Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery

Montella, Alfonso; Aria, Massimo; D’Ambrosio, Antonio; Mauriello, Filomena

doi:10.1016/j.aap.2011.04.025

Cited by 162 publications

(107 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CART Figure 1 shows the DT built using the CART method with 70% of the data for training and the remaining data (30%) for testing, as used by Montella et al (2011). The CART method creates a tree with 19 nodes and 10 terminal nodes.…”

Section: Resultsmentioning

confidence: 99%

“…The concepts of support (S) and probability (P) are central to association rules and have been used by several authors (Agrawal et al, 1993;Pande and Abdel-Aty, 2009;Montella et al 2011). Population (Po) is deduced from S and P (Po=S/P).…”

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

“…It means that no rules with support <0.90% and/or probability <10% would be considered. Montella et al (2011) used lower thresholds for their analysis (0.10% and 1.00% for support and probability respectively). In this paper, as the sample size is not very large and the sample is balanced, the threshold values used are 0.60% for support and 60% for probability.…”

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

“…To reduce this error and following other authors (Montella et al, 2011;, the dataset was split randomly in two parts: a training set (70% of the data) and a testing set (remaining 30%).…”

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

“…DT techniques are particularly appropriate for studying crashes because they are non-parametric techniques that do not require prior probabilistic knowledge on the study phenomena. Furthermore, they consider conditional interactions among input data (Montella et al, 2011). Other advantages of DTs compared to other methods with similar aims include the extraction of decision rules of the "if-then" type , and that they can be used to discover behaviours that occur within a specified set of data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Extracting decision rules from police accident reports through decision trees

Oña

López

Abellán³

2013

Accident Analysis & Prevention

111

View full text Add to dashboard Cite

Given the current number of road accidents, the aim of many road safety analysts is to identify the main factors that contribute to crash severity. To pinpoint those factors, this paper shows an application that applies some of the methods most commonly used to build Decision Trees (DTs), which have not been applied to the Road Safety field before. An analysis of accidents on rural highways in the province of Granada (Spain) between 2003 and 2009 (both inclusive) showed that the methods used to build DTs serve our purpose and may even be complementary. Applying these methods has enabled potentially useful decision rules to be extracted that could be used by road safety analysts. For instance, some of the rules may indicate that women, contrary to men, increase their risk of severity under bad lighting conditions. The rules could be used in road safety campaigns to mitigate specific problems. This would enable managers to implement priority actions based on a classification of accidents by types (depending on their severity). However, the primary importance of this proposal is that other databases not used here (i.e. other infrastructure, roads and countries) could be used to identify unconventional problems in a manner easy for road safety managers to understand, as decision rules.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

“…To reduce this error and following other authors (Montella et al, 2011;, the dataset was split randomly in two parts: a training set (70% of the data) and a testing set (remaining 30%).…”

Section: For Example: If (Accident Type=rollover and Atmospheric Conditmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Extracting decision rules from police accident reports through decision trees

Oña

López

Abellán³

2013

Accident Analysis & Prevention

111

View full text Add to dashboard Cite

show abstract

Severity Prediction of Traffic Accident Using an Artificial Neural Network

AlKheder

Taamneh

2016

Journal of Forecasting

178

View full text Add to dashboard Cite

In this paper, an artificial neural network (ANN) was used to predict the injury severity of traffic accidents based on 5973 traffic accident records occurred in Abu Dhabi over a 6‐year period (from 2008 to 2013). For each accident record, 48 different attributes had been collected at the time of the accident. After data preprocessing, the data were reduced to 16 attributes and four injury severity classes. In this study, WEKA (Waikato Environment for Knowledge Analysis) data‐mining software was used to build the ANN classifier. The traffic accident data were used to build two classifiers in two different ways. The whole data set were used for training and validating the first classifier (training set), while 90% of the data were used for training the second classifier and the remaining 10% were used for testing it (testing set). The experimental results revealed that the developed ANN classifiers can predict accident severity with reasonable accuracy. The overall model prediction performance for the training and testing data were 81.6% and 74.6%, respectively. To improve the prediction accuracy of the ANN classifier, traffic accident data were split into three clusters using a k‐means algorithm. The results after clustering revealed significant improvement in the prediction accuracy of the ANN classifier, especially for the training dataset. In this work, and in order to validate the performance of the ANN model, an ordered probit model was also used as a comparative benchmark. The dependent variable (i.e. degree of injury) was transformed from ordinal to numerical (1, 2, 3, 4) for (minor, moderate, sever, death). The R tool was used to perform an ordered probit. For each accident, the ordered probit model showed how likely this accident would result in each class (minor, moderate, severe, death). The accuracy of 59.5% obtained from the ordered probit model was clearly less than the ANN accuracy value of 74.6%. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

A semantic‐based classification and regression tree approach for modelling complex spatial rules in motor vehicle crashes domain

Effati

Sadeghi‐Niaraki

2015

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Innovative data mining and knowledge discovery approaches that take advantage of geospatial analysis can be useful for analysis of motor vehicle crashes on regional highway corridors. This study presents an Ontology-based Classification and Regression Tree (OCART) approach to induct crash rules on regional highway corridors by adding ontological reasoning to Classification and Regression Tree (CART) decision rules. It develops an ontology-driven geospatial framework to predict the motor vehicles crash severity through the proposed OCART approach. A system prototype has been developed and implemented on a regional highway corridor in order to illustrate and evaluate the proposed method. The results demonstrate the application of ontological reasoning and spatial computation significantly improves the performance of CART crash rules. The proposed method reveals new relationships among crash severities and contributing factors that have been kept implicit in CART decision rules.

show abstract

Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery

Cited by 162 publications

References 24 publications

Extracting decision rules from police accident reports through decision trees

Extracting decision rules from police accident reports through decision trees

Severity Prediction of Traffic Accident Using an Artificial Neural Network

A semantic‐based classification and regression tree approach for modelling complex spatial rules in motor vehicle crashes domain

Contact Info

Product

Resources

About