Yao Jan Wu

Bio: Yao Jan Wu is an academic researcher from University of Arizona. The author has contributed to research in topics: Intelligent transportation system & Public transport. The author has an hindex of 23, co-authored 95 publications receiving 1860 citations. Previous affiliations of Yao Jan Wu include University of Washington & National Taiwan University.

Mining smart card data for transit riders’ travel patterns

Abstract: To mitigate the congestion caused by the ever increasing number of privately owned automobiles, public transit is highly promoted by transportation agencies worldwide. A better understanding of travel patterns and regularity at the “magnitude” level will enable transit authorities to evaluate the services they offer, adjust marketing strategies, retain loyal customers and improve overall transit performance. However, it is fairly challenging to identify travel patterns for individual transit riders in a large dataset. This paper proposes an efficient and effective data-mining procedure that models the travel patterns of transit riders in Beijing, China. Transit riders’ trip chains are identified based on the temporal and spatial characteristics of their smart card transaction data. The Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm then analyzes the identified trip chains to detect transit riders’ historical travel patterns and the K-Means++ clustering algorithm and the rough-set theory are jointly applied to cluster and classify travel pattern regularities. The performance of the rough-set-based algorithm is compared with those of other prevailing classification algorithms. The results indicate that the proposed rough-set-based algorithm outperforms other commonly used data-mining algorithms in terms of accuracy and efficiency.

Mining Smart Card Data for Transit Riders’ Travel Patterns

Abstract: To mitigate congestion caused by the increasing number of privately owned automobiles, public transit is highly promoted by transportation agencies worldwide. With a better understanding of the travel patterns and regularity (the “magnitude” level of travel pattern) of transit riders, transit authorities can evaluate the current transit services to adjust marketing strategies, keep loyal customers and improve transit performance. However, it is fairly challenging to identify travel pattern for each individual transit rider in a large dataset. Therefore, this paper proposes an efficient and effective data-mining approach that models the travel patterns of transit riders using the smart card data collected in Beijing, China. Transit riders’ trip chains are identified based on the temporal and spatial characteristics of smart card transaction data. Based on the identified trip chains, the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is used to detect each transit rider’s historical travel patterns. The K-Means++ clustering algorithm and the rough-set theory are jointly applied to clustering and classifying the travel pattern regularities. The rough-set-based algorithm is compared with other classification algorithms, including Naive Bayes Classifier, C4.5 Decision Tree, K-Nearest Neighbor (KNN) and three-hidden-layers Neural Network. The results indicate that the proposed rough-set-based algorithm outperforms other prevailing data-mining algorithms in terms of accuracy and efficiency.

Origin-destination pattern estimation based on trajectory reconstruction using automatic license plate recognition data

Abstract: Origin-destination (OD) pattern estimation is a vital step for traffic simulation applications and active urban traffic management. Many methods have been proposed to estimate OD patterns based on different data sources, such as GPS data and automatic license plate recognition (ALPR) data. These data can be used to identify vehicle IDs and estimate their trajectories by matching vehicles identified by different sensors across the network. OD pattern estimation using ALPR data remains a challenge in real-life applications due to the difficulty in reconstructing vehicle trajectories. This paper proposes an offline method for historical OD pattern estimation based on ALPR data. A particle filter is used to estimate the probability of a vehicle’s trajectory from all possible candidate trajectories. The initial particles are generated by searching potential paths in a pre-determined area based on the time geography theory. Then, the path flow estimation process is conducted through dividing the reconstructed complete trajectories of all detected vehicles into multiple trips. Finally, the OD patterns are estimated by adding up the path flows with the same ODs. The proposed method was implemented on a real-world traffic network in Kunshan, China and verified through a calibrated microscopic traffic simulation model. The results show that the MAPEs of the OD estimation are lower than 19%. Further investigation shows that there exists a minimum required ALPR sampling rate (60% in the test network) for accurately estimating the OD patterns. The findings of this study demonstrate the effectiveness of the proposed method in OD pattern estimation.

Field Experiments on Bluetooth-Based Travel Time Data Collection

Abstract: Recently, a new Bluetooth-based travel time data collection approach has been gaining momentum in the transportation research community. This approach relies on identifying and matching the median access control (MAC) address of each Bluetooth device carried by bypassing vehicles for travel time data collection. Although there have been several studies documenting such data collection techniques, little research has been done regarding the inherent error rate of these devices. Furthermore, the use of multiple devices in tandem to improve results has not been fully investigated. This paper compares Bluetooth MAC address-based travel-time sensors developed by the authors with standard automatic license plate recognition (ALPR) devices commonly used for travel time data collection. Two types of antennae, omni-directional and directional, were tested to determine the effects of antenna selection on travel time data collection. Omni-directional sensors were found to have a larger detection zone than the directional sensors and are subject to more noise and bigger spatial errors, as a vehicle may be detected anywhere within the zone. Meanwhile, a larger detection zone also corresponds to a bigger sample size. Our test results indicate that although the Bluetooth sensors tended to be biased towards slower vehicles, the travel time measurements obtained were representative of the ground truth travel-time data measured by the ALPRs. There is great potential to apply this approach for cost-effective travel time data collection.

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

Abstract: Neural networks have been extensively applied to short-term traffic prediction in the past years. This study proposes a novel architecture of neural networks, Long Short-Term Neural Network (LSTM NN), to capture nonlinear traffic dynamic in an effective manner. The LSTM NN can overcome the issue of back-propagated error decay through memory blocks, and thus exhibits the superior capability for time series prediction with long temporal dependency. In addition, the LSTM NN can automatically determine the optimal time lags. To validate the effectiveness of LSTM NN, travel speed data from traffic microwave detectors in Beijing are used for model training and testing. A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.