Human Factors: The Journal of the Human Factors and Ergonomics Society ( IF 3.3 ) Pub Date : 2021-02-24 , DOI: 10.1177/0018720821995000 Ziyang Xie 1 , Li Li 1 , Xu Xu 1
Objective
We propose a method for recognizing driver distraction in real time using a wrist-worn inertial measurement unit (IMU).
Background
Distracted driving results in thousands of fatal vehicle accidents every year. Recognizing distraction using body-worn sensors may help mitigate driver distraction and consequently improve road safety.
Methods
Twenty participants performed common behaviors associated with distracted driving while operating a driving simulator. Acceleration data collected from an IMU secured to each driver’s right wrist were used to detect potential manual distractions based on 2-s long streaming data. Three deep neural network-based classifiers were compared for their ability to recognize the type of distractive behavior using F1-scores, a measure of accuracy considering both recall and precision.
Results
The results indicated that a convolutional long short-term memory (ConvLSTM) deep neural network outperformed a convolutional neural network (CNN) and recursive neural network with long short-term memory (LSTM) for recognizing distracted driving behaviors. The within-participant F1-scores for the ConvLSTM, CNN, and LSTM were 0.87, 0.82, and 0.82, respectively. The between-participant F1-scores for the ConvLSTM, CNN, and LSTM were 0.87, 0.76, and 0.85, respectively.
Conclusion
The results of this pilot study indicate that the proposed driving distraction mitigation system that uses a wrist-worn IMU and ConvLSTM deep neural network classifier may have potential for improving transportation safety.
中文翻译:
通过腕上加速度计进行实时驾驶分心识别
客观的
我们提出了一种使用腕戴式惯性测量单元 (IMU) 实时识别驾驶员分心的方法。
背景
每年因分心驾驶导致数以千计的致命车祸。使用穿戴式传感器识别分心可能有助于减轻驾驶员分心,从而提高道路安全。
方法
二十名参与者在操作驾驶模拟器时执行与分心驾驶相关的常见行为。从固定在每个驾驶员右手腕上的 IMU 收集的加速度数据用于检测基于 2 秒长流数据的潜在手动分心。比较了三个基于深度神经网络的分类器使用 F1 分数识别分心行为类型的能力,F1 分数是一种同时考虑召回率和精确度的准确性衡量标准。
结果
结果表明,卷积长短期记忆 (ConvLSTM) 深度神经网络在识别分心驾驶行为方面优于卷积神经网络 (CNN) 和具有长短期记忆 (LSTM) 的递归神经网络。ConvLSTM、CNN 和 LSTM 的参与者内部 F1 分数分别为 0.87、0.82 和 0.82。ConvLSTM、CNN 和 LSTM 的参与者间 F1 分数分别为 0.87、0.76 和 0.85。
结论
该试点研究的结果表明,所提出的使用腕戴式 IMU 和 ConvLSTM 深度神经网络分类器的驾驶分心缓解系统可能具有提高交通安全性的潜力。