Traffic accident risk classification using neural networks

Purkrábková, Zuzana; Růžička, Jiří; Bělinová, Zuzana; Korec, Vojtěch

doi:10.14311/nnw.2021.31.019

Cited by 7 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inspection team determines the severity of the risk based on their qualifications and experience. The circumstances involved in the occurrence of accidents are complex, and estimating the level of safety risks identified is a challenging task [14,15].…”

Section: Introductionmentioning

confidence: 99%

A Unified Approach for Risk Assessment of Road Crash Barriers Using Bayesian Statistics

et al. 2023

View full text Add to dashboard Cite

The aim of this article is to improve road safety. Specifically, it deals with the development of a mathematical model that will more accurately define the severity of a defect in a road restraint system. Currently, that evaluation is based only on the subjective perception of individual safety auditors. The mathematical model was developed based on the principle of Bayesian statistics. The determination of the specific risk was made by comparing the results of the model for two datasets. In the first case, the model was based on accident data correlated with recorded defects in road restraint systems. In the second case, the dataset represented accident events with crash barriers where no defect was identified. Based on the comparison, a total of 64 risk combinations were identified. The mathematical model confirmed 26 combinations (41% of all selected combinations of the defect levels of the crash barriers). Although not even half of the identified combinations were confirmed, more than 90% of all correlated records are found in these exposures of confirmed combinations. The verification was able to clearly define the risk of safety defects and thus brings potential accuracy to subsequent decision-making related to the repair of road restraint systems.

show abstract

Section: Introductionmentioning

confidence: 99%

A Unified Approach for Risk Assessment of Road Crash Barriers Using Bayesian Statistics

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Another extensive group of methods that have become popular in predicting traffic flow data due to its non-linear nature are machine learning algorithms [65]. In particular, these include artificial neural networks [31,33,43,55], support vector machines (SVM) [13,23,30,66,68], k-nearest neighbors [3,19,23,30,47], and random forests [8,10,47]. In contrast to statistical approaches, they provide higher accuracy and flexibility of traffic prediction.…”

Section: Introductionmentioning

confidence: 99%

Using Poisson proximity-based weights for traffic flow state prediction

Uglickich,

Nagy

2023

NNW

View full text Add to dashboard Cite

The development of traffic state prediction algorithms embedded in intelligent transportation systems is of great importance for improving traffic conditions for drivers and pedestrians. Despite the large number of prediction methods, existing limitations still confirm the need to find a systematic solution and its adaptation to specific traffic data. This paper focuses on the relationship between traffic flow states in different urban locations, where these states are identified as clusters of traffic counts. Extending the recursive Bayesian mixture estimation theory to the Poisson mixtures, the paper uses the mixture pointers to construct the traffic state prediction model. Using the predictive model, the cluster at the target urban location is predicted based on the traffic counts measured in real time at the explanatory urban location. The main contributions of this study are: (i) recursive identification and prediction of the traffic state at each time instant, (ii) straightforward Poisson mixture initialization, and (iii) systematic theoretical background of the prediction approach. Results of testing the prediction algorithm on real traffic counts are presented.

show abstract

Predictive analysis visualization component in simulated data streams

Dudáš,

Demian

2024

Discov Computing

View full text Add to dashboard Cite

One of the most significant problems related to Big Data is their analysis with the use of various methods from the area of descriptive statistics or machine and deep learning. This process is interesting in both—static datasets containing various data sources which do not change over time, and dynamic datasets collected with the use of ambient data sources, which measure a number of attribute values over long periods. Since access to actual dynamic data systems is demanding, the focus of this work is put on the design and implementation of a framework usable in a simulation of data streams, their processing and subsequent dynamic predictive and visual analysis. The proposed system is experimentally verified in the context of a case study conducted on an environmental variable dataset, which was measured with the use of a real-life sensor network.

show abstract

Traffic accident risk classification using neural networks

Cited by 7 publications

References 12 publications

A Unified Approach for Risk Assessment of Road Crash Barriers Using Bayesian Statistics

A Unified Approach for Risk Assessment of Road Crash Barriers Using Bayesian Statistics

Using Poisson proximity-based weights for traffic flow state prediction

Predictive analysis visualization component in simulated data streams

Contact Info

Product

Resources

About