Kyung Whan Kim

An Evaluation of Pedestrian Countdown Signals

In order to reduce complaints on the present pedestrian signal system and improve service to pedestrians, police installed pedestrian countdown signals at some crosswalks in selected cities for testing. This study was undertaken to evaluate the effects of pedestrian countdown signals in Korea and to compare the numeric and graphic countdown signals. The countdown signals had a positive effect on pedestrians and drivers compliance with the flashing Walking Person signal. A potential drawback for the countdown signals, however, is that more pedestrians remain on the crosswalk after the Standing Person signal appears. Comparing the two types of countdown signals revealed that the numeric countdown is more desirable than the graphic countdown for pedestrians compliance with the flashing Walking Person signal. But, the graphic countdown is more desirable than the numeric countdown for finishing crossing before the Standing Person signal appears and for drivers compliance with the flashing Walking Person signal. Further research is necessary to determine which of the two types of countdown signals is more effective. Sixty-two percent of the pedestrians surveyed claimed they were comfortable with the countdown signals. Likewise, Seventy-two percent of the respondents said countdown signals were helpful in determining walking speed. Sixty-eight percent also thought that countdown signals helped them decide whether to enter the crosswalk. Seventy-five percent preferred countdown signals to conventional signals, while sixty-nine percent preferred the numeric to the graphic countdown signal.

Forecast of domestic air travel demand change by opening the high speed rail

In Korea, the Seoul-Busan High Speed Rail (HSR) of which length is 430.7 km is under construction with plan to complete at the end of 2011. Therefore, there will be great change at modal split of this corridor travel, especially at air travel denand. This study forecasted the air travel demand changes of Seoul-Busan and Seoul-Daegu airlines which are competitive with the HSR. The result of this study can be used for airline companies to prepare the impact and for government to adjust the domestic air transportation planning. First, studies were conducted to establish a modal split model of regional transit travel by using the travel data between Seoul and 8 regional cities where the airplane, express train and express bus are mutually competitive. For the model, abstract, Logit and neural network models were analyzed, and the best result was obtained at the neural network model. The model has an input layer, 4 hidden layers and an output layer. The input units consists of travel time, travel cost, number of service frequency and number of seats of regional transit modes such as express bus, express train and airplane, and the hidden layers have 8 neurons. Using the neural network model, the travel demands of Seoul-Busan and Seoul-Daegu airlines in the horizon year when the HSR would begin service were estimated. Due to the HSR opening, the demand of Seoul-Busan airline is forecasted to decrease by 69.5% and the demand of the Seoul-Daegu airline is forecasted to decrease by 59.0%.

Normalization methods on backpropagation for the estimation of driver's route choice

The artificial neural network has recently been applied in many areas including transport engineering and planning. Even though its successful application for wide transportation areas, there are some major issues to be considered before using the neural network models, such as the network topology, learning parameter, and normalization methods for the input vectors. In this research, se veral normalization methods for input vectors were studied and the experimental results showed that the performance of the driers ro ute choice model using the neural networks was dependent on the normalization methods. For the estimation of drivers route choice, the best normalization method in the Backpropagation neural network model was suggested in this study.