國道客運駕駛疲勞偵測模型之比較研究

A COMPARATIVE STUDY OF DROWSY DRIVING DETECTION MODELS FOR INTERCITY BUS DRIVERS

李威勳(Wei-Hsun Lee)；林政宇(Zheng-Yu Lin)；劉宗憲(Tsung-Hsien Liu)；陳羨邦(Hsien-Pang Chen)；張宏璿(Hung-Hsuan Chang)

疲勞駕駛 ； 駕駛行為辨識 ； 深度學習 ； 資料不平衡 ； 時間序列分類 ； Drowsy Driving ； Fatigue Driving ； Driving Behavior Recognition ； Deep Learning ； Data Imbalance ； Time Series Classification

運輸計劃季刊

52卷1期（2023 / 03 / 30）

29 - 50

繁體中文;英文

疲勞駕駛為公路運輸安全一大隱憂，統計顯示超過七成事故來自包含疲勞駕駛在內的危險行為。由於疲勞駕駛之資料僅佔駕駛資訊的一小部分，具有高度不平衡的特性，本研究針對真值標記後之車輛動態數據，將數據以SMOTE進行數據不平衡處理後，使用支持向量機、隨機森林、啟動時間序列模型（InceptionTime）及堆疊式長短期記憶模型（Stacked-LSTM）等四種機器學習模型進行分析，結果顯示，應用SMOTE方法之四種模型，雖正確率達到0.96，但模型對於疲勞駕駛風格並不具有辨識能力。因此本研究提出採用滑動時間窗格放大目標樣本並建立時間序列資料，進行數據不平衡之預處理，利用啟動時間序列模型及堆疊式長短期記憶模型深度學習方法進行模型訓練，學習危險行為與疲勞駕駛事件間的關聯，以利用車輛動態資料的標記達到預判即將發生疲勞駕駛事件。利用滑動時間窗格方法之深度學習模型，啟動時間序列模型獲得0.7763之準確度，但其F1-score則為0.791，比SMOTE處理過的模型平均F1-score約0.5更高。代表其應用滑動窗格方法之深度學習模型，已可成功萃取與疲勞駕駛相關之特徵，並可穩定獲得七成以上正確率。

Fatigue or drowsy driving is one of the major concerns for road transport safety. Statistics show that more than 70% of vehicle accidents come from risky driving behaviors, including fatigue driving. Drowsy driving is hard to be detected by inspecting the vehicle dynamic data because it accounts for very small proportion, hence it is highly data imbalanced. Synthetic minority oversampling technique (SMOTE) is applied to preprocessing the vehicle dynamics data, which is labeled by the fleet manager, for the data imbalance issue. Four machine learning models are applied for predicting drowsy driving including support vector machine (SVM), random forest, InceptionTime, and Stacked-LSTM. Results show that although the average accuracy is 0.96 of these four models by using SMOTE, however, it cannot identify drowsy driving correctly. To more accurate predict the drowsy driving events by using the vehicle dynamic data, a time window slicing combining with target sample augmentation method is proposed for the data imbalance preprocessing issue. InceptionTime and Stacked-LSTM models are applied for training and learning the correlations within the vehicle dynamic data and drowsy driving style. Experiment results show the accuracy of proposed sliding window method with InceptionTime model is 0.7763, the F1-score is 0.791 which is better than the models using SMOTE method with the average F1-score 0.5. With the proposed sliding window method, it helps the deep learning models to better predict the drowsy driving.

1. Ashouri, M. R. a. N., A.,Azadi, S.(2018).Time Delay Analysis of Vehicle Handling Variables for Near-Crash Detection of Drowsy Driving Using a Bus Driving Simulator.Proceedings of the 6th RSI International Conference on Robotics and Mechatronics
2. Chawla, N. V.,Bowyer, K. W.,Hall, L. O.,Kegelmeyer, W. P.(2002).SMOTE: Synthetic Minority Over-sampling Technique.Journal of Artificial Intelligence Research,16,321-357.
3. Fawaz, H. I.,Forestier, G.,Weber, J.,Idoumghar, L.,Muller, P. A.(2019).Deep Learning for Time Series Classification: A Review.Data Mining and Knowledge Discovery,33(4),917-963.
4. Jia, S.,Hui, F.,Li, S.,Zhao, X.,Khattak, A. J.(2020).Long Short-Term Memory and Convolutional Neural Network for Abnormal Driving Behaviour Recognition.IET Intelligent Transport Systems,14(5),306-312.
5. Klauer, S. G.,Dingus, T. A.,Neale, V. L.,Sudweeks, J. D.,Ramsey, D. J.(2006).The impact of driver inattention on near-crash/crash risk: An Analysis Using the 100-car Naturalistic Driving Study Data.Washington:National Highway Traffic Safety Administration.
6. Lee, J.-W.,Lee, S.-K.,Kim, C.-H.,Kim, K.-H.,Kwon, O.-C.(2014).Detection of Drowsy Driving Based on Driving Information.Proceedings of IEEE International Conference on Information & Communication Technology Convergence (ICTC)
7. Saleh, K.,Hossny, M.,Nahavandi, S.(2017).Driving Behavior Classification Based on Sensor Data Fusion Using LSTM Recurrent Neural Networks.IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
8. World Health Organization, “Road Traffic Injuries”, https://www.who.int/news-room/ fact-sheets/detail/road-traffic-injuries, 2022/6/20.
9. 交通部(2012).101 年運輸政策白皮書.
10. 李威勳,周建銘,謝永達,蔡以誠,盧冠宏,蕭至良,邱繼億(2016)。科技部巨量資料產學共創合作專案計畫報告科技部巨量資料產學共創合作專案計畫報告,科技部。
11. 周建成(2017)。國立高雄應用科技大學電機工程研究所。
12. 陳柏瑋(2018)。國立臺灣科技大學電機工程研究所。