An Interlligent Driver Guidance Tool using Location Based Services
This paper suggests a decision support system for vehicle drivers, accessible via mobile phone. Concept behind the system is to help drivers to schedule their activities, best utilizing their time along the way, minimizing the impacts of traffic. This is in contrast to existing approaches focused on controlling traffic in highways. Vehicle is continuously tracked along the journey and information presented to user is adapted according his location and time dimensions. System is based on a decision tree based classification model to predict the future traffic and use those results for decision making. System mines spatio-temporal data to build the decision tree, therefore developed in a distributed architecture to avoid load for a single server. System is exposed to community via existing social networks, bringing social networks into vehicular context. Decision trees to predict traffic are periodically rebuilt using most recent data, therefore this is an intelligent system which learns through empirical data, and best suited for dynamic vehicular environment.
Decision Tree Spatio Temporal Data Spatial Data Mining Social Networks M2M Platform A*Search Algorithm
Kushani Perera Dileeka Dias
Dialog Molile Communications Research Laboratory,University of Moratuwa University of Moratuwa, Mora Electronic and Telecommunication Departmen t,University of Moratuwa University of Moratuwa, Moratuwa
国际会议
福州
英文
246-251
2011-06-29（万方平台首次上网日期，不代表论文的发表时间）