Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data become available. The primary goal of this thesis is to develop mode choice models using artificial neural networks and compare the results with traditional mode choice models like the multinomial logit model and linear regression method. The data used for this modeling is extracted from the American Travel Survey data. Data mining procedures like clustering are used to process the extracted data. The results of three models are compared based on residuals and error criteria. It is found that neural network approach produces the best results for the chosen set of explanatory variables. The possible reasons for such results are identified and explained to the extent possible. The three major objectives of this thesis are to: present an approach to handle the data from a survey database, address the mode choice problem using artificial neural networks, and compare the results of this approach with the results of traditional models vis-à-vis logit model and linear regression approach. The results of this research work should encourage more transportation researchers and professionals to consider artificial intelligence tools for solving transportation planning problems. / Master of Science

A model that can be used to analyze both current and future high-speed rail corridors is presented in this work. This model has been integrated into the Transportation Systems Analysis Model (TSAM). The TSAM is a model used to predict travel demand between any two locations in the United States, at the county level. The purpose of this work is to develop tools that will create the necessary input data for TSAM, and to update the model to incorporate passenger rail as a viable mode of transportation. This work develops a train dynamics model that can be used to calculate the travel time and energy consumption of multiple high-speed train types while traveling between stations. The work also explores multiple options to determine the best method of improving the calibration and implementation of the model in TSAM. For the mode choice model, a standard C logit model is used to calibrate the mode choice model. The utility equation for the logit model uses the decision variables of travel time and travel cost for each mode. A modified utility equation is explored; the travel time is broken into an in-vehicle and out-of-vehicle time in an attempt to improve the model, however the test determines that there is no benefit to the modification. In addition to the C-logit model, a Box-Cox transformation is applied to both variables in the utility equation. This transformation removes some of the linear assumptions of the logit model and thus improves the performance of the model. The calibration results are implemented in TSAM, where both existing and projected high-speed train corridors are modeled. The projected corridors use the planned alignment for modeling. The TSAM model is executed for the cases of existing train network and projected corridors. The model results show the sensitivity of travel demand by modeling the future corridors with varying travel speeds and travel costs. The TSAM model shows the mode shift that occurs because of the introduction of high-speed rail. / Master of Science

A tool to model both current rail and future high-speed rail (HSR) corridors has been presented in this work. The model is designed as an addition to the existing TSAM (Transportation System Analysis Model) capabilities of modeling commercial airline and automobile demand. TSAM is a nationwide county to county multimodal demand forecasting tool based on the classical four step process. A variation of the Box-Cox logit model is proposed to best capture the characteristic behavior of rail demand in US. The utility equation uses travel time and travel cost as the decision variables for each model. Additionally, a mode specific geographic constant is applied to the rail mode to model the North-East Corridor (NEC). NEC is of peculiar interest in modeling, as it accounts for most of the rail ridership. The coefficients are computed using Genetic Algorithms. A one county to one station assignment is employed for the station choice model. Modifications are made to the station choice model to replicate choices affected by the ease of access via driving and mass transit. The functions for time and cost inputs for the rail system were developed from the AMTRAK website. These changes and calibration coefficients are incorporated in TSAM. The TSAM model is executed for the present and future years and the predictions are discussed. Sensitivity analysis for cost and speed of the predicted HSR is shown. The model shows the market shift for different modes with the introduction of HSR. Limited data presents the most critical hindrance in improving the model further. The current validation process incorporates essential assumptions and approximations for transfer rates, short trip percentages, and access and egress distances. The challenges for the model posed by limited data are discussed in the model. / Master of Science