Characterising and predicting urban mobility dynamics by mining bike sharing system data

Ida Bagus Irawan Purnama; Neil Bergmann; Raja Jurdak; Kun Zhao

doi:10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

Characterising and predicting urban mobility dynamics by mining bike sharing system data

Ida Bagus Irawan Purnama, Neil Bergmann, Raja Jurdak, Kun Zhao

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution

3 Citations (Scopus)

Abstract

Understanding the spatio-temporal characteristics of human mobility in urban areas is invaluable especially for traffic management and urban planning. An opportunity to characterize and predict urban mobility is provided by mining Bike Sharing System (BSS) trip data spatially and temporally. This study focuses on identifying highly predictable BSS users, revealing their mobility characteristics and predicting their next-place movements. In undertaking user classification, we compare between naïve subscription based classification, namely registered and unregistered users, and trip number based classification, namely commuter, regular and casual users. Our analysis of 13 weeks of London BSS data shows that users with high predictability are those with 50 or more historical trips and with commuting patterns that can be fairly represented by registered users. However, because of the diversity of usage patterns, the spatio-temporal mobility characteristics of registered users are not as uniform as commuters who are the fastest, farthest travelled, most consistent, and most predictable riders with Markovian qualities. Using only a first order Markov predictor, the prediction of trip destination based on trip origin in weekday morning is up to 78% predictable for commuters.

Original language	English
Title of host publication	Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops
Subtitle of host publication	UIC-ATC-ScalCom-CBDCom-IoP 2015
Editors	Jianhua Ma, Laurence T. Yang, Huansheng Ning, Ali Li
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	159-167
Number of pages	9
ISBN (Electronic)	9781467372114
ISBN (Print)	9781467372121
DOIs	https://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46
Publication status	Published - 2015
Externally published	Yes
Event	Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015 - Beijing, China Duration: 10 Aug 2015 → 14 Aug 2015

Other

Other	Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015
Country	China
City	Beijing
Period	10/08/15 → 14/08/15

Keywords

Bike sharing system
Characterization
Commuter
Data mining
Entropy
Markov predictor
Next-place prediction
Predictability
Urban mobility dynamics

Access to Document

10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Characterising and predicting urban mobility dynamics by mining bike sharing system data'. Together they form a unique fingerprint.

Cite this

Purnama, I. B. I., Bergmann, N., Jurdak, R., & Zhao, K. (2015). Characterising and predicting urban mobility dynamics by mining bike sharing system data. In J. Ma, L. T. Yang, H. Ning, & A. Li (Eds.), Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops: UIC-ATC-ScalCom-CBDCom-IoP 2015 (pp. 159-167). [7518223] Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

Purnama, Ida Bagus Irawan ; Bergmann, Neil ; Jurdak, Raja ; Zhao, Kun. / Characterising and predicting urban mobility dynamics by mining bike sharing system data. Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops: UIC-ATC-ScalCom-CBDCom-IoP 2015. editor / Jianhua Ma ; Laurence T. Yang ; Huansheng Ning ; Ali Li. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 159-167

@inproceedings{863149a9061e456187f518a92d1b8687,

title = "Characterising and predicting urban mobility dynamics by mining bike sharing system data",

abstract = "Understanding the spatio-temporal characteristics of human mobility in urban areas is invaluable especially for traffic management and urban planning. An opportunity to characterize and predict urban mobility is provided by mining Bike Sharing System (BSS) trip data spatially and temporally. This study focuses on identifying highly predictable BSS users, revealing their mobility characteristics and predicting their next-place movements. In undertaking user classification, we compare between na{\"i}ve subscription based classification, namely registered and unregistered users, and trip number based classification, namely commuter, regular and casual users. Our analysis of 13 weeks of London BSS data shows that users with high predictability are those with 50 or more historical trips and with commuting patterns that can be fairly represented by registered users. However, because of the diversity of usage patterns, the spatio-temporal mobility characteristics of registered users are not as uniform as commuters who are the fastest, farthest travelled, most consistent, and most predictable riders with Markovian qualities. Using only a first order Markov predictor, the prediction of trip destination based on trip origin in weekday morning is up to 78{\%} predictable for commuters.",

keywords = "Bike sharing system, Characterization, Commuter, Data mining, Entropy, Markov predictor, Next-place prediction, Predictability, Urban mobility dynamics",

author = "Purnama, {Ida Bagus Irawan} and Neil Bergmann and Raja Jurdak and Kun Zhao",

year = "2015",

doi = "10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46",

language = "English",

isbn = "9781467372121",

pages = "159--167",

editor = "Jianhua Ma and Yang, {Laurence T.} and Huansheng Ning and Ali Li",

booktitle = "Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Purnama, IBI, Bergmann, N, Jurdak, R & Zhao, K 2015, Characterising and predicting urban mobility dynamics by mining bike sharing system data. in J Ma, LT Yang, H Ning & A Li (eds), Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops: UIC-ATC-ScalCom-CBDCom-IoP 2015., 7518223, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 159-167, Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015, Beijing, China, 10/08/15. https://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

Characterising and predicting urban mobility dynamics by mining bike sharing system data. / Purnama, Ida Bagus Irawan; Bergmann, Neil; Jurdak, Raja; Zhao, Kun.

Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops: UIC-ATC-ScalCom-CBDCom-IoP 2015. ed. / Jianhua Ma; Laurence T. Yang; Huansheng Ning; Ali Li. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 159-167 7518223.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution

TY - GEN

T1 - Characterising and predicting urban mobility dynamics by mining bike sharing system data

AU - Purnama, Ida Bagus Irawan

AU - Bergmann, Neil

AU - Jurdak, Raja

AU - Zhao, Kun

PY - 2015

Y1 - 2015

N2 - Understanding the spatio-temporal characteristics of human mobility in urban areas is invaluable especially for traffic management and urban planning. An opportunity to characterize and predict urban mobility is provided by mining Bike Sharing System (BSS) trip data spatially and temporally. This study focuses on identifying highly predictable BSS users, revealing their mobility characteristics and predicting their next-place movements. In undertaking user classification, we compare between naïve subscription based classification, namely registered and unregistered users, and trip number based classification, namely commuter, regular and casual users. Our analysis of 13 weeks of London BSS data shows that users with high predictability are those with 50 or more historical trips and with commuting patterns that can be fairly represented by registered users. However, because of the diversity of usage patterns, the spatio-temporal mobility characteristics of registered users are not as uniform as commuters who are the fastest, farthest travelled, most consistent, and most predictable riders with Markovian qualities. Using only a first order Markov predictor, the prediction of trip destination based on trip origin in weekday morning is up to 78% predictable for commuters.

AB - Understanding the spatio-temporal characteristics of human mobility in urban areas is invaluable especially for traffic management and urban planning. An opportunity to characterize and predict urban mobility is provided by mining Bike Sharing System (BSS) trip data spatially and temporally. This study focuses on identifying highly predictable BSS users, revealing their mobility characteristics and predicting their next-place movements. In undertaking user classification, we compare between naïve subscription based classification, namely registered and unregistered users, and trip number based classification, namely commuter, regular and casual users. Our analysis of 13 weeks of London BSS data shows that users with high predictability are those with 50 or more historical trips and with commuting patterns that can be fairly represented by registered users. However, because of the diversity of usage patterns, the spatio-temporal mobility characteristics of registered users are not as uniform as commuters who are the fastest, farthest travelled, most consistent, and most predictable riders with Markovian qualities. Using only a first order Markov predictor, the prediction of trip destination based on trip origin in weekday morning is up to 78% predictable for commuters.

KW - Bike sharing system

KW - Characterization

KW - Commuter

KW - Data mining

KW - Entropy

KW - Markov predictor

KW - Next-place prediction

KW - Predictability

KW - Urban mobility dynamics

UR - http://www.scopus.com/inward/record.url?scp=84983389554&partnerID=8YFLogxK

U2 - 10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

DO - 10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46

M3 - Conference proceeding contribution

SN - 9781467372121

SP - 159

EP - 167

BT - Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops

A2 - Ma, Jianhua

A2 - Yang, Laurence T.

A2 - Ning, Huansheng

A2 - Li, Ali

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

ER -

Purnama IBI, Bergmann N, Jurdak R, Zhao K. Characterising and predicting urban mobility dynamics by mining bike sharing system data. In Ma J, Yang LT, Ning H, Li A, editors, Proceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops: UIC-ATC-ScalCom-CBDCom-IoP 2015. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 159-167. 7518223 https://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.46