Premium
Urban Sensing by Crowdsourcing: Analysing Urban Trip behaviour in Zurich
Author(s) -
Shin Dongyoun
Publication year - 2016
Publication title -
international journal of urban and regional research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.456
H-Index - 114
eISSN - 1468-2427
pISSN - 0309-1317
DOI - 10.1111/1468-2427.12416
Subject(s) - crowdsourcing , data collection , computer science , data science , key (lock) , urban computing , measure (data warehouse) , urban planning , domain (mathematical analysis) , transport engineering , data mining , human–computer interaction , world wide web , computer security , engineering , civil engineering , mathematical analysis , statistics , mathematics
The research on which this essay is based sought to provide a deeper understanding of live urban activities. The main idea was to obtain in‐depth trip information by integrating sensing technology with crowdsourcing‐based methods. Location and acceleration sensors embedded in smartphones can deliver useful trip information. Research had previously been conducted to find an accurate data analysis algorithm for high‐level data mining, an efficient sensing method for power saving. As a proof of concept, this essay presents a case study of Zurich that successfully implemented previous research achievements in the real environment. It established that urban travel behaviour can, in fact, be collected by sensors embedded in mobile devices, and that the data thus obtained can be used to measure the characteristics of trip behaviour in cities by means of an advanced classifying algorithm and analysis. The strength of this research is its pioneering role in clearing the ground for future urban data collection methods and planning strategies. Specifically, this study could provide answers to the following key questions: How can crowdsourcing be applied to the collection of urban transportation data? What kinds of information can be extracted from the crowdsourced mobile sensing platform? What kinds of knowledge, within the transportation domain, can be derived from the above?