Stacking‐based ensemble learning method for cognitive distraction state recognition for drivers in traditional and connected environments

Abstract

Compared with the traditional environment, a connected environment in which multiple types of intelligent vehicles share roads will be more complicated. However, do changes in the traffic environment affect the driver's distraction level and distraction recognition? Relatively few studies have addressed these questions. This study constructs traditional and connected environments and conducts driving simulation experiments. Distracted driving data for 60 drivers were collected in each environment, and the one‐way repeated analysis of variance (ANOVA) method was used to select the distraction indices with significant differences as the input indices. An independent t‐test was applied to analyse changes in the distraction indices in the two environments. The results show that the distraction indices, including the standard deviation (SD) of the horizontal fixation angles, blink frequency, mean pupil diameter, mean saccade speed, SD of the steering wheel angle, mean speed and SD of the lane acceleration, differ in the two environments; therefore, the distraction recognition model in the traditional environment is no longer suitable for connected environments. A distraction state recognition model developed with a stacking‐based ensemble learning algorithm composed of a support vector machine (SVM), extreme gradient boosting (XGBoost), long short‐term memory (LSTM), and bi‐directional LSTM with an attention mechanism (AT‐Bi‐LSTM) was proposed for each environment. The recognition accuracy reaches 95.71% in the traditional environment, and the accuracy rate reaches 97.92% in the connected environment. Compared with traditional algorithms, the proposed approach yields greater recognition accuracy and can be applied in intelligent vehicle distraction early warning assistance systems to improve road safety.

A Novel Deep Stacking-Based Ensemble Approach for Short-Term Traffic Speed Prediction

“…The identification of the LCM of the prior automobile was also accomplished in this study using a stacking-based ensemble learning strategy, which incorporates RF, SVM, LSTM, and bi-directional LSTM based on the attention mechanism. The authors in [44] explored driving simulations in conventional and connected contexts. A stack-based ensemble learning system made up of support vector machines (SVM), XGBoost (LSTM), and bi-directional LSTM with an Attention-based Bidirectional Long-Short Term Memory(AT-Bi-LSTM) for the environment was used to build a method for recognizing distracted states.…”

Detection of Driver Cognitive Distraction Using Machine Learning Methods

“…The majority of the studies have focused on visual [6] or manual distraction [7]. While a few studies have explored cognitive distraction detection [8].…”

Non‐instinct detection of cellphone usage from lane‐keeping performance based on eXtreme gradient boosting and optimal sliding windows

“…RF achieved a bet-ter balance between sensitivity and specificity than SVM, with accuracies of 85.38% and 81.26%. As deep learning shines in time-series data processing, some RNN-based methods were employed to pattern the driver distraction detection [6,23]. The increasing demand for explanations for the driving system [24] makes these deep learning methods underperform traditional machine learning in this aspect currently.…”