Analysis of truck drivers’ unsafe driving behaviors using four machine learning methods

Niu, Yi; Li, Zhenming; Yang, Fan

doi:10.1016/j.ergon.2021.103192

Cited by 21 publications

(7 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ma et al (2020) proposed a new conceptual road model for vehicle running state monitoring and active driving identification. With the rapid development of machine learning, various machine learning methods have also been widely applied to classify driving behaviors (Kluger et al, 2016; Niu et al, 2021). Xu et al (2022) proposed an aggressive driving behavior prediction method based on Hidden Markov Models and attention‐based long short‐term memory networks.…”

Section: Literature Reviewmentioning

confidence: 99%

Identification of aggressive driving behavior of online car‐hailing drivers based on association classification

Wu,

Chen,

et al. 2023

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

With the rapid development of online car‐hailing, the related crashes have become a key issue with public concern. Identifying and predicting aggressive driving behaviors is critical to reduce traffic crashes. In this study, we propose a method to recognize aggressive driving behavior based on association classification, with multisource features being employed, including driver emotion, vehicle kinematic characteristics, and road environment. The model performs best in a 10‐fold cross‐test when the minimum support and minimum confidence are set as 0.01 and 0.8, respectively. Besides, we also compare the performance of aggressive driving behavior recognition classifiers constructed using association classification with other rule‐based classification methods, including ID3, C4.5, CART, and Random Forest. The results show that association classification performs better than other classification competitors. Thirty‐six if–then rules generated by the association classification are used to analyze the influencing factors and associated mechanisms of aggressive driving behavior. It is found that aggressive driving behavior is highly correlated with driver anger and disgust emotions. Aggressive driving behavior is more likely to occur when no passengers are in the car than the case with passengers. Driver entertainment behavior and passenger interference also affect driving behavior. Moreover, drivers are prone to aggressive driving when making a U‐turn. This research not only proposed a new identification method for aggressive driving behavior but also provided a comprehensive understanding of the associated influencing factors which thus benefit the further research and development of safety assistance driving devices.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Identification of aggressive driving behavior of online car‐hailing drivers based on association classification

Wu,

Chen,

et al. 2023

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

show abstract

“…Each node is split using the best predictor from a subset of predictors chosen randomly at that node. As it is more robust in terms of generalizability than the decision trees, RF plays an important role in machine learning, such as the works of Niu et al and Poh et al [45,48]. Recently, decision trees have been extended to the family of gradient boosting algorithms, such as eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost).…”

Section: Classification By Four Classifiers Of Machine Learningmentioning

confidence: 99%

“…There are many indicators to evaluate the final training model's performance. For simplicity and efficiency, this study employs common indicators, including area under the curve of receiver characteristic operator (AUC), accuracy, precision, recall, and F1-score [48]. Accuracy, precision, recall, and F1-score are partial performance indicators, whereas AUC is a comprehensive indicator.…”

Section: Optimal Model Acquisitionmentioning

confidence: 99%

Development of a Classification Framework for Construction Personnel’s Safety Behavior Based on Machine Learning

Yin

Shen

et al. 2022

Buildings

View full text Add to dashboard Cite

Different sets of drivers underlie different safety behaviors, and uncovering such complex patterns helps formulate targeted measures to cultivate safety behaviors. Machine learning can explore such complex patterns among safety behavioral data. This paper aims to develop a classification framework for construction personnel’s safety behaviors with machine learning algorithms, including logistics regression (LR), support vector machine (SVM), random forest (RF), and categorical boosting (CatBoost). The classification framework has three steps, i.e., data collection and preprocessing, modeling and algorithm implementation, and optimal model acquisition. For illustrative purposes, five common safety behaviors of a random sample of Hong Kong-based construction personnel are used to validate the classification framework. To achieve high classification performance, this paper employed a combinative strategy, consisting of feature selection, synthetic minority over-sampling technique (SMOTE), one-hot encoding, standard scaler and classifiers to classify safety behaviors, and multi-objective slime mould algorithm (MOSMA) to optimize parameters in the classifiers. Results suggest that the combinative strategy of CatBoost–MOSMA achieves the highest classification performance with the maximum average scores, including area under the curve of receiver characteristic operator (AUC) ranging from 0.84 to 0.92, accuracy ranging from 0.80 to 0.86, and F1-score ranging from 0.79 to 0.86. From the optimal model, a unique set of important features was identified for each safety behavior, and ten out of the 46 input indicators were found important for all five safety behaviors. Based on the findings, this study advocates using the machine learning strategy of CatBoost–MOSMA in future construction safety behavior research and makes concrete and targeted suggestions to cultivate different construction safety behaviors.

show abstract

“…Currently, research in this area is primarily focused on six aspects: (1) Analyzing the existing unsafe acts, unsafe behaviors, and human errors arising from the safety management process or accidents [ 6 , 7 , 8 ]. More detailed classifications and in-depth research on the obtained results have also been conducted by some scholars [ 9 , 10 ]. (2) Research into the causes of unsafe acts.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Unsafe Acts Influence Law Based on System Dynamics Simulation: Thoughts on Behavior Mechanism and Safety Control

Xie

Gui

et al. 2023

IJERPH

View full text Add to dashboard Cite

In modern safety management, it is very important to study the influence of the whole safety system on unsafe acts in order to prevent accidents. However, theoretical research in this area is sparse. In order to obtain the influence law of various factors in the safety system on unsafe acts, this paper used system dynamics simulation to carry out theoretical research. First, based on a summary of the causes of the coal and gas outburst accidents, a dynamic simulation model for unsafe acts was established. Second, the system dynamics model is applied to investigate the influence of various safety system factors on unsafe acts. Third, the mechanism and the control measures of unsafe acts in the enterprise safety system are studied. This study’s main result and conclusions are as follows: (1) In the new coalmines, the influence of the safety culture, safety management system, and safety ability on the safety acts were similar. The order of influence on the safety acts in production coalmines is as follows: safety management system > safety ability > safety culture. The difference is most evident in months ten to eighteen. The higher the safety level and safety construction standard of the company, the greater the difference. (2) In the construction of the safety culture, the order of influence was as follows: safety measure elements > safety responsibility elements = safety discipline elements > safety concept elements. It shows the difference in influence from the 6th month and attains its maximum value from the 12th month to the 14th month. (3) In the construction of the safety management system, the degree of influence in new coalmines was as follows: safety policy > safety management organization structure > safety management procedures. Among them, especially in the first 18 months, the impact of the safety policy was most apparent. However, in the production mine, the degree of influence was as follows: safety management organization structure > safety management procedures > safety policy, but the difference is very small. (4) The degree of influence on the construct of safety ability was as follows: safety knowledge > safety psychology = safety habits > safety awareness, but the difference on the impact was small.

show abstract

Analysis of truck drivers’ unsafe driving behaviors using four machine learning methods

Cited by 21 publications

References 59 publications

Identification of aggressive driving behavior of online car‐hailing drivers based on association classification

Identification of aggressive driving behavior of online car‐hailing drivers based on association classification

Development of a Classification Framework for Construction Personnel’s Safety Behavior Based on Machine Learning

Investigation of Unsafe Acts Influence Law Based on System Dynamics Simulation: Thoughts on Behavior Mechanism and Safety Control

Contact Info

Product

Resources

About