine. IEEE Sensors Journal, 2020. 20(12): p. 6552-6559.
[52] Ahmad, B.I., et al., Driver and Passenger Identification from Smartphone Data. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2018. 20(4): p. 1278-1288.
[53] Reynolds, D.A. and R.C. Rose, Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1995. 3(1): p. 72-83.
[54] Bae, A. and W. Kim, Speaker Verification Employing Combinations of Self-Attention Mechanisms. Electronics, 2020. 9(12).
[55] Ozgunduz, E., T. ?enturk, and M.E. Karsl?gil, Efficient Off-Line Verification and Identification of Signatures by Multiclass Support Vector Machines, in International Conference on Computer Analysis of Images and Patterns, A. Gagalowicz, Editor. 2005, Springer: Berlin, Heidelberg. p. 799–805.
[56] Milgram, J., M. Cheriet, and R. Sabourin. “One Against One” or “One Against All”: Which One is Better for Handwriting Recognition with SVMs? in Proceedings of 10th International Workshop on Frontiers in Handwriting Recognition. 2006. France.
[57] Cappelli, R., et al., Performance Evaluation of Fingerprint Verification Systems. IEEE Transactions on Pattern Analysis and Machine Intellegence, 2006. 28(1): p. 1-18.
[58] Klausner, M. and W. Grimm, Method for detecting the position of hands on a steering wheel. 2006, Robert Bosch GmbH. Stuttgart (DE) United States.
[59] Mardi Putri, R.R., et al., Smartwatch-Based Open-Set Driver Identification by Using GMM-Based Behavior Modeling Approach. IEEE Sensors Journal, 2021. 21(4): p. 4918-4926.
[60] R. Wynne, V. Beanland, and P. Salmon, “Systematic review of driving simulator validation studies,” Safety Science, vol. 117, pp. 138–151, 08 2019.
[61] Huang, N.E., et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. A 1998. 454: p. 903–995.
[62] TTDCi9. How to apply for a locally issued Taiwan driver’s license - Travel Taiwan During Covid-19. 2022 [cited 2023; Available from: https://blog.mrhost.com.tw/1604/how-to-get-ctaiwan-drivers-license/.
[63] Hsu, C.W., C.C. Chang, and C.J. Lin, A Practical Guide to Support Vector Classification. 2003: National Taiwan University. p. 1-2.
[64] Hossain, M.Y. and A. Sayeed, A Comparative Study of Motor Imagery (MI) Detection in Electroencephalogram (EEG) Signals Using Different Classification Algorithms, in 2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI). 2021. p. 1-6.
[65] Xing, H.-j., et al., Linear Feature-weighted Support Vector Machine. Fuzzy Information and Engineering, 2019. 1(3): p. 289-305.
[66] Yogendra, N., Comparative analysis of SVM and Naive Bayes classifier for the SEMG signal classification. Materials Today: Proceedings, 2021. 37: p. 3241-3245.
[67] Ali, Ahmed & Abdullah, Mudhfer & Hamid, Ahmed & Fahem, Ali. (2011). Effect of Steering Wheel Vibration on drivers Hands in a Two-WheelDrivers Hand tractor. Journal of Engineering. 17. 1539-1549.
[68] Hao, N.; Sun, X.; Zhang, M.; Zhang, Y.; Wang, X.; Yi, X. Vibration and Noise Analysis and Experimental Study of Rail Conveyor. Sensors 2023, 23, 4867. https://doi.org/10.3390/s23104867
[69] A. Zuska and D. Wi?ckowski, "The impact of unbalanced wheels and vehicle speed on driving comfort," 2018 XI International Science-Technical Conference Automotive Safety, ?asta, Slovakia, 2018, pp. 1-6, doi: 10.1109/AUTOSAFE.2018.8373310.
[70] S. Xiaocai, S. Huo, L. Yang, J. Cao, J. Zou, L. Chen, P. G. Sarrigiannis, and Y. Zhao. "A revised hilbert-huang transformation to track non-stationary association of electroencephalography signals." IEEE Trans. Neural Syst. Rehab. Eng., vol. 29, pp. 841–851, 2021.
[71] Jolliffe, I.T. and J. Cadima, Principal component analysis: a review and recent developments. Phil. Trans. R. Soc. A, 2016. 374: p. 20150202.
[72] Shlens, J. A Tutorial on Principal Component Analysis. 2017.
[73] Balakrishnama, S. and A. Ganapathiraju, Linear Discriminant Analysis - A Brief Tutorial. 2017: Institute for Signal and Information Processing. p. 1-8.

指導教授

梁德容博士(Professor Deron Liang)

審核日期

2025-1-22

推文