Causality in Urban Engineering
Studied causal relations and the effect of interventions in travel demand, electricity usage, and water consumption datasets using Causal Discovery and Causal Inference. Estimated Travel Choice Model by applying four Causal Discovery Algorithms, namely Peter-Clark (PC), Fast Causal Inference (FCI), Fast Greedy Equivalence Search (FGES), and Linear Non-Gaussian Acyclic Models (LiNGAM).
Comparing Rapid Transit Systems among Major U.S. Cities
Compared the access to rapid transit systems among the five most populated cities in the U.S., namely New York City, Los Angeles, Chicago, Houston, and Pheonix. Calculated the percentage of population living within half a miles of a rapid transit station Using Geographic Information System (GIS).
Autonomous vehicle Testing
Obtained Autonomous Vehicle Driverless License from Local Motors by successfully completing the Steward Training for a self-driving, electric and cognitive shuttle (Olli Bus). The training involved unmanned and manned operations, safety operations, data collection, charging, parking, loading, and unloading. Conducted Autonomous vehicle tests and Demonstrations, and prepared Observation Reports.
COVID Future Study
Conducted a nationwide online panel survey in the United States on transportation related attitudes and behavior before, during, and after COVID-19. Helped in project planning, survey design, survey deployment, data cleaning and analysis. The data is available online here. Learn more about the project and the data.
Border Crossing Delay Prediction at the U.S.-Canada Border
Predicted passenger cars’ traffic delays at the three Niagara Frontier Border Crossings for the next 60 minutes into the future using four deep learning techniques, namely Multilayer Perceptron (MLP), Convolutional Neural Networks (CNN), Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), and Gated Recurrent Unit Recurrent Neural Networks (GRU-RNN).