kth.sePublications
Change search
Link to record
Permanent link

Direct link
Yang, Can, Ph.D. studentORCID iD iconorcid.org/0000-0001-5361-6034
Publications (10 of 10) Show all publications
Gidofalvi, G. & Yang, C. (2020). The potential of route based ERS network optimization. In: TRA (Ed.), TRA2020 Book of Abstracts: Proceedings of 8th Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland. Paper presented at Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland (pp. 1-12). , Article ID 960.
Open this publication in new window or tab >>The potential of route based ERS network optimization
2020 (English)In: TRA2020 Book of Abstracts: Proceedings of 8th Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland / [ed] TRA, 2020, p. 1-12, article id 960Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

The large scale deployment of Electric Road Systems (ERS) is a necessary and viable choice for reaching the emission reduction targets in the road-bound heavy freight sector. The per-kilometer infrastructure development cost of ERS is large, thus selecting segments that yield a high utility is important. According to a newly introduced concept, the electrification utility of a segment in a network is highly dependent on the freight routes-, the powertrain technology-, the energy supply and demand- and the transport loads of the vehicles as well as the topographic aspects- and traffic state of the road network. This paper explains these concepts and aspects and provides first empirical evidence about the potential of route based ERS network optimization that takes these aspects into consideration. Results show that the potential cost savings are up to 75%, which for national expressway networks is estimated to be in the range of 120M€ to 8,520M€.

National Category
Computer Sciences Information Systems Energy Systems Transport Systems and Logistics Infrastructure Engineering
Identifiers
urn:nbn:se:kth:diva-270700 (URN)
Conference
Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland
Funder
Swedish Transport Administration, 2016/81924
Note

QC 20200313

Available from: 2020-03-12 Created: 2020-03-12 Last updated: 2022-06-26Bibliographically approved
Gidofalvi, G. & Yang, C. (2020). The potential of route based ERS network optimization: Transport demand optimized electric road placement. In: : . Paper presented at Transportforum 2020, Linköping, Sweden, 8-9 January, 2020 (pp. 1-2). Linköping, Article ID 10.9.4.
Open this publication in new window or tab >>The potential of route based ERS network optimization: Transport demand optimized electric road placement
2020 (English)Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Background

The large scale deployment of Electric Road Systems (ERS) is a necessary and viable choice for reaching the emission reduction targets in the road-bound heavy freight sector. The per-kilometer infrastructure development cost of ERS is large, thus selecting segments that yield a high utility is important.

Current methods that utilize freight routes try to optimize the ERS network infrastructure based on the amount of freight routes that include a road segment / link based on select link analysis which, based on network assignment models / assumptions or real data, provides information of where traffic comes from and goes to at selected links, i.e., it provides the spatial distribution and origin–destination (OD) pair composition of aggregate link flows.

However, as it is suggested in a recent pre-study [1], it is not sufficient to select segments simply based on the number of routes that include the segment or based on the OD-information. In particular, different vehicle-powertrain-onboard and road charging technologies have different energy consumption, energy storage and charging characteristics. The energy consumption and charging characteristics of these vehicle-energy-technology configurations are also heavily affected by the load that they carry as well as the surface and 3D geometry of the roads that they are operated on. Finally, last but not least, as the vehicles have a finite energy storage and an objective to complete maximal part of their routes on electric energy, the electrification utility of segments / links in a network are not independent of one another, but largely depend on which part of the routes include the segments.

Method

To take the aforementioned aspects into account, the proposed methodology, adopts the newly introduced concept of Route Based Electrification Utility (RBEU) [1], which can be informally defined as the extra transport work that can be performed in electric operations because of the electrification of the segment in question. Given an infrastructure budget of N segments, to find the N segments that maximizes the electrification utility, the proposed Route based ERS Network Optimization (RENO) method first compresses and indexes the massive input set of vehicle trajectories (routes) and then utilizes this data structure to incrementally add segments to the partial solution that maximize the RBEU of the selection. To take into consideration of vehicle load, speed and road geometries two approaches are proposed: one based on GIS data and simulations and one based on vehicle fuel consumption as a proxy.

Results and Conclusions

Empirical evaluations on a real word data set 1) illustrate the superiority of the RENO method over the segment based optimization approach for a wide range of electrification scenarios and 2) analyze the characteristics of the solutions found by the RENO methodology. The potential infrastructure cost savings resulting from RENO are up to 75%, which for national expressway networks is estimated to be in the range of 120M€ (Sweden) to 8,520M€ (China).

Place, publisher, year, edition, pages
Linköping: , 2020
Keywords
Route analysis, combinatorial network optimization, electric roads, big mobility data analytics
National Category
Transport Systems and Logistics
Research subject
Transport Science, Transport Systems; Transport Science, Transport Infrastructure; Computer Science; Geodesy and Geoinformatics, Geoinformatics
Identifiers
urn:nbn:se:kth:diva-272076 (URN)
Conference
Transportforum 2020, Linköping, Sweden, 8-9 January, 2020
Projects
RENO: Route Based ERS Network Optimization
Note

QC 20200416

Available from: 2020-04-16 Created: 2020-04-16 Last updated: 2022-06-26Bibliographically approved
Cumbane, S. P., Yang, C. & Gidofalvi, G. (2019). A Framework for Traffic Prediction Integrated with Deep Learning. In: : . Paper presented at The 8th Symposium of the European Association for Research in Transportation.
Open this publication in new window or tab >>A Framework for Traffic Prediction Integrated with Deep Learning
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

City-scale traffic prediction is an important task for public safety, traffic management, and deployment of intelligent transportation systems. Many approaches have been proposed to address traffic prediction task using machine learning techniques. In this paper, we present a framework to help on addressing the task at hand (density-, traffic flow- and origin-destination flow predictions) considering data type, features, deep learning techniques such as Convolutional Neural Networks (CNNs), e.g., Autoencoder, Recurrent Neural Networks (RNNs), e.g., Long Short Term Memory (LSTM), and Graph Convolutional Networks (GCNs). An autoencoder model is designed in this paper to predict traffic density based on historical data. Experiments on real-world taxi order data demonstrate the effectiveness of the model.

National Category
Natural Sciences
Identifiers
urn:nbn:se:kth:diva-254200 (URN)
Conference
The 8th Symposium of the European Association for Research in Transportation
Note

QC 20190625

Available from: 2019-06-24 Created: 2019-06-24 Last updated: 2022-06-26Bibliographically approved
Yang, C. & Gidófalvi, G. (2019). Detecting regional dominant movement patterns in trajectory data with a convolutional neural network. International Journal of Geographical Information Science
Open this publication in new window or tab >>Detecting regional dominant movement patterns in trajectory data with a convolutional neural network
2019 (English)In: International Journal of Geographical Information Science, ISSN 1365-8816, E-ISSN 1365-8824Article in journal (Refereed) Published
Abstract [en]

Detecting movement patterns with complicated spatial or temporal characteristics is a challenge. The past decade has witnessed the success of deep learning in processing image, voice and text data. However, its application in movement pattern detection is not fully exploited. To address the research gap, this paper develops a deep learning approach to detect regional dominant movement patterns (RDMP) in trajectory data. Specifically, a novel feature descriptor called directional flow image (DFI) is firstly proposed to store the local directional movement information in trajectory data. A DFI classification model called TRNet is designed based on convolutional neural network. The model is then trained with a synthetic trajectory dataset covering 11 classes of commonly encountered movement patterns in reality. Finally, a sliding window detector is built to detect RDMP at multiple scales and a clustering-based merging method is proposed to prune the redundant detection results. Training of TRNet on the synthetic dataset achieves considerably high accuracy. Experiments on a real-world taxi trajectory dataset further demonstrate the effectiveness and efficiency of the proposed approach in discovering complex movement patterns in trajectory data.

Place, publisher, year, edition, pages
Taylor and Francis Ltd., 2019
Keywords
convolutional neural network, deep learning, Movement pattern
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:kth:diva-268454 (URN)10.1080/13658816.2019.1700510 (DOI)000502416100001 ()2-s2.0-85076374636 (Scopus ID)
Note

QC 20200409

Available from: 2020-04-09 Created: 2020-04-09 Last updated: 2024-03-18Bibliographically approved
Yang, C. & Gidofalvi, G. (2018). Mining and visual exploration of closed contiguous sequential patterns in trajectories. International Journal of Geographical Information Science, 32(7), 1282-1303
Open this publication in new window or tab >>Mining and visual exploration of closed contiguous sequential patterns in trajectories
2018 (English)In: International Journal of Geographical Information Science, ISSN 1365-8816, E-ISSN 1365-8824, Vol. 32, no 7, p. 1282-1303Article in journal (Refereed) Published
Abstract [en]

Large collections of trajectories provide rich insight into movement patterns of the tracked objects. By map matching trajectories to a road network as sequences of road edge IDs, contiguous sequential patterns can be extracted as a certain number of objects traversing a specific path, which provides valuable information in travel demand modeling and transportation planning. Mining and visualization of such patterns still face challenges in efficiency, scalability, and visual cluttering of patterns. To address these challenges, this article firstly proposes a Bidirectional Pruning based Closed Contiguous Sequential pattern Mining (BP-CCSM) algorithm. By employing tree structures to create partitions of input sequences and candidate patterns, closeness can be checked efficiently by comparing nodes in a tree. Secondly, a system called Sequential Pattern Explorer for Trajectories (SPET) is built for spatial and temporal exploration of the mined patterns. Two types of maps are designed where a conventional traffic map gives an overview of the movement patterns and a dynamic offset map presents detailed information according to user-specified filters. Extensive experiments are performed in this article. BP-CCSM is compared with three other state-of-the-art algorithms on two datasets: a small public dataset containing clickstreams from an e-commerce and a large global positioning system dataset with more than 600,000 taxi trip trajectories. The results show that BP-CCSM considerably outperforms three other algorithms in terms of running time and memory consumption. Besides, SPET provides an efficient and convenient way to inspect spatial and temporal variations in closed contiguous sequential patterns from a large number of trajectories.

Place, publisher, year, edition, pages
Taylor & Francis, 2018
Keywords
Closed contiguous sequential pattern, trajectory pattern mining, trajectory pattern visualization
National Category
Transport Systems and Logistics
Identifiers
urn:nbn:se:kth:diva-217997 (URN)10.1080/13658816.2017.1393542 (DOI)000432634200002 ()2-s2.0-85032699315 (Scopus ID)
Note

QC 20171121

Available from: 2017-11-20 Created: 2017-11-20 Last updated: 2024-03-15Bibliographically approved
Yang, C. & Gidofalvi, G. (2017). Fast map matching, an algorithm integrating hidden Markov model with precomputation. International Journal of Geographical Information Science, 1-24
Open this publication in new window or tab >>Fast map matching, an algorithm integrating hidden Markov model with precomputation
2017 (English)In: International Journal of Geographical Information Science, ISSN 1365-8816, E-ISSN 1365-8824, p. 1-24Article in journal (Refereed) Published
Abstract [en]

Wide deployment of global positioning system (GPS) sensors has generated a large amount of data with numerous applications in transportation research. Due to the observation error, a map matching (MM) process is commonly performed to infer a path on a road network from a noisy GPS trajectory. The increasing data volume calls for the design of efficient and scalable MM algorithms. This article presents fast map matching (FMM), an algorithm integrating hidden Markov model with precomputation, and provides an open-source implementation. An upper bounded origin-destination table is precomputed to store all pairs of shortest paths within a certain length in the road network. As a benefit, repeated routing queries known as the bottleneck of MM are replaced with hash table search. Additionally, several degenerate cases and a problem of reverse movement are identified and addressed in FMM. Experiments on a large collection of real-world taxi trip trajectories demonstrate that FMM has achieved a considerable single-processor MM speed of 25,000–45,000 points/second varying with the output mode. Investigation on the running time of different steps in FMM reveals that after precomputation is employed, the new bottleneck is located in candidate search, and more specifically, the projection of a GPS point to the polyline of a road edge. Reverse movement in the result is also effectively reduced by applying a penalty.

Place, publisher, year, edition, pages
Taylor & Francis, 2017
Keywords
Map matching, precomputation, performance improvement
National Category
Transport Systems and Logistics
Research subject
Geodesy and Geoinformatics
Identifiers
urn:nbn:se:kth:diva-217993 (URN)10.1080/13658816.2017.1400548 (DOI)000422691100006 ()2-s2.0-85033662435 (Scopus ID)
Note

QC 20171121

Available from: 2017-11-20 Created: 2017-11-20 Last updated: 2024-03-15Bibliographically approved
Yang, C. & Gyözö, G. (2016). Interactive Visual Exploration of Most LikelyMovements. In: Geospatial data in a changing world selected papers of the 19th AGILE Conference on Geographic Information Science: . Paper presented at the 19th AGILE International Conference on Geographic Information Science, Helsinki, Finland, 14-17 June 2016. Springer
Open this publication in new window or tab >>Interactive Visual Exploration of Most LikelyMovements
2016 (English)In: Geospatial data in a changing world selected papers of the 19th AGILE Conference on Geographic Information Science, Springer, 2016Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture notes in geoinformation and cartography, ISSN 1863-2246
National Category
Geosciences, Multidisciplinary
Identifiers
urn:nbn:se:kth:diva-198278 (URN)978-3-319-33782-1 (ISBN)
Conference
the 19th AGILE International Conference on Geographic Information Science, Helsinki, Finland, 14-17 June 2016
Note

QC 20170119

Available from: 2016-12-13 Created: 2016-12-13 Last updated: 2024-03-15Bibliographically approved
Gidofalvi, G. & Yang, C. (2015). Scalable Detection of Traffic Congestion from Massive Floating Car Data Streams. In: : . Paper presented at The First International Workshop on Smart Cities and Urban Analytics (UrbanGIS) 2015, Bellevue, WA, USA, NOVEMBER 3, 2015. ACM Press
Open this publication in new window or tab >>Scalable Detection of Traffic Congestion from Massive Floating Car Data Streams
2015 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Motivated by the high utility and growing availability of Floating Car Data (FCD) streams for traffic congestion modeling and subsequent traffic congestion-related intelligent traffic management tasks, this paper proposes a grid-based, time-inhomogeneous model and method for the detection of congestion from large FCD streams. Furthermore, the paper proposes a simple but effective, high-level implementation of the method using off-the-shelf relational database technology that can readily be ported to Big Data processing frameworks. Empirical evaluations on millions of real-world taxi trajectories show that 1) the spatio-temporal distribution and clustering of the detected congestions are reasonable and 2) the method and its prototype implementation scale linearly with the input size and the geographical level of detail / spatio-temporal resolution of the model.

Place, publisher, year, edition, pages
ACM Press, 2015
Keywords
Congestion Detection, FCD, Trajectory Data Mining, Intelligent Transport Systems
National Category
Computer Sciences Information Systems
Research subject
Computer Science; Transport Science; Geodesy and Geoinformatics
Identifiers
urn:nbn:se:kth:diva-184250 (URN)10.1145/2835022.2835041 (DOI)2-s2.0-84980396581 (Scopus ID)
Conference
The First International Workshop on Smart Cities and Urban Analytics (UrbanGIS) 2015, Bellevue, WA, USA, NOVEMBER 3, 2015
Note

QC 20220322

Available from: 2016-03-31 Created: 2016-03-31 Last updated: 2022-06-23Bibliographically approved
Yang, C. & Gidofalvi, G.Efficient Comparison of Contiguous Sequential Patterns in GPS Trajectory Data by Bidirectional Pruning.
Open this publication in new window or tab >>Efficient Comparison of Contiguous Sequential Patterns in GPS Trajectory Data by Bidirectional Pruning
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Contiguous sequential pattern (CSP) represents a contiguous subsequence that frequently appearing in a sequence database. When applies CSP mining to GPS trajectory data collected from vehicles, the discovered CSP reveals a frequent route in a road network. Retrieving the distribution of frequent routes over time or among different groups of users can be formulated as a CSP comparison problem, which has important application in intelligent transportation system. However, it confronts several challenges including compressed CSP information, large search space and redundancy in the output. To address those challenges, this paper proposes a Bidirectional pruning based CSP Comparison (BCSPC) algorithm by employing three tree structures to efficiently search and compare multiple sets of CSP. Comprehensive experiments are performed on a big public real-world GPS trajectory dataset where BCSPC is compared with two other algorithms CSP-FP-tree and BIDE. The results show that when CSP is mined with a small support, BCSPC considerably outperforms two other algorithms with speed improved by 2 to 10 times and memory significantly reduced. The visualization of comparison results demonstrates the effectiveness of BCSPC in answering sophisticated queries regarding the temporal distribution of frequent routes embedded in GPS trajectory data. 

Keywords
Contiguous sequential pattern, Sequential pattern comparison
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-286316 (URN)
Note

QC 20210122

Available from: 2020-11-24 Created: 2020-11-24 Last updated: 2022-06-25Bibliographically approved
Yang, C. & Gidofalvi, G.Matching Sparse GPS Data to Large Scale Road Network Accelerated by AStar Search.
Open this publication in new window or tab >>Matching Sparse GPS Data to Large Scale Road Network Accelerated by AStar Search
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Map matching (MM) infers the path on a road network from a noisy GPS trajectory. It is an important preprocessing procedure in many knowledge discovery tasks concerning GPS data. The bottleneck of MM has been widely recognized as the large number of repeated routing queries. Previous MM methods accelerated by precomputation can effectively address this issue but it can consume extremely high memory when the GPS dataset covers a large scale road network containing millions of edges. This paper studies the problem of matching sparse GPS data to a large scale road network. In addition to the repeated routing queries, another bottleneck of MM is identified as sequential search constraint where candidates of the current GPS observation must be evaluated before examining candidates of the next. With the objective to addressing those two types of bottleneck, this paper proposes an AStar Search based MM (ASMM) algorithm that is applicable for matching sparse GPS data to large scale road network. ASMM transforms MM into a candidate waynode routing problem and introduces level-associated distance label to avoid performing repeated routing queries. Moreover, the sequential search constraint is addressed by employing AStar search strategy. Comprehensive experiments on synthetic GPS dataset demonstrate the superiority of ASMM over three state-of-the-art algorithms. When matching sparse GPS data to a large scale network, the speed of ASMM is about 5 to 20 times of its competitors. When matching to a small scale network, ASMM is still competitive in achieving a similar speed as the fastest algorithm but consumes only 10% of memory. 

Keywords
Map matching A-star search
National Category
Computer and Information Sciences
Research subject
Geodesy and Geoinformatics, Geoinformatics
Identifiers
urn:nbn:se:kth:diva-286315 (URN)
Note

QC 20210122

Available from: 2020-11-24 Created: 2020-11-24 Last updated: 2022-06-25Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-5361-6034

Search in DiVA

Show all publications