Browsing by Author "Zhang, Zhaozhong"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Driver distraction detection using experimental methods and machine learning algorithms.
    (Cranfield University, 2020-02) Zhang, Zhaozhong; Velenis, Efstathios; Fotouhi, Abbas; Auger, Daniel J.
    Driver distraction causes numerous road accidents, which is approximately equal to 25% of the total crashes according to the reports by the National Highway Traffic Safety Administration. Warnings can be helpful to mitigate the risks caused by driver distraction. Previous studies on driver distraction detection have not sufficiently found relevant input features to filter insignificant information, thus limiting the improvement of efficiency. Moreover, the disadvantages of driving simulators and public roads pose a challenge in collecting suitable data for feature identification and comparisons of performance among driver distraction detection algorithms. While the previous research focuses on improving prediction accuracy, shortening the prediction time is critical in giving timely warnings to drivers. This thesis aims at detecting driver distraction, which could provide faster and accurate warnings to drivers. The developed method is implemented by cutting the redundancy and irrelevant information fed to the algorithms and instead selecting suitable algorithms that achieve the balance between the prediction accuracy and prediction time. Moreover, a closed testing field supplies an environment for collecting more accurate information to identify the relevant features and to determine suitable algorithms. In this study, open-source data and experimental data are used. The results show that a balance between the prediction accuracy and the prediction time is achieved by feeding the relevant features and using suitable machine learning algorithms (e.g. Decision Tree). Compared with existing state-of-the-art methods, the prediction accuracy of the method proposed in this study has reached approximately the same level. More importantly, the efficiency has improved, including reduced prediction time and fewer input features. Consequently, less computer storage is used.
  • Thumbnail Image
    ItemOpen Access
    Driver distraction detection using machine learning algorithms – an experimental approach
    (Inderscience, 2021-05-08) Zhang, Zhaozhong; Velenis, Efstathios; Fotouhi, Abbas; Auger, Daniel J.; Cao, Dongpu
    Driver distraction is the leading cause of accidents that contributes to 25% of all road crashes. In order to reduce the risks posed by distraction, warning must be given to the driver once distraction is detected. According to the literature, no rankings of relevant features have been presented. In this study, the most relevant features in detecting driver distraction are identified in a closed testing environment. The relevant features are found to be the mean values of speed and lane deviation, maximum values of eye gaze in direction, and head movement in direction. After the relevant features have been identified, pre-processed data with relevant features are fed into decision tree classifiers to discriminate the data into normal and distracted driving. The results show that detection accuracy of 78.4% using decision tree can be achieved. By eliminating unhelpful features, the time required to process data is reduced by around 40% to make the proposed technique suitable for real-time application.
  • Thumbnail Image
    ItemOpen Access
    Identification and analysis of driver postures for in-vehicle driving activities and secondary tasks recognition
    (IEEE, 2018-12-25) Xing, Yang; Lv, Chen; Zhang, Zhaozhong; Wang, Huaji; Na, Xiaoxiang; Cao, Dongpu; Velenis, Efstathios; Wang, Fei-Yue
    Driver decisions and behaviors regarding the surrounding traffic are critical to traffic safety. It is important for an intelligent vehicle to understand driver behavior and assist in driving tasks according to their status. In this paper, the consumer range camera Kinect is used to monitor drivers and identify driving tasks in a real vehicle. Specifically, seven common tasks performed by multiple drivers during driving are identified in this paper. The tasks include normal driving, left-, right-, and rear-mirror checking, mobile phone answering, texting using a mobile phone with one or both hands, and the setup of in-vehicle video devices. The first four tasks are considered safe driving tasks, while the other three tasks are regarded as dangerous and distracting tasks. The driver behavior signals collected from the Kinect consist of a color and depth image of the driver inside the vehicle cabin. In addition, 3-D head rotation angles and the upper body (hand and arm at both sides) joint positions are recorded. Then, the importance of these features for behavior recognition is evaluated using random forests and maximal information coefficient methods. Next, a feedforward neural network (FFNN) is used to identify the seven tasks. Finally, the model performance for task recognition is evaluated with different features (body only, head only, and combined). The final detection result for the seven driving tasks among five participants achieved an average of greater than 80% accuracy, and the FFNN tasks detector is proved to be an efficient model that can be implemented for real-time driver distraction and dangerous behavior recognition.