Research

Research Interest

Traffic Safety
Traffic Operation
Naturalistic Driving
Human Factors
Big Data Analytics
Data Mining
Machine Learning
Intelligent Transportation Systems

Research Projects

1. Automated Integrating Human Behavior toward the Development of Safer Cooperative Automated Transportation: Implementation of SHRP2 Naturalistic Driving Study, Funded by USDOT-FHWA and WYDOT.

(2021 - Present)

Project Tasks

Collecting and processing data from SHRP 2 NDS and Wyoming Connected Vehicle Pilot Deployment Program.
Conducting in-depth investigations of driver behavior under various weather and traffic condition to detect deviation from normal driving and pattern leading to crashes/ near-crashes.
Development of Cooperative Automated Transportation (CAT) algorithms based on Behavior Cloning and testing the algorithms in microsimulation platform.
Publishing and presenting academic papers and preparing technical reports for the implementation of the study.

Below is the journal publication related to this project:

A Deep Learning Approach for Detecting Lane Change Maneuvers Using SHRP2 Naturalistic Driving Data. (Under Review)

Cluster Analysis and Multi-level Modeling for Evaluating the Impact of Rain on Aggressive Lane-changing Characteristics. (In-Press)

2. Automated Real-Time Weather Detection System using Artificial Intelligence, Funded by WYDOT.

(2021 - Present)

Project Tasks

Collecting video recordings under various weather conditions from the webcams installed in the Wyoming road networks as well as from WYDOT snowplows.
Developing automatic real-time weather and surface detection algorithms using various Machine Learning and Artificial Intelligence algorithms.
Processing and annotating image datasets describing the classification of weather conditions.
Providing WYDOT with a practice-ready automatic weather detection system and a user manual.
Publishing and presenting academic papers and preparing technical reports for the implementation of the study.

Below is the journal publication related to this project:

Weather and Surface Condition Detection based on Road-Side Webcams: Application of Pre-trained Convolutional Neural Network.

Machine and Deep Learning Techniques for Daytime Fog Detection in Real-Time Using In-Vehicle Vision System Utilizing the SHRP2 Naturalistic Driving Study Data. (In-Press)

3. Driver Performance and Behavior in Adverse Weather Conditions: An Investigation Using the SHRP2 Naturalistic Driving Study Data, Funded by USDOT–FHWA and WYDOT.

(2016 - 2021)

Project Tasks

Investigated driver performance and behavior in adverse weather conditions aiming at improving the safety and mobility of rural freeways.
Developed machine and deep learning-based weather detection models leveraging trajectory-level video data.
Enhanced the existing weather-based VSL algorithms in Wyoming using emerging trajectory-level weather and human behavior data.
Published and presented academic papers and prepared technical reports for the implementation of the study.
Delivered technical assistance to several clients, including the US DOTs, FHWA, and WYDOT.

Below are the journal publication related to this project:

Global Lessons Learned from Naturalistic Driving Studies to Advance Traffic Safety and Operation Research: A Systematic Review.

Nonparametric Multivariate Adaptive Regression Splines Models for Investigating Lane-Changing Gap Acceptance Behavior Utilizing Strategic Highway Research Program 2 Naturalistic Driving Data.

Detecting Lane Change Maneuvers Using SHRP2 Naturalistic Driving Data: A Comparative Study Machine Learning Techniques.

Non-Parametric Association Rules Mining and Parametric Ordinal Logistic Regression for an In-Depth Investigation of Driver Speed Selection Behavior in Adverse Weather Using SHRP2 Naturalistic Driving Study Data.

Investigating the Impact of Fog on Freeway Speed Selection Using the SHRP2 Naturalistic Driving Study Data.

Snow Detection Using In-Vehicle Video Camera with Texture-Based Image Features Utilizing K-Nearest Neighbor, Support Vector Machine, and Random Forest.

Trajectory-Level Fog Detection Based on in-Vehicle Video Camera with TensorFlow Deep Learning Utilizing SHRP2 Naturalistic Driving Data.

Development of a Novel Convolutional Neural Network Architecture Named RoadweatherNet for Trajectory-Level Weather Detection using SHRP2 Naturalistic Driving Data.

Multilevel Weather Detection Based on Images: A Machine Learning Approach with Histogram of Oriented Gradient and Local Binary Pattern Based Features.

4. Application Development and Participant Training for Wyoming Connected Vehicle Pilot Deployment Program, Funded by USDOT–FHWA.

(2018 - 2019)

Project Tasks

Operated the driving simulator lab (WyoSafeSim).
Conducted different study sessions at the simulator lab, ran the driving simulator experiments for the recruited participants, and collected the data from the driving simulator.

5. Hazardous Materials Commodity Flow Study in Wyoming, Funded by SERC and WOHS.

(2017 - 2021)

Project Tasks

Participated in designing the plan for data collections
Collected HAZMAT traffic data on different locations of Natrona, Sweetwater, Goshen, Niobrara, and Sheridan counties in Wyoming.
Published and presented academic papers and prepared technical reports for the implementation of the study.

Below is the journal publication related to this project:

Development of a Novel Framework for Hazardous Materials Placard Recognition System to Conduct Commodity Flow Studies Using Artificial Intelligence AlexNet Convolutional Neural Network.