Walking is an essential sustainable mode of transportation. Encouraging to increase walking trips can bring various social and economic benefits to our society. Since the policy paradigm has been shifting from car-oriented to pedestrian-oriented, interest in securing pedestrian rights and improving walking environments is increasing significantly. This study aims to examine factors affecting pedestrian satisfaction according to land use and street type. A pedestrian satisfaction survey was conducted in an industrial city with a mid-size population in the city of Changwon, South Korea. Based on the survey data from 500 respondents, factors affecting pedestrian satisfaction were analyzed by land use (commercial or residential areas) and street type (non-separated or separated sidewalks). The analysis results, using binary and ordered logit models, showed that the less illegal parking, the more pedestrian space, pedestrian guidance facility, and green space, the higher the pedestrian satisfaction. Factors positively affecting the satisfaction of pedestrian paths according to land use were physical environmental variables, such as the separated sidewalk variable. In commercial areas, pedestrian guidance facilities and street cleanliness were included as major influencing factors, implying differences in land use influencing factors. A common factor affecting the satisfaction of separated or non-separated sidewalk cases was also identified as the sufficiency of walking space. Therefore, the most urgent policy measure for improving pedestrian satisfaction for the city was to install a sidewalk or expand the pedestrian space. In the pedestrian-vehicle separation models, green space and cleanliness were included as significant variables, and in the non-separated models, variables of pedestrian guidance facilities and sidewalk conditions were included.

Recently, local governments have been using transportation card data to monitor the use of public transport and improve the service. However, local governments that are applying a single-fare scheme are experiencing difficulties in using data for accurate identification of real travel patterns or policy decision support due to missing information on alighting stops of users. This policy limits its functionality of utilizing data such as accurate identification of real travel patterns, policy decision support, etc. In order to overcome these limitations, various methods for estimating alighting stops have been developed. This study classifies trips with missing alighting stop information into trip four types and then applies appropriate alighting stop estimation methodology for each trip type in stages. The proposed method is evaluated by utilizing transportation card data of the Seoul metropolitan area and checking the accuracy for each standard of allowable error for sensitivity analysis. The analysis shows that the stage-by-stage estimation methodology based on the trip type proposed in this study can estimate users’ destinations more accurately than the methodologies of previous studies. Furthermore, based on the construction of nearly 100% valid tag data, this study differs from prior studies.

Short-term traffic prediction has been an essential part of real-time applications in modern transportation systems for the last few decades. Despite the recent progress in the voluminous models and data sources, many existing studies have focused on prediction for either a single or a few locations. In addition, the spatiotemporal dependency in the traffic data was narrowly accounted for. Therefore, this paper finds a new short-term traffic speed prediction algorithm that can efficiently cope with the complexity and immensity of the prediction process derived from the network size and amount of data in order to provide accurate predictions in real time. This algorithm consists of two modules: (a) principal component analysis (PCA) for data dimensionality reduction and feature selection, and (b) multichannel singular spectral analysis (MSSA) for multivariate time-series data prediction. A large amount of traffic data is efficiently compressed by PCA with high accuracy, then used as an input in the multivariate time-series analysis. The algorithm was compared with a vector autoregressive (VAR) model to predict traffic speeds five minutes ahead for a 21.3-mile-long highway segment, using the traffic detector data, and for 451-mile-long segment, using probe-based speed data in Tennessee. The tested algorithm is found to provide accurate predictions with a computation time of less than one second without training. Furthermore, the algorithm shows a better prediction performance under congested flow conditions, compared to VAR. This indicates that the tested algorithm is suitable for real-time prediction and scalable for a large network analysis.