scholarly journals Analysing Road Accident Criticality using Data mining

2019 ◽  
pp. 408-415
Author(s):  
Shahsitha Siddique V ◽  
Nithin Ramakrishnan
Keyword(s):  
Data Mining ◽  
Road Transport ◽  
Road Accident ◽  
Machine Learning Algorithms ◽  
Road Accidents ◽  
Decision Tree Classifier ◽  
Efficient Manner ◽  
Tree Classifier ◽  
Accident Severity ◽  
Accident Data

Road transport is one of the most vital forms of transportation system, connecting both long and short distances in our country. There are several attributes, which affect the intensity of a road accident like speed of the vehicle, road conditions, time of the accident etc. Analysing these attributes gives an idea about the factors lead to the severity of the accident. Data mining is a method to analyse huge amount of traffic data in an efficient manner, which gives the factors, affect the road accidents. Several machine learning algorithms can be used to find the relation between traffic attributes the lead to the severity of the accidents. In this work, we use three methods for predicting accident criticality. First, Naive Bayesian Classifier is used to get the accident severity based on Bayes rule. Then, Decision Tree classifier is used for same purpose for accident severity calculation. Finally K-Nearest Neighbour(KNN) classifier is employed for severity calculation. The accuracy of the algorithms are compared and it is found that KNN performs better than the other two algorithms employed. The major aim of the work is to find the accident severity. Also the work aims to reduce road accidents by giving awareness to public using the above method.

High-Risk Road Accident Corridors in Dhaka, Bangladesh

2013 ◽  
Vol 65 (3) ◽  
Author(s):  
Ishtiaque Ahmed ◽  
Bayes Ahmed ◽  
Mohd. Rosli Hainin
Keyword(s):  
High Risk ◽  
Traffic Accident ◽  
Safety Management ◽  
Road Transport ◽  
Road Accident ◽  
Highway Safety ◽  
Road Accidents ◽  
Highway Safety Manual ◽  
Roadway Safety ◽  
Accident Data

Bangladesh has one of the highest fatality rates in road accidents and to address the safety problem is a serious concern. Dhaka is the most vulnerable city of the country. Bangladesh Road Transport Authority maintains a database of accidents using outdated software that lacks in geo-referencing facility.  This makes the analysis of accident locations a challenging task. The area for this study was the Dhaka Metropolitan Police area where the concerned forty one police stations are responsible for collecting traffic accident data. The Highway Safety Manual identifies the “Network Screening” as the first step of the Roadway Safety Management Process. This study focuses on locating the accidents on urban roadways in Dhaka and identifies thirty corridors and ranks them using geo-referenced data through developing and using a GIS database. Dhaka-Mymensing Road was found to be the most vulnerable road corridor followed by Airport Road and Mirpur Road respectively. The study recommended special attention and special “Diagnostic” studies as explained in the Highway Safety Manual for the high-risk corridors and to put emphasis on the accident data collection and reporting system. Adoption of modern technologies like GPS and GIS in collecting and reporting of the traffic accident data was emphasized.

scholarly journals Prioritization of Black Spots in Hilly Road Segment using Road Engineering Data

2020 ◽  
Vol 9 (3) ◽  
pp. 4418-4422
Keyword(s):  
Black Spot ◽  
Road Transport ◽  
Road Accident ◽  
Industrialized Countries ◽  
Road Accidents ◽  
Road Engineering ◽  
The Road ◽  
Black Spots ◽  
Accident Data ◽  
On The Road

Road accidents are one of the causes of disability, injury and death. As per the latest road accident data released by the Ministry of Road Transport & Highways (MoRTH), the total number of accidents increased by 2.5 percent from 4,89,400 in 2014 to 5,01,423 in 2015. The analysis reveals that about 1,374 accidents and 400 deaths take place every day. Every single year, it has been estimated that over three lakh persons die and 10-15 million persons are injured in road accidents throughout the world. According to the analyses, statistics of global accident indicate that in developing countries, the rate of fatality per licensed vehicle is very high as compared to that of industrialized countries. A road stretch of about 500 metres in length in which either ten fatalities or five road accidents (involving grievous injuries/fatalities) took place during last three calendar years, on National Highways is considered as a road accident black spot according to MoRTH, Government of India. In the present study the identified black spots of Haridwar and Dehradun city were included comprising of a total of 81 black spots out of which there were 49 black spots which were identified in Dehradun followed by 32 black spots in Haridwar. The present study was an attempt to carry out the prioritization of these identified blackspots with respect to the factors that were considered to evaluate accident prone locations on the road. The identified black spots were then prioritized using the classification scheme (ranking from low to high).The study reveals that the advantage of using this approach for prioritizing accident black spots on roads is that it requires very less additional data other than the road network maps.

scholarly journals Accident Severity in India

2020 ◽  
Vol 8 (12s3) ◽  
pp. 55-58
Keyword(s):  
Statistical Analysis ◽  
Road Transport ◽  
Road Accident ◽  
The Other ◽  
Road Accidents ◽  
Transportation Services ◽  
The Road ◽  
Accident Severity

Among all the transportation services available, road transport is one of the most important services available. It acts as a feeder for the other services. According to the Ministry of Road Transport and Highways, the road transport amounts to the traffic of about 87% related to the passenger and 60% related to the freight. Now, there is another field, where road transport is among the top list and that field is of road accidents. In 2016, about 150785 people died in road accidents. And as the population is increasing, there is also an increase in the rate of road accidents. So, it is vital to analyze the data of road accidents for future predictions and thereby developing proper measures for this increasing rate. Many factorsresult in accidents and many cases might not have been recorded. So, the available data may not be consistent, but the data is gathered mainly from the Ministry of Road Transport and Highways and then the information was extracted from that data. This information is used for the statistical analysis for the prediction of a future road accident or accident severity.

scholarly journals The Effect of Drivers' Demographic Characteristics on Road Accidents in Different Seasons Using Data Mining

2017 ◽  
Vol 29 (6) ◽  
pp. 555-567 ◽  
Author(s):  
Sajjad Shokohyar ◽  
Ehsan Taati ◽  
Sara Zolfaghari
Keyword(s):  
Data Mining ◽  
Clustering Algorithms ◽  
Road Accident ◽  
World Health ◽  
Road Accidents ◽  
Accident Data ◽  
Pass Through ◽  
And Gender ◽  
Health Organization ◽  
Demographic Features

According to World Health Organization, each year, over 1.2 million people die on roads, and between 20 and 50 million suffer non-fatal injuries. Based on international reports, Iran has a high death rate caused by road accidents. The objective of this study was to extract implicit knowledge from road accident data sets on roads of Iran through data mining. In this regard, three useful data mining techniques were combined: clustering, classification and rule extraction. Following the preparation stage, data were segmented via three clustering algorithms; Kohonen, K-Means and Twostep. Two-step cluster analysis is a one-pass-through data approach which generates a fairly large number of pre-clusters. Next, the optimized algorithm and cluster were identified, after which, in the classification level and by adding the drivers' demographic features through C5.0, a classification algorithm was employed so as to make the decision tree. Ultimately, the effects of these demographic features were investigated on road accidents. The characteristics such as age, job, driving license duration and gender proved to be more important factors in accident analysis. Certain rules of accidents were then extracted in each season of the year.

scholarly journals Student Academic Performance Prediction using Supervised Learning Techniques

2019 ◽  
Vol 14 (14) ◽  
pp. 92 ◽  
Author(s):  
Muhammad Imran ◽  
Shahzad Latif ◽  
Danish Mehmood ◽  
Muhammad Saqlain Shah
Keyword(s):  
Data Mining ◽  
Supervised Learning ◽  
Student Performance ◽  
Performance Prediction ◽  
Class Imbalance ◽  
Ensemble Methods ◽  
Fine Tuning ◽  
Classification Error ◽  
Decision Tree Classifier ◽  
Tree Classifier

Automatic Student performance prediction is a crucial job due to the large volume of data in educational databases. This job is being addressed by educational data mining (EDM). EDM develop methods for discovering data that is derived from educational environment. These methods are used for understanding student and their learning environment. The educational institutions are often curious that how many students will be pass/fail for necessary arrangements. In previous studies, it has been observed that many researchers have intension on the selection of appropriate algorithm for just classification and ignores the solutions of the problems which comes during data mining phases such as data high dimensionality ,class imbalance and classification error etc. Such types of problems reduced the accuracy of the model. Several well-known classification algorithms are applied in this domain but this paper proposed a student performance prediction model based on supervised learning decision tree classifier. In addition, an ensemble method is applied to improve the performance of the classifier. Ensemble methods approach is designed to solve classification, predictions problems. This study proves the importance of data preprocessing and algorithms fine-tuning tasks to resolve the data quality issues. The experimental dataset used in this work belongs to Alentejo region of Portugal which is obtained from UCI Machine Learning Repository. Three supervised learning algorithms (J48, NNge and MLP) are employed in this study for experimental purposes. The results showed that J48 achieved highest accuracy 95.78% among others.

scholarly journals Road Transport Accidents in Nigeria and the Role of Automotive Active Safety System

2016 ◽  
Vol 11 (1) ◽  
pp. 49-54
Author(s):  
Olasunkanmi Oriola Akinyemi ◽  
Hezekiah O Adeyemi ◽  
Olusegun Jinadu
Keyword(s):  
Traffic Safety ◽  
Traffic Accidents ◽  
Road Traffic ◽  
Transportation Network ◽  
Road Transport ◽  
Road Accident ◽  
Active Safety ◽  
Road Accidents ◽  
Road Transportation ◽  
Road Traffic Safety

Abstract Analysis of road traffic accidents revealed that most accidents are as a result of drivers’ errors. Over the years, active safety systems (ASS) were devised in vehicle to reduce the high level of road accidents, caused by human errors, leading to death and injuries. This study however evaluated the impacts of ASS inclusions into vehicles in Nigeria road transportation network. The objectives was to measure how ASS contributed to making driving safer and enhanced transport safety. Road accident data were collected, for a period of eleven years, from Lagos State Ministry of Economic Planning and Budget, Central Office of Statistics. Quantitative analysis of the retrospective accident was conducted by computing the proportion of yearly number of vehicles involved in road accident to the total number of vehicles for each year. Results of the analysis showed that the proportion of vehicles involved in road accidents decreased from 16 in 1996 to 0.89 in 2006, the injured persons reduced from 15.58 in 1998 to 0.3 in 2006 and the death rate diminished from 4.45 in 1998 to 0.1 in 2006. These represented 94.4 %, 95 % and 95 % improvement respectively on road traffic safety. It can therefore be concluded that the inclusions of ASS into design of modern vehicles had improved road safety in Nigeria automotive industry.

scholarly journals Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction

Computers ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 157
Author(s):  
Daniel Santos ◽  
José Saias ◽  
Paulo Quaresma ◽  
Vítor Beires Nogueira
Keyword(s):  
Machine Learning ◽  
Predictive Model ◽  
Road Accident ◽  
Influential Factors ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Economic Losses ◽  
Learning Approaches ◽  
Road Accidents ◽  
Accident Data

Traffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understood and predicted, it might be possible to take measures to mitigate the damages and its severity. The purpose of this work is to identify these factors using accident data from 2016 to 2019 from the district of Setúbal, Portugal. This work aims at developing models that can select a set of influential factors that may be used to classify the severity of an accident, supporting an analysis on the accident data. In addition, this study also proposes a predictive model for future road accidents based on past data. Various machine learning approaches are used to create these models. Supervised machine learning methods such as decision trees (DT), random forests (RF), logistic regression (LR), and naive Bayes (NB) are used, as well as unsupervised machine learning techniques including DBSCAN and hierarchical clustering. Results show that a rule-based model using the C5.0 algorithm is capable of accurately detecting the most relevant factors describing a road accident severity. Further, the results of the predictive model suggests the RF model could be a useful tool for forecasting accident hotspots.

Data Mining: A Bagged Decision Tree Classifier Algorithm For Ids Intrusion Detection System Based Attacks Classification

2021 ◽  
pp. 1826-1839
Author(s):  
Sandeep Adhikari, Dr. Sunita Chaudhary
Keyword(s):  
Data Mining ◽  
Intrusion Detection ◽  
Decision Tree ◽  
Intrusion Detection System ◽  
Detection System ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Decision Tree Classifier ◽  
Tree Classifier

The exponential growth in the use of computers over networks, as well as the proliferation of applications that operate on different platforms, has drawn attention to network security. This paradigm takes advantage of security flaws in all operating systems that are both technically difficult and costly to fix. As a result, intrusion is used as a key to worldwide a computer resource's credibility, availability, and confidentiality. The Intrusion Detection System (IDS) is critical in detecting network anomalies and attacks. In this paper, the data mining principle is combined with IDS to efficiently and quickly identify important, secret data of interest to the user. The proposed algorithm addresses four issues: data classification, high levels of human interaction, lack of labeled data, and the effectiveness of distributed denial of service attacks. We're also working on a decision tree classifier that has a variety of parameters. The previous algorithm classified IDS up to 90% of the time and was not appropriate for large data sets. Our proposed algorithm was designed to accurately classify large data sets. Aside from that, we quantify a few more decision tree classifier parameters.

Augmenting Classifiers Performance through Clustering

2018 ◽  
Vol 8 (1) ◽  
pp. 57-68 ◽  
Author(s):  
Sachin Kumar ◽  
Prayag Tiwari ◽  
Kalitin Vladimirovich Denis
Keyword(s):  
Traffic Accident ◽  
Latent Class ◽  
Safety Concern ◽  
Health And Safety ◽  
Road Accident ◽  
Support Vector ◽  
Road Accidents ◽  
Real World Data ◽  
The Public ◽  
Accident Data

Road and traffic accident data analysis are one of the prime interests in the present era. It does not only relate to the public health and safety concern but also associated with using latest techniques from different domains such as data mining, statistics, machine learning. Road and traffic accident data have different nature in comparison to other real-world data as road accidents are uncertain. In this article, the authors are comparing three different clustering techniques: latent class clustering (LCC), k-modes clustering and BIRCH clustering, on road accident data from an Indian district. Further, Naïve Bayes (NB), random forest (RF) and support vector machine (SVM) classification techniques are used to classify the data based on the severity of road accidents. The experiments validate that the LCC technique is more suitable to generate good clusters to achieve maximum classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document