Predicting Tour Patterns Derived from Ubiquitous Data Sources

摘要: Ubiquitous data sources (e.g. GPS traces, mobile phone call records, smart card entries etc.) are increasingly being popular among researchers for deriving mobility patterns. These patterns depend on socio-economic characteristics of the traveler as well associated situational, contextual and environmental factors. therefore vary substantially with age, gender, employment status, income level other demographic Habitual markers (propensity to use internet, social networking websites, phones or media example) also provide useful indications about these In this research, day-to-day tour travelers have been extracted from WLAN records a discrete choice modeling framework has proposed predict using factors, habitual travel related attributes collected Lausanne, Switzerland. The model parameters estimated by maximum likelihood technique software BIOGEME. Estimated confirm that factors occupation gender) combined habit listening music phone) day week) can be used pattern an individual certain day. developed demonstrates how information obtained ubiquitous successfully tool transportation planning management.