Sanjana Hossain

Bus service quality prediction and attribute ranking: a neural network approach

Evaluation of service quality (SQ) based on user preferences has become a primary concern for the transportation authorities. The most significant attributes of public transportation systems are revealed through service quality analysis. This information serves as valuable input in constantly updating the quality of public transportation services. An appropriate tool is therefore mandatory in this regard. This paper represents a comparative study on the bus SQ prediction capabilities of three effective Artificial Neural Network (ANN) approaches, namely: Generalized Regression Neural Network (GRNN), Probabilistic Neural Network (PNN) and Pattern Recognition Neural Network (PRNN). To calibrate the parameters of the developed ANN models, data on users’ perception toward bus services of Dhaka city, Bangladesh, have been used. Taking the public opinion as baseline, GRNN and PNN have proven to be better prediction models since both have achieved higher accuracy compared to PRNN. Among 22 selected SQ attributes, the most significant attributes have been ranked according to their influence on the users’ decision making process. According to the GRNN and PNN models, punctuality and reliability, service frequency, seat availability and commuting experience are found to be the most significant attributes, which support the user-stated preferences.

Structural equation modeling of user satisfaction of bus transit service quality based on stated preferences and latent variables

ABSTRACT Few studies have been conducted on the service quality (SQ) of bus transit in developing countries. This paper presents a structural equation modeling (SEM) approach to identifying the relationships among major attributes that affect the SQ of bus transit in the city of Dhaka in Bangladesh. Specifically, 22 bus transit SQ attributes, drawn from 655 questionnaires, are used to develop different SEM models for the city. Along with stated preferences, the effect of three latent variables on SQ is analyzed. Among the developed models, the best model is selected by using different statistical approaches. With the best model, selected attributes are rated according to their relative importance on SQ. Acknowledging limited resources of a developing nation, this study gives a clear way ahead to planners, operating companies and transport managers to design appropriate transport policies which will ensure more effective services to current bus users as well as attracting new passengers.

Pixel-based heterogeneous traffic measurement considering shadow and illumination variation

This paper endeavors to develop a new background estimation model for foreground segmentation using traditional background subtraction technique. Particularly, incorporation of luminance- and pollution-controlling parameters enables the model to address illumination variation and tail backs from vehicles, respectively. To classify each foreground pixel, a new heuristic dynamic threshold-difference function is proposed for determining individual threshold. Moreover, newly presented Positive Negative Segmentation technique removes shadow considering its physical characteristics from the foreground. After shadow correction, impulse flow waves and aggregated pictorial speed are computed accordingly. Impulse flow waves are eventually rectified and cumulated into actual flow. Pictorial speed is converted into actual speed using calibration equation considering perspective error. To facilitate video-based traffic measurement, a user-friendly tool PARTS (Pixel-Based Heterogeneous Traffic Measurement) is developed which incorporates the whole system. The data collected at different roadway locations are compared with that generated by the tool. It shows 90 and 97% correlations in measuring flow and speed, respectively.