|
Title:
|
NEW TRAFFIC INFORMATION SYSTEM BASED ON MEANS OF TRANSPORTATION CLASSIFICATION |
|
Author(s):
|
Theresa Nick, Jan Geldmacher, Jürgen Götze, Edmund Coersmeier |
|
ISBN:
|
978-972-8939-19-9 |
|
Editors:
|
Hans Weghorn, Jörg Roth and Pedro Isaías |
|
Year:
|
2010 |
|
Edition:
|
Single |
|
Keywords:
|
Ad Hoc network, WLAN, means of transportation classification, acceleration sensor |
|
Type:
|
Short Paper |
|
First Page:
|
186 |
|
Last Page:
|
190 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Sensors built into mobile phones have the ability to provide significant information about environmental states as well as about different activities of persons because users take their phones almost everywhere and do so nearly every day. This paper deals with the acceleration sensor of a commercial mobile phone that makes it possible to identify and classify the user's means of transportation. The classification algorithms used for classifying the acceleration sensor data are Support Vector Machine and Naive Bayes classifier. Their results on solving the classification problem show that both classifiers are able to solve the classification task with a high accuracy. But Support Vector Machines perform better than Naive Bayes classifier and can achieve a classification accuracy of over 97% on an unknown test data set. Using the results of the classification a navigation system that can incorporate different means of transportation for one route can be developed. It would offer the chance to navigate on the fastest route with a combination of more than one means of transportation. Furthermore for future realization the connection of mobile phones via an Ad Hoc network is used to allow the mobile phones to transfer data in a swarm which can enhance the classification results. In combination with a localization technique the new navigation and routing application could be completed: This system would not be limited to a single means of transportation and could realize a real-time traffic situation description through the use of the sensor data classification. |
|
|
|
|
|
|
