Data Analytics Process over Road Accidents Data—A Case Study of Lisbon City

Mesquitela, Joao; Elvas, Luís B.; Ferreira, João; Nunes, Luís

doi:10.3390/ijgi11020143

Cited by 24 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This study also used the Quantum Geographic Information System (Q-GIS) to enable the location of road traffic crashes and analyze spatial information [25]. It also used combined geographical, statistical, and mapping data in the study [26,27]. That was used for mapping road traffic injuries, accident analysis, and the determination of hot spots [28,29].…”

Section: Methods Of Analysismentioning

confidence: 99%

The Impact of Road Geometric Formation on Traffic Crash and Its Severity Level

Jima

Sipos

2022

Sustainability

View full text Add to dashboard Cite

Road infrastructure has an impact on the occurrence of road traffic crashes. The aim of this study was to analyze the impact of road geometric formation on road traffic crashes. Based on the nature, convenience, and availability of data, the study used Budapest city road traffic crash data from 2017 to 2021. For organizing, analysis, and modeling, the study used Microsoft-Excel, the Statistical Package for Social Science, and Quantum Geographic Information System. Relative frequency distribution, Multinomial Logistic Regression, Multilayer Perceptron Artificial Neural Network, and Severity Index were used for the analysis. Both inferential and descriptive statistics are used to describe and summarize the study outcome. Multicollinearity tests, p-value, overdispersion, percent of incorrect error, and other statistical model testes were undertaken to analyze the significance of the data and variable for modeling and analysis. A large number of crashes were observed in straight and one-lane road geometric formationsr890. However, the severity level was high at the horizontal curve and in all three lanes of the road. The regression model indicated that light conditions, collision type, road geometry, and speed had a significant effect on traffic accidents at a p-value of 0.05. A collision between the vehicle (rear end collision), and a vehicle with a pedestrian was the probable cause of the crash. The Multilayer Perceptron Artificial Neural Network indicated that horizontally curved geometry has a positive and strong relationship with road traffic fatalities. The primary reasons for the occurrences of a road traffic crash at an intersection, horizontal curve, and straight road geometric formation were the improper use of road traffic signs, road pavement condition, and stopping sight distance problems, respectively. The hourly distribution showed that from 16:01 to 17:00 time interval was a peak hour for the occurrences of road traffic crashes. Whereas, driver plays vital role and responsible body for the occurrences of crashes at all geometric formations.

show abstract

Section: Methods Of Analysismentioning

confidence: 99%

The Impact of Road Geometric Formation on Traffic Crash and Its Severity Level

Jima

Sipos

2022

Sustainability

View full text Add to dashboard Cite

show abstract

“…In addition, they suffer serious injuries among all traffic participants. Other studies have shown that factors such as alcohol consumption, age or gender of drivers, lighting, road condition, pedestrian behavior, accident scene, vehicle, speed and adverse weather affect pedestrian injury rates [6][7][8][9]. Adverse weather conditions and inadequate lighting, especially of pedestrian crossings, often lead to more serious injuries on the roads [10].…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluation of factors affecting the number of traffic accidents

Gorzelanczyk,

Piątkowski

2024

View full text Add to dashboard Cite

Year after year, the number of traffic accidents worldwide is decreasing. This value in recent years has been influenced mainly by the pandemic. However, the value is still very high. For this reason, every effort should be made to reduce the number of traffic accidents. The purpose of this article is to evaluate the factors affecting the number of traffic accidents according to weather conditions. For this purpose, a random selection was made of 10 measurement points in Poland, for which the following parameters were analyzed: traffic volume on the road and the number of accidents at the analyzed points. Based on the study, it can be concluded that the number of road accidents is most influenced by factors such as good weather conditions, as well as cloudy and rainy days.

show abstract

“…Mesquitela et al [7] dealt with identifying areas with traffic accidents in Lisbon. They used six datasets-meteorological data, emergency occurrences from the Fire Brigade, and historical traffic status-and a GIS-assisted technique (ArcGIS Pro) to determine the focus of accidents in Lisbon, thus contributing to implementing measures to make driving safe in these areas.…”

Section: Spatial Identification Of Accidents Using Gis Techniquesmentioning

confidence: 99%

“…Several studies are addressing this problem since it does not affect only Brazil, making the accident data analysis field more popular [3,4,6,7]. The main objectives of these studies include understanding the risk factors contributing to accidents and creating measures to reduce such accidents.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach for Classifying Road Accident Hotspots

Amorim

Firmino

Baptista

et al. 2023

IJGI

View full text Add to dashboard Cite

Road accidents are a worldwide problem, affecting millions of people annually. One way to reduce such accidents is to predict risk areas and alert drivers. Advanced research has been carried out on identifying accident-influencing factors and potential highway risk areas to mitigate the number of road accidents. Machine learning techniques have been used to build prediction models using a supervised classification based on a labeled dataset. In this work, we experimented with many machine learning algorithms to discover the best classifier for the Brazilian federal road hotspots associated with severe or nonsevere accident risk using several features. We tested with SVM, random forest, and a multi-layer perceptron neural network. The dataset contains a ten-year road accident report by the Brazilian Federal Highway Police. The feature set includes spatial footprint, weekday and time when the accident happened, road type, route, orientation, weather conditions, and accident type. The results were promising, and the neural network model provided the best results, achieving an accuracy of 83%, a precision of 84%, a recall of 83%, and an F1-score of 82%.

show abstract

Data Analytics Process over Road Accidents Data—A Case Study of Lisbon City

Cited by 24 publications

References 26 publications

The Impact of Road Geometric Formation on Traffic Crash and Its Severity Level

The Impact of Road Geometric Formation on Traffic Crash and Its Severity Level

Evaluation of factors affecting the number of traffic accidents

A Machine Learning Approach for Classifying Road Accident Hotspots

Contact Info

Product

Resources

About