Abolfazl Karimpour

Abolfazl Karimpour

Auto-generated profile, based on publicly available information

Abolfazl Karimpour

College of Engineering, State University of New York Polytechnic Institute, Utica, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 January 2024 in Journal of Intelligent Transportation Systems
Verified
Journal Article
Closed access
XMXiaobo Ma
Xiaobo Ma
AKAbolfazl Karimpour
Abolfazl Karimpour
YWYao-Jan Wu
Yao-Jan Wu

18 July 2019 in IET Intelligent Transport Systems
Verified
Journal Article
Open access
PDF file
AKAbolfazl Karimpour
Abolfazl Karimpour
AAAmin Ariannezhad
Amin Ariannezhad
YWYao‐Jan Wu
Yao‐Jan Wu
Truck travel time data plays a critical role in freight performance measurement and is usually collected with probe‐vehicle technologies. However, due to low sampling rates, truck data usually suffers from missing values. The primary purpose of this study is to develop a hybrid model to accurately impute missing truck travel time data by leveraging multiple data sources. The proposed model imputes missing values by considering the interaction, similarity, and differences of the data as well as incorporating available historical information. The hybrid model achieves robust results by combining both probe vehicle and loop detector data to impute continuous missing truck travel time data in sparse datasets. The proposed model was used to impute missing truck travel time data in the National Performance Measures Research Dataset (NPMRDS). The imputation performance of the proposed model was compared with several popular imputation models including historical, spline interpolation, random forest, and bootstrapping EM. The results indicated that the proposed model was capable of imputing missing data in sparse datasets, notably when the data was missing continuously. With ∼13% mean‐absolute percentage error, the hybrid model outperformed other models in imputing an entire day of missing data.

1 March 2021 in Journal of Transportation Engineering, Part A: Systems
Verified
Journal Article
Closed access
PDF file
AAAmin Ariannezhad
Amin Ariannezhad
AKAbolfazl Karimpour
Abolfazl Karimpour
XQXiao Qin
Xiao Qin
YWYao-Jan Wu
Yao-Jan Wu
YSYasamin Salmani
Yasamin Salmani
With a growing number of intelligent transportation system sensors and the networkwide deployment of those across the nation’s roadway facilities, current research and practices should concentrate on more proactive safety strategies. In recent years, real-time traffic data collected from ITS sensors have been utilized to develop crash prediction models. Real-time crash prediction models can be used to identify hazardous traffic conditions that might cause a crash. This study aims to examine how employing data mining techniques that account for imbalanced data could improve the predictive capability of real-time crash prediction models. The term imbalanced data refers to a condition where the number of observations in each class is not equally distributed among the data set (noncrash cases outnumber crash cases). To decrease the within-class variation of imbalanced data, the data were split into two traffic-state data sets: free-flow speed (FFS) and congestion. Three models, including logistic regression as the baseline, random forest (RF) with random undersampling, and Adaptive Boosting (AdaBoost), were estimated with each data set. The results were compared with the models that were estimated using the complete set of data. Model comparisons indicated that all three models achieved significantly better predictive results with the congested and FFS data sets as opposed to the data set containing all crashes and that, while in some cases the results of the undersampled RF model were slightly better than those of AdaBoost, both models outperformed the logistic regression model. The results of this study demonstrated that using models to deal with imbalanced data and lowering the variation of imbalanced data could substantially improve crash prediction accuracy. The findings could help traffic agencies to practically implement and deploy crash prediction models for real-time applications and develop crash prevention strategies accordingly.

4 November 2016 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
AMAli Mansourkhaki
Ali Mansourkhaki
AKAbolfazl Karimpour
Abolfazl Karimpour
HYHadi Sadoghi Yazdi
Hadi Sadoghi Yazdi
This study aims to address two potential issues regarding accident prediction models. (a) What are the benefits of using the prior information on the accuracy of prediction model, and (b) how to include the available prior knowledge of accident occurrences data in the prediction process? In accident databases, the prior knowledge can be defined as the most probable points in which an accident has happened in the earlier years and is closely correlated to its upcoming years. Large databases such as traffic and accident databases, inevitably contain noisy data. Therefore, to have accurate results, using approaches to alleviate the impact of these anomalies is significant. In this research, a hybrid method based on a module of prediction and a prior knowledge block is proposed. The module used for prediction is Recursive Least Square filter and Maximum a Posterior (MAP) estimator is used as the prior knowledge block. Results indicate an increase in accuracy of prediction by using the proposed hybrid model.

1 June 2017 in Proceedings of the Institution of Civil Engineers - Transport
Verified
Journal Article
Closed access
AMAli Mansourkhaki
Ali Mansourkhaki
AKAbolfazl Karimpour
Abolfazl Karimpour
HYHadi Sadoghi Yazdi
Hadi Sadoghi Yazdi
This paper aims to develop a model to improve road safety based on the spatial and temporal features of accident occurrence. The spatial distribution characteristic of an accident follows a probability density function (PDF) that can be estimated with parametric functions. Estimating the PDF of accidents can help road specialists recognise accident-prone locations and improve road safety through countermeasures. In this study, the PDF of accidents is estimated using Gaussian mixture models. Gaussian models possess local and density information about accident distributions. For the prediction step, the parameters of the Gaussian models are predicted by means of a recursive least-squares approach. The major feature of this study is that the proposed model can accurately predict physical points where accidents are more likely to take place in the upcoming year. Moreover, because of the non-stationary feature of accidents, the proposed model is online, implying that it would update itself annually. The range of errors obtained from the results of cross-validation with existing data provides a very good indication of the accuracy of the proposed model.

8 August 2023 in Journal of Intelligent Transportation Systems
Verified
Journal Article
Closed access
XMXiaobo Ma
Xiaobo Ma
AKAbolfazl Karimpour
Abolfazl Karimpour
YWYao-Jan Wu
Yao-Jan Wu