Classification and Evaluation of Driving Behavior Safety Levels: A Driving Simulation Study

Abstract

The road traffic safety situation is severe worldwide and exploring driving behavior is a research hotspot since it is the main factor causing road accidents. However, there are few studies investigating how to evaluate real-time traffic safety of driving behavior and the number of driving behavior safety levels has not yet been thoroughly explored. This paper aims to propose a framework of real-time driving behavior safety level classification and evaluation, which was validated by a case study of driving simulation experiments. The proposed methodology focuses on determining the optimal aggregation time interval, finding the optimal number of safety levels for driving behavior, classifying the safety levels, and evaluating the driving safety levels in real time. An improved cross-validation mean square error model based on driver behavior vectors was proposed to determine the optimal aggregation time interval, which was found to be 1s. Three clustering techniques were applied, i.e., k-means clustering, hierarchical clustering and model-based clustering. The optimal number of clusters was found to be three. Support vector machines, decision trees and naï ve Bayes classifiers were then developed as classification models. The accuracy of the combination of kmeans clustering and decision trees proved to be the best with three clusters.

Driver Behavior Classification: A Systematic Literature Review

“…They focused on the unbalanced time series sample problem when evaluating driving behavior, which can be alleviated by MeanShift clustering. The authors of the article [50] proposed a realtime classification of driving behavior based on k-means clustering, hierarchical clustering, and model-based clustering algorithms to identify the number of behavioral classes as normal, high, and low risk. Then SVM, Decision Tree (DT), and Naive Bayes (NB) algorithms were applied to evaluate these risk behaviors and test the performance of the clustering methods.…”

“…Accident Analysis and Prevention [58], [66], [83], [87], [89], [93], [94], [105], [116] Transportation Research Part F: Traffic Psychology and Behavior [40], [46], [104], [109], [111], [113], [115], [122] IEEE Access [61], [91], [97], [100], [101], [103] Journal of Safety Research [112], [114], [118], [119] Type of behavior Papers Abnormal driver behavior [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51],…”

“…Papers Percentage of studies Simulator [54], [46], [66], [89], [90], [76], [82], [81], [47], [34], [35], [69], [79], [104], [80], [57], [70], [92], [108], [93], [94], [51], [88], [50] 25% Camera [29], [38], [40], [53], [75], [84], [106], [107], [34], [77], [77], [77], [77], [86], [87], [103] 17% GPS [31], [33], [40], [43], [45], [58], [62], [67], [68], [83],…”

Driver Profile and Driving Pattern Recognition for Road Safety Assessment: Main Challenges and Future Directions

“…Based on this, the driving risk identification and prediction will be certainly improved, as it will be possible to develop individualized driving risk models with higher accuracy. These models will allow the interpretation of driving safety behavior into probability of collision by focusing on the individual behavioral characteristics of each driver on a micro and macro level [69], [70]. These individualized driving risk models will be a more accurate representation of human behavior, which can be exploited in order to form an "optimal" driving model, by obtaining the safest driving characteristics under different driving and environmental conditions.…”

A Comprehensive Review of Driving Style Evaluation Approaches and Product Designs Applied to Vehicle Usage-Based Insurance

“…In the classification of styles, different conclusions may be drawn due to different research methods. The representative of simple classification can be seen in the research of Johnson et al, which just divides driving styles into 2 types-"radical" and "non-radical" [87]; Tricot et al also believe that driving styles can be simply divided into 3 categories: peaceful type, radical type and ordinary type [88]; Qi et al believe that driving status plays a role in the connection between driving behavior and its corresponding style, and have divided driving status into 3 categories: "aggressive", "cautious" and "moderate" from the data collected by onboard detection sensors [89]; likewise, Yang et al have also divided driving safety levels into "normal" driving, "low-risk" driving and "high-risk" driving, and analyzed the effectiveness of several different clustering algorithms in dividing driving behavior risk levels under different traffic flow and driver distraction scenarios [90]. Based on the analysis of a large number of survey data, Taubman-Ben-Ari et al have divided driving style into 8 types: free type, anxiety type, adventure type, anger type, highspeed type, danger aversion type, caution type, and patience type [91].…”