Factors Identification and Prediction for Mind Wandering Driving Using Machine Learning

Abstract

Traffic safety is affected by many complex factors. Mind wandering (MW) is a fatal cause affecting driving safety and is hard to be detected and prevented due to its uncertain and complex occurrence mechanism. The aim of this study was to propose a framework for analyzing and predicting MW based on readily available driving status data. The data used in this study are the single-trip information collected by the questionnaire, which includes drivers’ personal characteristics, contextual information in which MW occurs, and in-vehicle environmental factors. After investigating the extent of factors that influence MW, these chosen factors are used to forecast MW. Based on these results, we select factors reliable to be obtained in real life to forecast MW. To verify that the new factors explored are useful in improving the forecast accuracy, the compared analysis is conducted with the results found by our approach and the existing approaches. We compare results obtained by four machine-learning-enabled forecasting approaches on a real-life data set. The result shows that the factors found in this paper can significantly improve forecast accuracy. The confusion matrix, ROC curves, and AUC are conducted, and the performance of the gradient boosting decision tree algorithm is better than other forecast approaches. The importance rankings of most factors obtained by the Gradient Boosting Decision Tree and questionnaire are the same.

Preventing mind-wandering during driving: Predictions on potential interventions using a cognitive model

“…In addition, low cognitive workload does not directly imply that driving performance is decreased and the cognitive mechanisms behind human failure due to low cognitive load in monotonous driving situations are not yet fully understood (Engström et al, 2017). Therefore, it is unsurprising that while many researchers have attempted to assess the cognitive stage of the driver in low workload scenarios (e.g., Baldwin et al, 2017;Bencich et al, 2014;Walker and Trick, 2018;Alsaid et al, 2018;He et al, 2011;Burdett et al, 2019;Zhang and Kumada, 2018;Lin et al, 2016;Pepin et al, 2021;Lin et al, 2021;Zhang and Kumada, 2017;Kutila et al, 2007;Bosch and Mecacci, 2023), few have aspired to leverage this information and increase the cognitive workload to optimize performance (drivers: e.g., Mishler and Chen (2023), pilots: e.g., Schwerd and Schulte (2021). However, any automated system needs to be defined in terms of what changes to the level automation occur at what times (Byrne and Parasuraman, 1996).…”