Homa Taghipour

Homa Taghipour

Auto-generated profile, based on publicly available information

Homa Taghipour

University of Illinois at Chicago 842 W Taylor Street 60607 Chicago IL 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
1 March 2020 in Accident Analysis & Prevention
Verified
Journal Article
Closed access
APAmir Bahador Parsa
Amir Bahador Parsa
Ali MovahediAli Movahedi
Ali Movahedi
HTHoma Taghipour
Homa Taghipour
SDSybil Derrible
Sybil Derrible
AMAbolfazl (Kouros) Mohammadian
Abolfazl (Kouros) Mohammadian

1 August 2019 in Accident Analysis & Prevention
Verified
Journal Article
Closed access
APAmir Bahador Parsa
Amir Bahador Parsa
HTHoma Taghipour
Homa Taghipour
SDSybil Derrible
Sybil Derrible
AMAbolfazl (Kouros) Mohammadian
Abolfazl (Kouros) Mohammadian

1 April 2022 in IATSS Research
Verified
Journal Article
Open access
HTHoma Taghipour
Homa Taghipour
APAmir Bahador Parsa
Amir Bahador Parsa
RCRishabh Singh Chauhan
Rishabh Singh Chauhan
SDSybil Derrible
Sybil Derrible
AMAbolfazl (Kouros) Mohammadian
Abolfazl (Kouros) Mohammadian

22 December 2019 in arXiv
Verified
Preprint
Open access
PDF file
APAmir Bahador Parsa
Amir Bahador Parsa
RCRishabh Singh Chauhan
Rishabh Singh Chauhan
HTHoma Taghipour
Homa Taghipour
SDSybil Derrible
Sybil Derrible
AMAbolfazl Mohammadian
Abolfazl Mohammadian
Accident detection is a vital part of traffic safety. Many road users suffer from traffic accidents, as well as their consequences such as delay, congestion, air pollution, and so on. In this study, we utilize two advanced deep learning techniques, Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs), to detect traffic accidents in Chicago. These two techniques are selected because they are known to perform well with sequential data (i.e., time series). The full dataset consists of 241 accident and 6,038 non-accident cases selected from Chicago expressway, and it includes traffic spatiotemporal data, weather condition data, and congestion status data. Moreover, because the dataset is imbalanced (i.e., the dataset contains many more non-accident cases than accident cases), Synthetic Minority Over-sampling Technique (SMOTE) is employed. Overall, the two models perform significantly well, both with an Area Under Curve (AUC) of 0.85. Nonetheless, the GRU model is observed to perform slightly better than LSTM model with respect to detection rate. The performance of both models is similar in terms of false alarm rate.

25 October 2016 in MATEC Web of Conferences
Verified
Journal Article
Open access
PDF file
HTHoma Taghipour
Homa Taghipour
YSYousef Shafahi
Yousef Shafahi
MATEC Web of Conferences, open access proceedings in Materials science, Engineering and Chemistry

1 September 2021
Verified
Report
Closed access
AMAbolfazl Mohammadian
Abolfazl Mohammadian
UCUniversity of Illinois at Chicago
University of Illinois at Chicago
APAmir Bahador Parsa
Amir Bahador Parsa
HTHoma Taghipour
Homa Taghipour
ADAmir Davatgari
Amir Davatgari
MMMotahare Mohammadi
Motahare Mohammadi
Reversible lanes in Chicago’s Kennedy Expressway are an available infrastructure that can significantly improve traffic performance; however, a special focus on congestion management is required to improve their operation. This research project aims to evaluate and improve the operation of reversible lanes in the Kennedy Expressway. The Kennedy Expressway is a nearly 18-mile-long freeway in Chicago, Illinois, that connects in the southeast to northwest direction between the West Loop and O’Hare International Airport. There are two approximately 8-mile reversible lanes in the Kennedy Expressway’s median, where I-94 merges into I-90, and there are three entrance gates in each direction of this corridor. The purpose of the reversible lanes is to help the congested direction of the Kennedy Expressway increase its traffic flow and decrease the delay in the whole corridor. Currently, experts in a control location switch the direction of the reversible lanes two to three times per day by observing real-time traffic conditions captured by a traffic surveillance camera. In general, inbound gates are opened and outbound gates are closed around midnight because morning traffic is usually heavier toward the central city neighborhoods. In contrast, evening peak-hour traffic is usually heavier toward the outbound direction, so the direction of the reversible lanes is switched from inbound to outbound around noon. This study evaluates the Kennedy Expressway’s current reversing operation. Different indices are generated for the corridor to measure the reversible lanes’ performance, and a data-driven approach is selected to find the best time to start the operation. Subsequently, real-time and offline instruction for the operation of the reversible lanes is provided through employing deep learning and statistical techniques. In addition, an offline timetable is also provided through an optimization technique. Eventually, integration of the data-driven and optimization techniques results in the best practice operation of the reversible lanes.