Noisy values detection and correction of traffic accident data

Deb, Rupam; Liew, Alan Wee‐Chung

doi:10.1016/j.ins.2018.10.002

Cited by 22 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…De Oña et al [74] also recommend using two or more data analysis techniques. The data heterogeneity can also be addressed by improving data quality through noise reduction, such as by using an algorithm called NoiseCleaner, suggested by Deb and Lew [75]. The review conducted by Gutierrez-Osorio and Pedraza [7] on using analytic algorithms and machine learning methods in traffic safety studies can be further referenced.…”

Section: Discussionmentioning

confidence: 99%

A review of accident data for traffic safety studies in Indonesia

Kusumastutie,

Patria,

Kusrohmaniah

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Accident data is a crucial indicator of traffic safety. This study investigates the use of accident data in traffic safety studies in Indonesia. The analysis was conducted on studies that met the eligibility criteria, which included using traffic accident data in Indonesia and articles published in Indonesian and English language journals or proceedings. The search was conducted on four databases: Garuda, Neliti, Google Scholar, and Scopus. The final selection resulted in 50 articles. The data analysis indicates the need for improvement in the number of studies, the utilization of data elements in investigations, supplement data, and data analysis techniques. In addition to providing recommendations to optimize the use of traffic accident data in future studies, this study also emphasizes the importance of improving the accuracy of traffic accident data.

show abstract

Section: Discussionmentioning

confidence: 99%

A review of accident data for traffic safety studies in Indonesia

Kusumastutie,

Patria,

Kusrohmaniah

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…The anomalous data may provide false information for the results analysis of a fatal urban traffic accident; thus, detecting abnormal data and recovering the missing data are both essential in data pre-processing. Many techniques have been proposed for outlier detection and correction: linear regression, neural network, decision trees, and the maximum likelihood estimation-based Bayesian dynamic linear model [21][22][23]. For missing value, mainly strategies are deletion, mean imputation [24], and data-driven imputation.…”

Section: Study On the Accident Data Processing Methodsmentioning

confidence: 99%

Data-Driven Analysis of Fatal Urban Traffic Accident Characteristics and Safety Enhancement Research

Zhang

et al. 2023

Sustainability

View full text Add to dashboard Cite

The occurrence of fatal traffic accidents often causes serious casualties and property losses, endangering travel safety. This work uses the statistical data of fatal road traffic accidents in Shenzhen from 2018 to 2022 as the basis to determine the characteristic patterns and the main influencing factors of the occurrence of fatal road traffic accidents. The accident description data are also analyzed using the analysis method based on Term Frequency-Inverse Document Frequency (TF-IDF) data mining to obtain the characteristics of accident fields, objects, and types. Furthermore, this work conducts a kernel density analysis combined with spatial autocorrelation to determine the hotspot areas of accident occurrence and analyze their spatial aggregation effects. A principal component analysis is performed to calculate the factors related to the accident subjects. Results showed that weak safety awareness of motorists and irregular driving operations are the main factors for the occurrence of accidents. Finally, targeted safety management strategies are proposed based on the analysis results. In the current data era, the research results of this paper can be used for the prevention and emergency of accidents to formulate corresponding measures, and provide a theoretical basis for decision making.

show abstract

“…The time sequence of traffic flow parameters not only contains regular fluctuations, but also has its own random fluctuations ( 21 ). The existence of randomness in a single sample will greatly interfere with traffic pattern extraction and law learning, reduce prediction performance, and even cause subsequent misjudgment of traffic state.…”

Section: Methodsmentioning

confidence: 99%

Graph Spatiotemporal Pattern Learning Network for Real-Time Road Network Traffic Abnormal Incident Detection

Li,

Ma,

Wang

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

To improve the efficiency of detecting abnormal traffic incidents on the road network and reduce the false alarm rate, a real-time traffic anomaly detection framework based on a graph spatiotemporal pattern learning (GSTPL) network is proposed. In this framework, a traffic pattern search algorithm based on a fluctuation similarity measure is designed to screen traffic flow data with the same traffic pattern, and a traffic pattern graph tuple is constructed as the input of the network model to avoid the sample imbalance problem and the effect of single-sample randomness for traffic pattern learning. Then the GSTPL network is designed to extract, unsupervised, the traffic spatiotemporal pattern features and make a reasonable prediction of future traffic parameters as the basis for anomaly evaluation. To further restrain the effect of random fluctuations in traffic flow parameters, an abnormal state evaluation method is designed to calculate the anomaly state likelihood by prediction error distribution learning. The overall detection framework realizes stable prediction of network key node traffic parameters by using spatiotemporal pattern features to construct the traffic pattern graph tuple, and gives incident evaluation results in real time by combination with the detection data. The experiment uses I90 and I405 highway traffic data in Seattle, WA, from 2015. Through comparative analysis, the proposed incident detection method based on GSTPL has a higher detection rate and lower false alarm rate, can adaptively learn dynamic changes of the traffic pattern, and has strong adaptability and stability to different traffic environments.

show abstract

Noisy values detection and correction of traffic accident data

Cited by 22 publications

References 14 publications

A review of accident data for traffic safety studies in Indonesia

A review of accident data for traffic safety studies in Indonesia

Data-Driven Analysis of Fatal Urban Traffic Accident Characteristics and Safety Enhancement Research

Graph Spatiotemporal Pattern Learning Network for Real-Time Road Network Traffic Abnormal Incident Detection

Contact Info

Product

Resources

About