The Experts below are selected from a list of 16320 Experts worldwide ranked by ideXlab platform
Jianfeng Liu - One of the best experts on this subject based on the ideXlab platform.
-
mining smart card data for transit riders Travel Patterns
Transportation Research Part C-emerging Technologies, 2013Co-Authors: Yaojan Wu, Yinhai Wang, Feng Chen, Jianfeng LiuAbstract: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
2013Co-Authors: Yinhai Wang, Feng Chen, Jianfeng LiuAbstract: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.
Yinhai Wang - One of the best experts on this subject based on the ideXlab platform.
-
urban spatial structure and Travel Patterns analysis of workday and holiday Travel using inhomogeneous poisson point process models
Computers Environment and Urban Systems, 2019Co-Authors: Shen Zhang, Jinjun Tang, Shaowu Cheng, Yinhai WangAbstract:Abstract City land-use features and Travel behavior are mutually related and restricted. This research attempts to model the spatial-temporal Travel Patterns based on spatial point Pattern theory. Using a twelve-day private automobile data set collected in Beijing, we systematically investigate the temporal variations of trip-destination distributions, and their association with city spatial structure. The availability of detailed POIs (Points of Interest) data enables us to study the effect of city structure on Travel Pattern at a refined level. Four types of inhomogeneous Poisson point process models are built to capture the impacts on human mobility posed by spatial covariates. Residual analysis, inhomogeneous K function and leverage diagnostic tools are further adopted to validate the model performance and determine the best fitted model. The validation results indicate that the proposed model reasonably explains the Travel Patterns in both holiday and workday throughout the city. The inclusion of Cartesian coordinates, population distribution, and city subdivision-category improves the model performance. The empirical results based on the dataset also reveal the differences in impacts on Travel Patterns posed by underlying city structure between holidays and weekdays as well as between citywide districts. The modeling method and the exploratory spatial–temporal analysis in this study can offer complementary techniques for traffic management and urban planning.
-
mining smart card data for transit riders Travel Patterns
Transportation Research Part C-emerging Technologies, 2013Co-Authors: Yaojan Wu, Yinhai Wang, Feng Chen, Jianfeng LiuAbstract: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
2013Co-Authors: Yinhai Wang, Feng Chen, Jianfeng LiuAbstract: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.
-
pedestrian Travel Pattern discovery using mobile bluetooth sensors
Transportation Research Board 91st Annual MeetingTransportation Research Board, 2012Co-Authors: Yegor Malinovskiy, Yinhai WangAbstract:The ubiquity of mobile devices, coupled with their need to communicate wirelessly, provides a wealth of data that, if properly handled, can be used to quickly enhance understanding and recognition of transport Patterns. This dataset provides an opportunity to create a very low maintenance sensor infrastructure that is scalable and inexpensive. This paper presents a proof of concept experiment for a new mobile device-based framework for transportation data collection and interpretation. A novel “app-based” sensing paradigm, which turns smartphones into Bluetooth sensors, is developed, tested, and evaluated in this study for the purposes of Travel data collection and analysis. Of particular interest are the spatial and temporal Patterns that evolve as a result of daily human activity in very dense urban cores and campuses, where non-motorized modes dominate. The test results indicate that this new data collection framework is effective and has great potential for future pedestrian Travel Pattern discovery and activity data collection.
Frank Witlox - One of the best experts on this subject based on the ideXlab platform.
-
inferring temporal motifs for Travel Pattern analysis using large scale smart card data
Transportation Research Part C-emerging Technologies, 2020Co-Authors: Da Lei, Xuewu Chen, Long Cheng, Lin Zhang, Satish V Ukkusuri, Frank WitloxAbstract:Abstract In this paper, we proposed a new method to extract Travel Patterns for transit riders from different public transportation systems based on temporal motif, which is an emerging notion in network science literature. We then developed a scalable algorithm to recognize temporal motifs from daily trip sub-sequences extracted from two smart card datasets. Our method shows its benefits in uncovering the potential correlation between varying topologies of trip combinations and specific activity chains. Commuting, different types of transfer, and other Travel behaviors have been identified. Besides, varying Travel-activity chains like “Home → Work → Post-work activity (for dining or shopping) → Back home” and the corresponding Travel motifs have been distinguished by incorporating the land use information in the GIS data. The analysis results contribute to our understanding of transit riders’ Travel behavior. We also present application examples of the Travel motif to demonstrate the practicality of the proposed approach. Our methodology can be adapted to Travel Pattern analysis using different data sources and lay the foundation for other Travel-Pattern related studies.
Zhengqiu Yang - One of the best experts on this subject based on the ideXlab platform.
-
a decision model of identifying user Travel Pattern based on the intelligent terminal sensor data
International Conference on Cloud Computing, 2016Co-Authors: Shuai Wang, Jiapeng Xiu, Chen Liu, Zhengqiu YangAbstract:The identification of user Travel Pattern has important research value for intelligent transportation. Intelligent terminal can supply GPS, acceleration sensors, pressure sensors data which can provide data base for the identification of user Travel Patterns. This paper research on a user Travel Pattern decision model based on the sensor data. The decision algorithm adopts decision tree algorithm based on ID3. Experiments data shows that this decision model is effective in identifying the Pattern of user's Travel.
-
CCIS - A decision model of identifying user Travel Pattern based on the intelligent terminal sensor data
2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS), 2016Co-Authors: Shuai Wang, Jiapeng Xiu, Chen Liu, Zhengqiu YangAbstract:The identification of user Travel Pattern has important research value for intelligent transportation. Intelligent terminal can supply GPS, acceleration sensors, pressure sensors data which can provide data base for the identification of user Travel Patterns. This paper research on a user Travel Pattern decision model based on the sensor data. The decision algorithm adopts decision tree algorithm based on ID3. Experiments data shows that this decision model is effective in identifying the Pattern of user's Travel.
Yaojan Wu - One of the best experts on this subject based on the ideXlab platform.
-
mining smart card data for transit riders Travel Patterns
Transportation Research Part C-emerging Technologies, 2013Co-Authors: Yaojan Wu, Yinhai Wang, Feng Chen, Jianfeng LiuAbstract: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.
