Mobile Subscriber Profiling and Personal Service Generation using Location Awareness
In the mobile environment, the location and the next move of subscribers are important. In this study, a method to detect the next move of the subscribers is proposed. In addition to the categorization of subscribers by using their Internet usage history, the knowledge of the next move pattern of...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Stefan cel Mare University of Suceava
2018-08-01
|
Series: | Advances in Electrical and Computer Engineering |
Subjects: | |
Online Access: | http://dx.doi.org/10.4316/AECE.2018.03014 |
id |
doaj-cf6c6a497eb04b05a9ffb84e5e9653af |
---|---|
record_format |
Article |
spelling |
doaj-cf6c6a497eb04b05a9ffb84e5e9653af2020-11-24T23:15:03ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002018-08-0118310511210.4316/AECE.2018.03014Mobile Subscriber Profiling and Personal Service Generation using Location AwarenessOZTOPRAK, K.In the mobile environment, the location and the next move of subscribers are important. In this study, a method to detect the next move of the subscribers is proposed. In addition to the categorization of subscribers by using their Internet usage history, the knowledge of the next move pattern of subscribers will provide the flexibility to guide them to decide the next move. During the tracking of subscribers, the mobile devices of the subscribers are used as sensors to get in-depth knowledge about their preferences in their social life. The method presented here is the first in the literature to estimate the next move without connecting to any social networks. It combines the geographic locations and the Internet usage of the subscribers in order to predict their movement. In addition, most of the IoT studies either concentrate on network topologies or power consumption, while in this study, dynamicity and exact location estimation are utilized to handle the challenges and attain the required results. The results of the experiments show that the proposed system predicts the next move of a subscriber with a precision of more than 90 percent.http://dx.doi.org/10.4316/AECE.2018.03014social network servicesartificial neural networksdata miningreal-time systemscooperative communication |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
OZTOPRAK, K. |
spellingShingle |
OZTOPRAK, K. Mobile Subscriber Profiling and Personal Service Generation using Location Awareness Advances in Electrical and Computer Engineering social network services artificial neural networks data mining real-time systems cooperative communication |
author_facet |
OZTOPRAK, K. |
author_sort |
OZTOPRAK, K. |
title |
Mobile Subscriber Profiling and Personal Service Generation using Location Awareness |
title_short |
Mobile Subscriber Profiling and Personal Service Generation using Location Awareness |
title_full |
Mobile Subscriber Profiling and Personal Service Generation using Location Awareness |
title_fullStr |
Mobile Subscriber Profiling and Personal Service Generation using Location Awareness |
title_full_unstemmed |
Mobile Subscriber Profiling and Personal Service Generation using Location Awareness |
title_sort |
mobile subscriber profiling and personal service generation using location awareness |
publisher |
Stefan cel Mare University of Suceava |
series |
Advances in Electrical and Computer Engineering |
issn |
1582-7445 1844-7600 |
publishDate |
2018-08-01 |
description |
In the mobile environment, the location and the next move of subscribers are important. In this study,
a method to detect the next move of the subscribers is proposed. In addition to the categorization
of subscribers by using their Internet usage history, the knowledge of the next move pattern of
subscribers will provide the flexibility to guide them to decide the next move. During the tracking
of subscribers, the mobile devices of the subscribers are used as sensors to get in-depth knowledge
about their preferences in their social life. The method presented here is the first in the literature
to estimate the next move without connecting to any social networks. It combines the geographic
locations and the Internet usage of the subscribers in order to predict their movement.
In addition, most of the IoT studies either concentrate on network topologies or power
consumption, while in this study, dynamicity and exact location estimation are utilized
to handle the challenges and attain the required results. The results of the experiments
show that the proposed system predicts the next move of a subscriber with a precision of
more than 90 percent. |
topic |
social network services artificial neural networks data mining real-time systems cooperative communication |
url |
http://dx.doi.org/10.4316/AECE.2018.03014 |
work_keys_str_mv |
AT oztoprakk mobilesubscriberprofilingandpersonalservicegenerationusinglocationawareness |
_version_ |
1725592395200856064 |