No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Predicting interstate motor carrier crash rate level using classification models
Abstract
Ensuring safe operations of large commercial vehicles (motor carriers) remains an important challenge, particularly in the United States. While the federal regulatory agency has instituted a compliance review-based rating method to encourage carriers to improve their safety levels, concerns have been expressed regarding the effectiveness of the current ratings. In this paper, we consider a crash rate level (high, medium, and low) rather than a compliance review-based rating (satisfactory, conditional satisfactory, and unsatisfactory). We demonstrate an automated way of predicting the crash rate levels for each carrier using three different classification models (Artificial Neural Network, Classification and Regression Tree (CART), and Support Vector Machine) and three separate variable selection methods (Empirical Evidence, Multiple Factor Analysis, Garson's algorithm). The predicted crash rate levels (high, low) are compared to the assigned levels based on the current safety rating method. The results indicate the feasibility of crash rate level as an effective measure of carrier safety, with CART having the best performance.
... In the second procedure, the neural network model is estimated with all the selected variables as inputs, and the relative importance of every input variable is calculated. As a nonlinear model, determining the relative importance of variables is more difficult than in linear regression models, and Garson's method is used in this study, because it was proved that the neural network can identify the most influential input variables from a given variable list by Garson's method (Garson 1991), and recently, the reliability of Garson's method in the variable selection process of three-layer neural network is verified to be better than other widely used methods, such as correlation method and principal component analysis (Papatheocharous and Andreou 2010;Fischer 2015;Yousefi et al. 2018;Liu et al. 2018). According to Garson's method (Garson 1991), for a neural network model with N neurons in the input layer and L neurons in the hidden layer, the relative importance of the ith input variable to the kth output variable ( I ik ) can be defined as where ij is the weight of the ith neuron in the input layer and jth neuron in the hidden layer, and jk is the weight of the jth neuron in the hidden layer and kth neuron in the output layer. ...
... After determining the input variables, output variables, and number of neurons in the hidden layer, the actual structure of the neural network model is determined. Garson's method is capable of quantifying the relative importance and select variables (Papatheocharous and Andreou 2010;Fischer 2015;Yousefi et al. 2018;Liu et al. 2018). Other methods such as Olden's method and SHapley Additive exPlanations (SHAP) values can quantify the intensity and direction of each input variable's contribution to each output variable (Olden and Jackson 2002;Lundberg and Lee 2017), which is helpful to understand the relationship between each input and output variable in the model. ...
Pedestrian spaces are increasingly becoming popular locations for shopping, recreation, festivities, and other social activities. Therefore, an improved understanding of the factors that make walking environments enjoyable and safe is essential. Most existing studies focus on modelling walking behaviours of individual pedestrians. However, most people participate in these activities as parts of social groups. Although the movement and choice behaviours of pedestrians in social groups differ from those of individuals, a model featuring group movements has not been developed. This study uses neural networks to analyse the effects of variables influencing pedestrian movements of social groups and predict the variation in walking dynamics. A top-view video was used to extract the trajectories of pedestrian groups. After identifying the social groups in a crowd, the movement characteristics, pedestrian–environment interaction, inter-pedestrian interaction, intra-group relationship, and inter-group relationship of all group members were calculated and considered in the model. After a variable selection process using neural networks, a neural network model was developed featuring variables that are strongly related to the lateral or longitudinal changes in the individual’s walking speed. The current movement condition, presence of obstacles nearby, impending collisions, current position and velocity of other group members, and following behaviour were found to impact a pedestrian’s walking dynamics. The proposed model can predict the pedestrian density and distribution according to a space function, contributing to better crowd management and efficient design and renovation of pedestrian spaces. Furthermore, the variable selection method can optimise and simplify other pedestrian behaviour prediction models.
... Machine learning techniques have proven to be highly valuable in real-time crash analysis, enabling the identification of relationships between accident occurrences and various associated factors or contemporary situations. Support Vector Machines [22], Neural Networks [23], and Bayesian Networks [14,15] are among the commonly implemented machine learning approaches. Artificial Neural Networks (ANNs) are particularly effective in handling noisy data and performing fast real-time computations with robust efficiency [7]. ...
Road crashes are one of the most critical issues that pose a serious threat to our daily life; Crash occurrences prediction is a key role in designing efficient intelligent transportation systems. In this study, we aim to analyze road crash events for experienced and novice drivers under several weather conditions during multiple driving simulations that have been conducted using a desktop driving simulator. This work outlined the effect of snow and rain conditions on driver behavior by endorsing real-time driver data namely: wheel angle position, throttle pedal position and brake pedal position. Moreover, optimized modeling strategies using the deep learning algorithm Multilayer Perceptron (MLP) and Support Vector Machine (SVM) along with Bayesian Networks (BN) models have been developed to analyze crash events. To the authors’ knowledge, there has been a limited interest at assessing the impact of both snow and rainy weather conditions on the occurrence of crash events while providing a critical analysis for experienced and novice drivers based on driver entries; this approach fill the research gap of the combined effect of driving experience and weather conditions on road crash occurrence. The findings depict superior performances have been obtained when adopting the proposed strategy. As a whole, new insights into weather-induced crash events’ investigation for experienced and novice drivers have been acquired and can be endorsed for designing effective crash avoidance/warning systems. KeywordsCrash predictionMachine learningNovice driversExperienced driversWeather conditionsData balancingDriving simulator
... A few other computer vision methods that are used in road safety applications in Table 2. The speed factor plays an important role in the study of the causes of accidental deaths; fifty drivers were recruited by Charlton and Starkey to analyze the driver speed choice and it was found that the mean speed is normal among all drivers in varying road situations [93]. Prototype willingness model is developed by Preece et al. [92] to identify fast driving and willingness in text driving is conducted in IBM SPSS Version 24 form the data received from 183 licensed drivers of 17-25 years old drivers and found that most of the positive attitude young drivers were protagonists. ...
Advanced driver assistance and accident detection system is significantlyneeded to ensure safety for drivers. Drowsiness detection, collision detection and various driver alert systems have penetrated into market with an aim to provide higher security for driver but due to population of vehicle and modification in structure of roads these system fails to answer safety problems that results in severe accidents.In this paper we provide accurate analysis of past recorded accidents in Tamil Nadu state and analysis of public opinion on Accident detection system is carried out using 1004 licensed persons under different ages in three cities (Coimbatore, Erode and Nilgiris) by focusing the major 10 parameters carrying 48 Questions. Findings and implications of this analysis is also discussed in this article. A thorough analysis of recent techniques that are used for AAD (Automatic Accident Detection) and road safety programmes that resolve the pre and post cautionary concerns of accidents in developing countries is addressed with the review of most 4 influencing algorithms in ITS for AAD.. 1 Vehicle Detection using Wheel arc Counter Detection Algorithm, 2 Enhancement of V2X Communication using Multi-RAT,3Road Curvature Estimation using Circle Fitting Algorithm and4Driver Safety Systemis discussed in this paper. To understand recent computational challenges and extended areas of research in ITS, anhybrid approach of CNN with VANETs for accident detection has been suggested to enumerate the obtained accidental information.
... The F1-score is a harmonized average of precision and recall that can accurately evaluate the model's performance when the data label is imbalanced. The larger the F1-score, the better the model can be determined, and the calculation formula is presented in Equation (5) [41,42]. From Table 3, it can be seen that the average of the overall classification accuracy for all scenarios is 81%. ...
Background:
Factors related to the wellness of taxi drivers are important for identifying high-risk drivers based on human factors. The purpose of this study is to predict high-risk taxi drivers based on a deep learning method by identifying the wellness of a driver, which reflects the personal characteristics of the driver.
Methods:
In-depth interviews with taxi drivers are conducted to collect wellness data. The priorities of factors affecting the severity of accidents are derived through a random forest model. In addition, based on the derived priority of variables, various combinations of inputs are set as scenarios and optimal artificial neural network models are derived for each scenario. Finally, the model with the best performance for predicting high-risk taxi drivers is selected based on three criteria.
Results:
A model with variables up to the 16th priority as inputs is selected as the best model; this has a classification accuracy of 86% and an F1-score of 0.77.
Conclusions:
The wellness-based model for predicting high-risk taxi drivers presented in this study can be used for developing a taxi driver management system. In addition, it is expected to be useful when establishing customized traffic safety improvement measures for commercial vehicle drivers.
... It produces superior predictive performance to kNN at the significant level of 10%, and also marginally outperforms SVM in short-term BFP of Chinese listed companies. A recent study by Liu et al. [19] also shows the superiority of CART algorithm in both accuracy and speed in comparison with ANN and SVM. In contrast to ID3 [20] and C4.5 [21], the other two traditional decision tree algorithms, CART algorithm uses the Gini index to choose the optimal split point. ...
Intelligent manufacturing poses a challenge for fault diagnosis of rotor systems to meet the three tasks: whether exists faults, faults location and quantitative diagnosis. Traditional methods hardly meet all the three tasks in online fault diagnosis. This paper proposes a modified classification and regression tree (CART) algorithm named D-CART algorithm to provide much faster fault classification by reducing the iteration times in computation while still ensuring accuracy. Experiments are carried on to achieve a comprehensive online fault diagnosis for rotor systems such as faults location, faults types and quantitative analysis of unbalanced mass in this paper. In comparison with the other 4 novel CART-based algorithms, the experimental results indicate that the speed of D-CART algorithm is improved by a factor of 23.92 compared to the fastest improved algorithm (Adaboost-CART) and a model accuracy of up to 96.77%. Thus demonstrating the speed superiority of D-CART algorithm in both diagnosing locations of different faults types and determining the loading masses of unbalanced faults. The proposed method has the potential to realize high-accuracy online fault diagnosis for rotor systems.
Road crash events are a fact of life. Although significant progress have been made in adopting machine learning techniques for analyzing road crashes, there has been limited emphasis on evaluating crash events within data fusion systems. The primary purpose of this study is to outline and validate a comparative safety analysis of an ensemble fusion system founded on the use of different base classifiers and a meta-classifier to procure more efficient crash prediction. Three categories of features namely vehicle-telemetry, driver-inputs and environmental-conditions have been collected using a driving-simulator in order to identify the crash strongest precursors through feature extraction technique. Furthermore, optimized strategies using AdaBoost, XGBoost, RF, GBM, LightGBM, CatBoost and KNN techniques were implemented to establish effective predictions within a fusion-based system. To ensure that the proposed system provide superior decisions given the infrequent nature of crash events, an imbalance-learning approach was conducted based on three resampling strategies: over-sampling, under-sampling and SMOTE-Tomek-Links. The findings depict that the superior performance has been attained when adopting LightGBM, CatBoost and KNN as base classifiers along with SMOTE-TL as balancing technique and XGBoost as meta-classifier with 89.19% precision, 96.77% recall and 92.83% f1-score. To our knowledge, there has been a limited interest, if not at all, at endorsing a fusion-based system examining the impact of real-time features' combinations on the prediction of road crashes while providing a critical analysis of class-imbalance. Overall, the findings emphasized the relevance of the explanatory features and can be endorsed in designing efficient intelligent transportation systems.
The truck platoon is one of the most promising connected and autonomous vehicle (CAV) technologies that can reduce fuel consumption and emission, enhance traffic safety, and increase roadway capacity. It is predicted to become mainstream in the next decade. Therefore, it is imperative to fully investigate the safety issues of the truck platoon before its large-scale deployment. However, studies on the lateral safety of the truck platoon under extreme weather, especially crosswinds are still lacking. To fill such a research gap, the current study contributes to the literature by proposing a reliability-based framework to evaluate the safety of the truck platoon regarding incursion into neighboring lanes due to extreme weather, especially crosswinds. The proposed approach involved three main steps: (1) the computational fluid dynamics (CFD) simulation of the aerodynamics of the truck platoon; (2) the truck platoon driving simulation under crosswind; and (3) the advanced response surface model development and the reliability analysis. Four main factors regarding lateral safety of the platoon were considered: wind speed, road friction coefficients, driving speed, and inter-vehicle spacing. The maximum lateral displacement (MLD) was chosen as a measure of lateral safety. The results showed that there was a significant difference between the aerodynamics of a single truck and that of the truck platoon vehicles and the inter-vehicle spacing between trucks within the truck platoon barely influenced the MLD. The MLD was largest for the leading truck as compared to those of the following trucks. The inter-vehicle spacing didn’t have a significant influence on MLD when the inter-vehicle spacing is shorter than 1.5 times of the truck length, while the other factors impacted the MLD significantly. In addition, the support vector regression with the radial basis function outperformed the other response surface functions. Based on reliability analysis, the risk level of the truck platoon was quantified using the safety index, and the impact of contributing factors towards the safety index of the truck platoon was also evaluated. This study confirmed that the proposed framework could be applied to evaluate the lateral safety of the truck platoon. The findings provide important practical implications for the decision-making of transportation management agencies and tailored countermeasures in the CAV) environment.
Introduction
Nowadays, a significant part of goods and passengers are transported on suburban highways with mainly high-speed vehicles. Hence, these highways are very prone to collisions with different injuries. For this reason, road collisions have become one of the largest international health issues in the world recently. Due to the high fatality or severe physical/mental injury rates caused by car collisions and the complex interactions between the factors affecting them, analyzing these collision-prone areas, identifying the factors affecting their occurrences, and discovering knowledge in the form of key rules is crucial, as the purposes for this study.
Methods
Three supervised algorithms including Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forests (RF) were used to build up classification models for the fatality severity of 2355 fatal collision data records during 2007–2009 occurred in the roadways of 8 states in the USA with different driver-related, environmental, and road factors. Predicted risk maps were generated for each classifier and the importance of contributing factors was evaluated based on the mean decrease in accuracy and the mean decrease in Gini Index. Finally, association rule mining was performed by the Apriori algorithm to extract collision rules.
Results
RF outperformed the other methods in terms of the highest overall accuracy and kappa rates, which were 94% and 92% respectively. The risk maps revealed that collisions with the most fatalities were mainly concentrated in the northern states. The number of travel lanes, speed limit, roadway profile, and light conditions were the most influencing factors in the collisions. 68 association rules were mined by the Apriori algorithm. Then, important rules were specified to extract hidden information from the collision data.
Conclusions
The RF model was more accurate in collision analysis, along with comprehensive collision factors. Great importance should be given to road factors in route design, especially in critical locations with severe fatality risk.
Abstract This article presents results of a systematic review of the US motor-carrier safety literature in transportation, logistics, and safety journals. The discipline has seen growth in research over the decades, and growth of the field rapidly increased in the last decade. We organize the literature into a systems framework and summarize the research across industry system levels to include government, regulators, carriers, and drivers. We then apply a goal-framing approach to reveal some of the dynamic interactions between system levels and the environment, as entities work to minimize risk to life and property during freight operations while striking a balance between the industry's welfare and societal welfare. This article provides recommendations for future research to fill gaps in the current body of knowledge and to aid government officials, regulators and law enforcement officials, carrier managers, and drivers in addressing industry challenges and maintaining safe roads in 2020 and beyond.
Evaluating road safety is an enduring research topic in Infrastructure and Transportation Engineering. The prediction of crash risk is very important for avoiding other crashes and safeguarding road users. According to this task, awareness of the number of vehicles involved in an accident contributes greatly to safety analysis, hence, it is necessary to predict it. In this study, the main aim is to develop a binary model for predicting the number of vehicles involved in an accident using Neural Networks and the Group Method of Data Handling (GMDH). For this purpose, 775 accident cases were accurately recorded and evaluated from the urban and rural areas of Cosenza in southern Italy and some notable parameters were considered as input data including Daylight, Weekday, Type of accident, Location, Speed limit and Average speed; and the number of vehicles involved in an accident was considered as output. In this study, 581 cases were selected randomly from the dataset to train and the rest were used to test the developed binary model. A confusion matrix and a Receiver Operating Characteristic curve were used to investigate the performance of the proposed model. According to the obtained results, the accuracy values of the prediction model were 83.5% and 85.7% for testing and training, respectively. Finally, it can be concluded that the developed binary model can be applied as a reliable tool for predicting the number of vehicles involved in an accident.
Real-time traffic crash prediction has been a major concern in the development of Collision Avoidance Systems (CASs) along with other intelligent and resilient transportation technologies. There has been a pronounced progress in the use of machine learning models for crash events assessment by the transportation safety research community in recent years. However, little attention has been paid so far to evaluating real-time crash occurrences within information fusion systems. The main aim of this paper is to design and validate an ensemble fusion framework founded on the use of various base classifiers that operate on fused features and a Meta classifier that learns from base classifiers’ results to acquire more performant crash predictions. A data-driven approach was adopted to investigate the potential of fusing four real-time and continuous categories of features namely physiological signals, driver maneuvering inputs, vehicle kinematics and weather covariates in order to systematically identify the crash strongest precursors through feature selection techniques. Moreover, a resampling-based scheme, including Bagging and Boosting, is conducted to generate diversity in learner combinations comprising Bayesian Learners (BL), k-Nearest Neighbors (kNN), Support Vector Machine (SVM) and Multilayer Perceptron (MLP). To ensure that the proposed framework provide powerful and stable decisions, an imbalance-learning strategy was adopted using the Synthetic Minority Oversampling TEchnique (SMOTE) to address the class imbalance problem as crash events usually occur in rare instances. The findings show that Boosting depicted the highest performance within the fusion scheme and can accomplish a maximum of 93.66% F1 score and 94.81% G-mean with Naïve Bayes, Bayesian Networks, k-NN and SVM with MLP as the Meta-classifier. To the best of our knowledge, this work presents the first attempt at establishing a fusing framework on the basis of data from the four aforementioned categories and fusion models while accounting for class imbalance. Overall, the method and findings provide new insights into crash prediction and can be harnessed as a promising tool to improve intervention efforts related to traffic intelligent transportation systems.
This study used the bus incident data in Victoria, Australia to establish the relationship between operational characteristics and the safety performance of bus operators. A series of count models were investigated to account for methodological challenges, including excess zeros and panel data structure. The empirical results highlighted the different effects operational characteristics had on the risk and prevalence of bus incidents. Operators of smaller size, providing non-route services and operating in regional areas had a lower risk of having any reported incidents compared with larger route operators and operators in areas of higher accessibility. In cases where at least one incident had been reported, incident frequency was higher for operators with higher fleet total travel distance, older fleets and better roadworthy performance (this factor being counterintuitive). Findings from this study provide safety regulators with evidence-driven opportunities to enhance bus safety, including improving incident reporting practices, the establishment of a comprehensive database for heavy vehicle operators, and specific efforts targeted at older fleets.
In 2010, there were 32,999 people killed, 3.9 million were injured, and 24 million vehicles were damaged in motor vehicle crashes in the United States. The economic costs of these crashes totaled 277 billion cost of motor vehicle crashes represents the equivalent of nearly 14.96 trillion real U.S. Gross Domestic Product for 2010. These figures include both police-reported and unreported crashes. When quality of life valuations are considered, the total value of societal harm from motor vehicle crashes in 2010 was 93 billion of the total 76 billion. Medical expenses totaled 28 billion. Each fatality resulted in an average discounted lifetime cost of 24 billion in 2010, the equivalent of over 59 billion or 21 percent of all economic costs, and 84 percent of these costs occurred in crashes where a driver or non-occupant had a blood alcohol concentration (BAC) of .08 grams per deciliter or greater. Alcohol was the cause of the crash in roughly 82 percent of these cases, causing 59 billion in 2010. Seat belt use prevented 12,500 fatalities, 308,000 serious injuries, and 14 billion in easily preventable injury related costs. Crashes in which at least one driver was identified as being distracted cost $46 billion in 2010. The report also includes data on the costs associated with motorcycle crashes, failure to wear motorcycle helmets, pedestrian crash, bicyclist crashes, and numerous different roadway designation crashes.
Special report This study examines the relationship of heavy truck mechanical condition and crash risk. The LTCCS presents an opportunity to examine in more detail than previously possible the relationship of vehicle condition to crash risk. The report includes a review of existing literature, a full analysis of the results of the post-crash truck inspections, and a series of logistic regression models to test the association of vehicle condition and crash role. Two specific hypotheses are tested: The first hypothesis is that trucks with defects and out of service conditions are statistically more likely to be in the role of precipitating a crash than trucks with no defects or out of service conditions. The second hypothesis is that defects in specific systems, such as the brake system, are associated with crash roles in which those systems are primary in crash avoidance, and that there is a physical mechanism that links the vehicle defect with the crash role. Post crash inspections showed that the condition of the trucks in the LTCCS is poor. Almost 55 percent of vehicles had one or more mechanical violations. Almost 30 percent had at least one out of service condition. Among mechanical systems, violations in the brake (36 percent of all) and lighting system (19 percent) were the most frequent. A brake OOS condition increased the odds of the truck assigned the critical reason (identifying the precipitating vehicle) by 1.8 times. Both HOS violations and log OOS increased by a larger amount—2.0 and 2.2 times respectively. In rear-end and crossing paths crashes, brake violations, especially related to adjustment, increased the odds of the truck being the striking vehicle by 1.8 times. Federal Motor Carrier Safety Administration, Washington, D.C. http://deepblue.lib.umich.edu/bitstream/2027.42/64999/1/102509.pdf
The majority of previous research and analysis has indicated driverrelated factors as the main cause of most commercial vehicle-related crashes. The main goal of the current project is to provide greater concentration on the commercial driver, so as to have the most significant impact on the number of crashes. The ultimate outcome of this study is to save lives, prevent injuries, and prevent property damage associated with commercial vehicle-related crashes. To accomplish this crash reduction goal, the current study combines and expands on two previous research efforts: development of the Inspection Selection System (ISS) and a project analyzing the use of driver traffic conviction data to identify high-safety-risk motor carriers better. To accomplish greater focus on the commercial driver, the first objective of the current project was to analyze further the data and weightings associated with the carrier driver conviction measure created through the conviction data study. With use of results from this first objective, the second objective of the present project was to then integrate the carrier driver conviction measure into the current ISS and conduct a pilot test of this new ISS algorithm, termed ISS-D. Results from the pilot test indicate an approximate 10% increase in driver out-of-service rates after the ISS-D algorithm implementation. In addition, there was an almost doubling of the driver out-of-service rate when the ISS-D recommended the inspection.
We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal 'hidden' units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure.
In complex engineering systems, empirical relationships are often employed to estimate design parameters and engineering properties. A complex domain is characterized by a number of interacting factors and their relationships are, in general, not precisely known. In addition, the data associated with these parameters are usually incomplete or erroneous (noisy). The development of these empirical relationships is a formidable task requiring sophisticated modeling techniques as well as human intuition and experience. This paper demonstrates the use of back-propagation neural networks to alleviate this problem. Backpropagation neural networks are a product of artificial intelligence research. First, an overview of the neural network methodology is presented. This is followed by some practical guidelines for implementing back-propagation neural networks. Two examples are then presented to demonstrate the potential of this approach for capturing nonlinear interactions between variables in complex engineering systems.
An approach to the integrated water resources management based on Neuro-Dynamic Programming (NDP) with an improved technique for fastening its Artificial Neural Network (ANN) training phase will be presented. When dealing with networks of water resources, Stochastic Dynamic Programming provides an effective solution methodology but suffers from the so-called "curse of dimensionality", that rapidly leads to the problem intractability. NDP can sensibly mitigate this drawback by approximating the solution with ANNs. However in the real world applications NDP shows to be considerably slowed just by this ANN training phase. To overcome this limit a new training architecture (SIEVE: Selective Improvement by Evolutionary Variance Extinction) has been developed. In this paper this new approach is theoretically introduced and some preliminary results obtained on a real world case study are presented.
Copyright © 2005 IFAC
In the paper the authors are listed in alphabetical order as the contribution of each was essential. Major contributions from the author whose name is underlined. Presented by Castelletti, A. Published in Proceedings of the 16th IFAC World Congress, Prague, 2005 ISBN: 978-3-902661-75-3
In 1986 the federal government expanded its program of company inspections for enforcement of motor carrier safety regulations. We find that many parts of these inspections are unrelated to the safety performance of firms. Never the less, reinspection of firms found to be unsatisfactory in a previous inspection does appear to bring about a substantial improvement in their safety performance. However, such firms represent a small fraction of the industry, and the probability of being inspected is very low. Thus, the program does not appear to have resulted in a detectable improvement in the accident rate of the industry.
This paper expands an earlier analysis of the effect of firm characteristics and safety practices on truck accident rates. The sample size has been increased from 13,000 to 75,500. Negative binomial regressions are used in preference to the Poisson technique used previously. The current analysis confirms previous results, but provides important new insights into the safety implications of being a private carrier and hauling hazardous materials and the effect of having been in business for many years.
The compliance review (CR) is a federal program monitoring motor carrier safety performance and regulatory compliance. This study sought to assess the impact of CRs on reviewed trucking companies in reducing truck crashes.
Data was from the Motor Carrier Management Information System. Study subjects were trucking companies established during 1990-1995, had at least one truck, and remained active until April 2004. Truck crash data of these companies was examined from 1996 to 2003. The crash rates in 2003 and annual percentage changes in number of crashes were computed. Analyses were stratified by company size, organization, operation classification, and safety rating.
Companies that received CRs had a higher crash rate than never-reviewed companies. Reviewed companies experienced a 39-15% reduction in number of crashes in the year the CR was performed. The reduction in crashes was observed in all reviewed companies regardless of company size, operation classification, type of organization, or safety rating. The reduction in crashes was sustained for at least 7 years after CRs.
The study results were controlled for the year in which CRs were performed, crash trend, and CR selection bias. However, further studies, especially a randomized prospective longitudinal study, are needed to overcome the limitations that are associated with an observation study.
Accountability (CSA), Carrier Safety Measurement 450
- Safety Compliance
Compliance, Safety, Accountability (CSA), Carrier Safety Measurement
450
Federal Motor Carrier 451 Safety Administration
System (CSMS) Methodology, Technical Report, Federal Motor Carrier
451
Safety Administration, 2013.
Compliance, safety, accountability: Analyzing the rela-453 tionship of scores to crash risk
- M D Lueck
M. D. Lueck, Compliance, safety, accountability: Analyzing the rela-453
tionship of scores to crash risk (2012).
Predicting truck crash involve-461 ment: Developing a commercial driver behavior-based model and rec-462 ommended countermeasures
- D C Murray
- B Lantz
- S A Keppler
D. C. Murray, B. Lantz, S. A. Keppler, Predicting truck crash involve-461
ment: Developing a commercial driver behavior-based model and rec-462
ommended countermeasures, Transportation Research Forum (2005).
463
Linkages between motor carrier 478 accidents and safety regulation
- T M Corsi
- P Fanara
- M J Roberts
T. M. Corsi, P. Fanara, M. J. Roberts, Linkages between motor carrier
478
accidents and safety regulation, Logistics and Transportation Review
479
20 (1984).
Safety Measurement System 487 (SMS) Methodology: Behavior Analysis and Safety Improvement Cat-488 egory (BASIC) Prioritization Status
- Safety Compliance
Compliance, Safety, Accountability (CSA), Safety Measurement System
487
(SMS) Methodology: Behavior Analysis and Safety Improvement Cat-488
egory (BASIC) Prioritization Status, Technical Report, Federal Motor
489