Enabling Smart Urban Services with GPS Trajectory Data

ISBN-13: 9789811601804 / Angielski / Miękka / 2022 / 368 str.

Chao Chen;Daqing Zhang;Yasha Wang

Opis

With the proliferation of GPS devices in daily life, trajectory data that records where and when people move is now readily available on a large scale. As one of the most typical representatives, it has now become widely recognized that taxi trajectory data provides rich opportunities to enable promising smart urban services. Yet, a considerable gap still exists between the raw data available, and the extraction of actionable intelligence. This gap poses fundamental challenges on how we can achieve such intelligence. These challenges include inaccuracy issues, large data volumes to process, and sparse GPS data, to name but a few. Moreover, the movements of taxis and the leaving trajectory data are the result of a complex interplay between several parties, including drivers, passengers, travellers, urban planners, etc.In this book, we present our latest findings on mining taxi GPS trajectory data to enable a number of smart urban services, and to bring us one step closer to the vision of smart mobility. Firstly, we focus on some fundamental issues in trajectory data mining and analytics, including data map-matching, data compression, and data protection. Secondly, driven by the real needs and the most common concerns of each party involved, we formulate each problem mathematically and propose novel data mining or machine learning methods to solve it. Extensive evaluations with real-world datasets are also provided, to demonstrate the effectiveness and efficiency of using trajectory data.Unlike other books, which deal with people and goods transportation separately, this book also extends smart urban services to goods transportation by introducing the idea of crowdshipping, i.e., recruiting taxis to make package deliveries on the basis of real-time information. Since people and goods are two essential components of smart cities, we feel this extension is bot logical and essential. Lastly, we discuss the most important scientific problems and open issues in mining GPS trajectory data.

Spis treści

1.     Trajectory data map-matching 

        1.1 Introduction

        1.2 Definitions and problem formulation

        1.3 SD-Matching algorithm

        1.4 Evaluations

        1.5 Conclusions and discussions

2.     Trajectory data compression

        2.1 Introduction

        2.2 Basic concepts and system overview

        2.3 HCC algorithm

        2.4 System implementation 

        2.5 Evaluations

        2.6 Conclusions

3.     Trajectory data protection 

        3.1 Introduction

        3.2 Preliminary

        3.3 Trajectory protection mechanism

        3.4 Performance evaluations

        3.5 Conclusions

 

Part II: Enabling Smart Urban Services: Travellers

4.     TripPlanner: Personalized trip planning leveraging heterogeneous trajectory data

        4.1 Introduction

        4.2 TripPlanner System

        4.3 Dynamic network modelling

        4.4 The two-phase approach

        4.5 System evaluations

        4.6 Conclusions and future work

5.     ScenicPlanner: Recommending the most beautiful driving routes

        5.1 Introduction

        5.2 Preliminary

        5.3 The two-phase approach

        5.4 Experimental evaluations

        5.5 Conclusion and future work

 

Part III: Enabling Smart Urban Services: Drivers

6.     GreenPlanner: Planning fuel-efficient driving routes

6.1 Introduction

        6.2 Basic concepts and problem formulation

        6.3 Personal fuel consumption model building

        6.4 Fuel-efficient driving route planning

        6.5 Evaluations

        6.6 Conclusions and future work

7.     Hunting or waiting: Earning more by understanding taxi service strategies

        7.1 Introduction

        7.2 Empirical study

        7.3 Taxi strategy formulation

        7.4 Understanding taxi service strategies

        7.5 Conclusions

 

Part IV: Enabling Smart Urban Services: Passengers

8.     iBOAT: Real-time detection of anomalous taxi trajectories from GPS traces

        8.1 Introduction

        8.2 Preliminaries and problem definition

        8.3 Isolation-based online anomalous trajectory detection

        8.4 Empirical evaluations

        8.5 Fraud behaviour analysis

        8.6 Conclusions and future work

9.     Real-Time imputing trip purpose leveraging heterogeneous trajectory data

        9.1 Introduction

        9.2 Basic concepts and problem statement

        9.3 Imputing trip purposes

        9.4 Enabling real-time response

        9.5 Evaluations

        9.6 Conclusions and future work

 

Part V: Enabling Smart Urban Services: Urban Planners

10.  GPS environment friendliness estimation with trajectory data

        10.1 Introduction

        10.2 Basic concepts

        10.3 Methodology

        10.4 Experiments

        10.5 Limitations and future work

        10.6 Conclusions

11.  B-Planner: Planning night bus routes using taxi trajectory data

        11.1 Introduction

        11.2 Candidate bus stop identification

        11.3 Bus route selection

        11.4 Experimental evaluations

        11.5 Conclusions and future work

12.  VizTripPurpose: Understanding city-wide passengers’ travel behaviours

        12.1 Introduction

        12.2 System overview

        12.3 Trip2Vec model

        12.4 User interfaces

        12.5 Case studies

        12.6 Conclusions and future work

 

Part VI: Enabling Smart Urban Services: Beyond People Transportation

13.  CrowdDeliver: Arriving as soon as possible

        13.1 Introduction

        13.2 Basic concepts, assumptions and problem statement

        13.3 Overview of CrowdDeliver

        13.4 Two-phase approach

        13.5 Evaluations

        13.6 Conclusions and future work

14.  CrowdExpress: Arriving by the user-specified deadline

        14.1 Introduction

        14.2 Preliminary, problem statement and system overview

        14.3 Offline package transport network building

        14.4 Online taxi scheduling and package routing

        14.5 Experimental evaluations

        14.6 Conclusions and future work

 

Part VII: Open Issues and Conclusions

15.  Open Issues

16.  Conclusions

 

O autorze

Chao Chen is a Full Professor of Computer Science at Chongqing University. He received his Ph.D. in Computer Science from Pierre and Marie Curie University and Institut Mines-Télécom/Télécom SudParis, France in 2014. He has authored or co-authored more than 100 papers including 20 ACM/IEEE Transactions. His research interests include pervasive computing, mobile computing, urban logistics, data mining from large-scale taxi GPS trajectory data, and big data analytics for smart cities. Dr. Chen’s work on taxi trajectory data mining was featured by IEEE SPECTRUM in 2011, 2016 and 2020, respectively. He was also the winner of the Best Paper Runner-Up Award at MobiQuitous 2011.                

Daqing Zhang is a Chair Professor at Peking University, China. He received his Ph.D. from the University of Rome “La Sapienza” and University of L’Aquila in 1996. He has authored or co-authored more than 180 referred journal and conference papers, particularly on practical applications in digital cities, mobile social networks, and elderly care. His research interests include large-scale data mining, urban computing, context-aware computing, and ambient assistive living. He is a recipient of the 10 Years CoMoRea Impact Paper Award at IEEE PerCom 2013, the Best Paper Award at IEEE UIC 2015/2012, and the Best Paper Runner Up Award at MobiQuitous 2011.

Yasha Wang is a Full Professor and Associate Director of the National Research and Engineering Center of Software Engineering at Peking University, China. He received his Ph.D. from Northeastern University, Shenyang, China, in 2003. He also served as the head of the technical special group of the National Big Data Standards Committee of China, and as a standing committee member of the ubiquitous computing special interest group of CCF. He has long been engaged in research in the fields of data analysis, ubiquitous computing, and urban computing, and has published more than 100 papers in international high-level academic conference proceedings and journals such as IEEE TMC, ACM Ubicomp, IEEE ICDE, ACM CSCW, AAAI, and IJCAI. Cooperating with major smart-city solution providers, the results of his work have been adopted in more than 20 Chinese cities.

Hongyu Huang is an Associate Professor of Computer Science at Chongqing University. He received his B.S. degree from Chongqing Normal University in 2002, his M.S. from Chongqing University in 2005, and his Ph.D. from Shanghai Jiao Tong University in 2009. His research interests include mobile crowd-sensing, privacy preserving computing, and vehicular ad hoc networks.