Branislav Dimitrijevic

Dr. Branislav Dimitrijevic

New Jersey Institute of Technology, Newark, NJ 07102, USA
orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
1 March 2003 in Journal of Public Transportation
Verified
Journal Article
Open access
PDF file
SCSteven Chien
Steven Chien
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
LSLazar Spasovic
Lazar Spasovic
Bus routing is one of the most important elements of public transit system planning. This article presents a model for optimizing service headway and a bus route serving an area with a commuter (many-to-one) travel pattern. The bus route is optimized by minimizing the total system cost, including operator and user costs, while considering diagonal links in the study network. A method is developed for transforming this network into a pure grid, which enables construction of pure grid network models applicable to irregular grid networks. A case is presented to demonstrate the application of the model. Results show that the optimal bus route is sensitive to demand distribution over the service area. The developed model is particularly useful for planning a new bus service and evaluating an existing one in many cities embedded with general grid networks.

14 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
SKSina Darban Khales
Sina Darban Khales
RARoksana Asadi
Roksana Asadi
Joyoung LeeJoyoung Lee
Joyoung Lee
Highway crashes, along with the property damage, personal injuries, and fatalities that they cause, continue to present one of the most significant and critical transportation problems. At the same time, provision of safe travel is one of the main goals of any transportation system. For this reason, both in transportation research and practice much attention has been given to the analysis and modeling of traffic crashes, including the development of models that can be applied to predict crash occurrence and crash severity. In general, such models assess short-term crash risks at a given highway facility, thus providing intelligence that can be used to identify and implement traffic operations strategies for crash mitigation and prevention. This paper presents several crash risk and injury severity assessment models applied at a highway segment level, considering the input data that is typically collected or readily available to most transportation agencies in real-time and at a regional network scale, which would render them readily applicable in practice. The input data included roadway geometry characteristics, traffic flow characteristics, and weather condition data. The paper develops, tests, and compares the performance of models that employ Random effects Bayesian Logistics Regression, Gaussian Naïve Bayes, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine methods. The paper applies random oversampling examples (ROSE) method to deal with the problem of data imbalance associated with the injury severity analysis. The models were trained and tested using a dataset of 10,155 crashes that occurred on two interstate highways in New Jersey over a two-year period. The paper also analyzes the potential improvement in the prediction abilities of the tested models by adding reactive data to the analysis. To that end, traffic crashes were classified in multiple classes based on the driver age and the vehicle age to assess the impact of these attributes on driver injury severity outcomes. The results of this analysis are promising, showing that the simultaneous use of reactive and proactive data can improve the prediction performance of the presented models.

4 June 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
RARoksana Asadi
Roksana Asadi
AKAfaq Khattak
Afaq Khattak
HVHossein Vashani
Hossein Vashani
HAHamad Almujibah
Hamad Almujibah
HRHelia Rabie
Helia Rabie
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
The identification of causative factors and implementation of measures to mitigate work zone crashes can significantly improve overall road safety. This study introduces a Self-Paced Ensemble (SPE) framework, which is utilized in conjunction with the Shapley additive explanations (SHAP) interpretation system, to predict and interpret the severity of work-zone-related crashes. The proposed methodology is an ensemble learning approach that aims to mitigate the issue of imbalanced classification in datasets of significant magnitude. The proposed solution provides an intuitive way to tackle issues related to imbalanced classes, demonstrating remarkable computational efficacy, praiseworthy accuracy, and extensive adaptability to various machine learning models. The study employed work zone crash data from the state of New Jersey spanning a period of two years (2017 and 2018) to train and evaluate the model. The study compared the prediction outcomes of the SPE model with various tree-based machine learning models, such as Light Gradient Boosting Machine, adaptive boosting, and classification and regression tree, along with binary logistic regression. The performance of the SPE model was superior to that of tree-based machine learning models and binary logistic regression. According to the SHAP interpretation, the variables that exhibited the highest degree of influence were crash type, road system, and road median type. According to the model, on highways with barrier-type medians, it is expected that crashes that happen in the same direction and those that happen at a right angle will be the most severe crashes. Additionally, this study found that severe injuries were more likely to result from work zone crashes that happened at night on state highways with localized street lighting.

1 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Abolfazl AfshariAbolfazl Afshari
Abolfazl Afshari
Joyoung LeeJoyoung Lee
Joyoung Lee
DBDejan Besenski
Dejan Besenski
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
LSLazar Spasovic
Lazar Spasovic
This study introduces a data-driven approach to calibrate microscopic traffic simulation models like VISSIM using high-resolution trajectory data, aiming to improve simulation accuracy and fidelity. The study focuses on a highway segment of NJ-3 and NJ-495 in Hudson County, New Jersey, selected as a case study for its high traffic volume and strategic significance. Trajectory data from 338 connected vehicles, sourced from the Wejo dataset, a global provider of anonymized, high-resolution vehicle movement data, along with traffic volume data from Remote Traffic Microwave Sensors (RTMS), served as inputs. The trajectories produced by the simulation model were compared to the ground truth to measure discrepancies. By adjusting driving behavior parameters (e.g., car-following and lane-changing behaviors) and other factors (e.g., desire speed), a Genetic Algorithm was adopted to minimize these differences. Results showed significant improvements, including a 14.19% reduction in mean error, an 18.27% reduction in median error, and a 22.57% reduction in the 75th percentile error during calibration. In the validation phase, the calibrated parameters yielded a 32.68% reduction in mean error, demonstrating the framework’s robustness. This study presents a scalable calibration framework using connected vehicle data, providing tools for accurate simulation, real-time traffic management, and infrastructure planning.

10 October 2022 in Interactive Learning Environments
Verified
Journal Article
Open access
PAPramod Abichandani
Pramod Abichandani
DLDeepan Lobo
Deepan Lobo
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
ABAshish Borgaonkar
Ashish Borgaonkar
JSJaskirat Sodhi
Jaskirat Sodhi
MKMoshe Kam
Moshe Kam
This paper presents a competition-based active learning approach that prepares undergraduate students for careers in the drone industry. The competition-based learning (CBL) approach focuses on preparing students for three key drone industry requirements (1) drone assembly, testing, and validation using commercial off-the-shelf (COTS) parts, (2) simulation of drone flight missions and (3) manual and semi-autonomous drone piloting. The CBL curricular modules were developed using the Interactive-Constructive-Active-Passive (ICAP) framework of cognitive engagement. These modules immersed students in the technical challenges corresponding to the three essential drone industry requirements. The approach was implemented through fourteen (14) drone workshops that culminated in a final drone piloting competition at a STEM research university in the United States. Ninety-seven (97) students from various backgrounds with little to no prior experience in building drones participated in the competition as part of 22 teams in total. Multiple assessment methods were used to evaluate the students' progress and the perceived drone-related skills gained by the end of the workshops. Assessment methods included data from direct formative (weekly or biweekly curricular milestones), direct summative (drone piloting for multiple flight tests), indirect quantitative (Likert-style feedback survey about student perceptions), and indirect qualitative (descriptive feedback comments) tools. Direct quantitative assessments indicated that most students successfully reached the technical milestones of the workshop sessions and gained practical drone piloting skills. The indirect quantitative assessment revealed that students perceived the workshops to be a valuable experience in their drone industry skills and knowledge. Indirect qualitative analysis of the feedback comments revealed that students perceived CBL as an engaging and effective method of introducing drone technology.

1 November 2020 in Canadian Journal of Civil Engineering
Verified
Journal Article
Closed access
SKSina Darban Khales
Sina Darban Khales
MKMehmet Metin Kunt
Mehmet Metin Kunt
Branislav DimitrijevicBranislav Dimitrijevic
Branislav Dimitrijevic
The study analyzed injury severity of teenage and older drivers using 2015–2016 crash data from New Mexico. The fitness of the random-parameter ordered probit models developed for each age group was tested using likelihood ratio, comparing them to a unified model that combines both age groups, as well as comparing the random-parameter to fixed-parameter ordered probit for each age group. In both cases separate random-parameter ordered probit provided better results. It was found that vehicle type and age, lighting condition, alcohol or drug use, speeding, and seatbelt use were significant both for the teenage and older driver injury severity. The weather condition and gender were significant only in the teenage driver model, while driver inattention was significant for older drivers. The impacts of crash factors on injury severity was analyzed using marginal effects. The results indicate notable differences in the effects of contributing factors on driver injury severity between teenage and older drivers, including the sensitivity to changes in the mutual predictor parameter values.