| Title |
Forecasting Transport Mode Use with Support Vector Machines Based Approach |
| ID_Doc |
41181 |
| Authors |
Semanjski, I; Lopez, AJ; Gautama, S |
| Title |
Forecasting Transport Mode Use with Support Vector Machines Based Approach |
| Year |
2016 |
| Published |
Transactions On Maritime Science-Toms, 5, 2 |
| Abstract |
Since information and communication technologies have become an integral part of our everyday lives, it only seems logical that the smart city concept should attempt to explore the role of an integrated information and communication approach to city asset management and raising the quality of life of its citizens. Raising the quality of life relies not only on improving the management of a city's systems (e.g. transportation system) but also on the provision of timely and relevant information to its citizens to allow them to make better informed decisions. This requires the use of forecasting models. In this paper, a support vector machine-based model is developed to predict future mobility behavior from crowdsourced data. Crowdsourced data are collected through a dedicated smartphone app tracking mobility behavior. The use of a forecasting model of this type can facilitate the management of a smart city's mobility system while simultaneously ensuring the timely provision of relevant pre-travel information to its citizens. |
| PDF |
https://www.toms.com.hr/index.php/toms/article/download/150/142
|
