Show simple item record

dc.contributor.author Bhagya, NK
dc.contributor.author Kumarage, AS
dc.contributor.author Lokanathan, S
dc.contributor.editor Gunaruwan, TL
dc.date.accessioned 2022-04-26T09:24:38Z
dc.date.available 2022-04-26T09:24:38Z
dc.date.issued 2017-06
dc.identifier.citation Bhagya, N.K., Kumarage, A.S., & Lokanathan, S. (2017). Understanding travel behaviour from call detail records [Extended Abstract]. In T.L. Gunaruwan (Ed.), Proceedings of 2nd International Conference on Research for Transport and Logistics Industry 2017 (pp. 167-171 ). Sri Lanka Society of Transport and Logistics. https://slstl.lk/r4tli-2017/ en_US
dc.identifier.uri http://dl.lib.uom.lk/handle/123/17709
dc.description Understanding human mobility is essential in many fields including transportation planning. Currently, manually carried out surveys are the primary source for such data and analysis. Such data collection, while being expensive, takes time and is often outdated by the time it is available for analysis. Mobile Network Big Data (MNBD) has the possibility of supplementing traditional data sampling programs, resulting not only in cost and time savings, but with a striking growth in the amount of information available for analysis. Mobile Network Big Data (MNBD) concerns large-volume, complex, growing data sets derived from the way people use communication devices. Compared to other network-related data like GPS, Call Detail Records (CDRs) are the largest subset of MNBD and are easily available since most telecommunication service providers maintain such data for billing purposes (Manoranjan Dash, 2015). Whenever a cellular transaction is made, a CDR which consists of time-stamped tower locations with caller IDs are generated (Md.Shahadat Iqbal, 2014). CDR describes the mobile usage pattern of a particular user of which the present focus is to extract information on the mobility of the user. Thus, analysing CDR will lead to understanding human mobility. Moreover, CDRs have been used in various analyses which address different transport concepts. These include O-D trip estimation with different techniques (M. K. D. T. Maldeniya, 2016), identifying significant locations visited by users, and deriving home and work points through more advanced models developed for the purpose. However, in Sri Lanka there is less research on understanding travel behaviour. A firm theoretical account will enable the effective use of MNBD for transport demand forecasting. en_US
dc.language.iso en en_US
dc.publisher Sri Lanka Society of Transport and Logistics en_US
dc.relation.uri https://slstl.lk/r4tli-2017/ en_US
dc.subject Mobile network en_US
dc.subject Big data en_US
dc.subject Call detail record en_US
dc.subject Load balancing en_US
dc.title Understanding travel behaviour from call detail records en_US
dc.type Conference-Extended-Abstract en_US
dc.identifier.faculty Engineering en_US
dc.identifier.department Department of Transport and Logistics Management en_US
dc.identifier.year 2017 en_US
dc.identifier.conference 2nd International Conference on Research for Transport and Logistics Industry 2017 en_US
dc.identifier.place Colombo en_US
dc.identifier.pgnos pp. 167-171 en_US
dc.identifier.proceeding Proceedings of 2nd International Conference on Research for Transport and Logistics Industry 2017 en_US


Files in this item

Icon
Name: Understanding Travel ...
Size: 107.5Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record