Publications - Pervasive Computing Laboratory

Access control anotacionsemantica authentication Cloud computing coap compromise cryptography cynamon emadrid emrisco entropy home network I-Shaper identity management inrisco inteligenciafuentesabiertas Internet of Things IoT magos middleware Pervasive computing privacy Protocols Qursa raudo2 Security Smart Card Trust management Ubisec VANETs 
Show all
2012
 Rodriguez-Carrion, Alicia;  García-Rubio, Carlos;  Campo-Vázquez, Celeste;  Cortés, Alberto;  García-Lozano, Estrella
Study of LZ-Based Location Prediction and Its Application to Transportation Recommender Systems Journal Article 
In: Sensors , vol. 12, iss. 6, pp. 7496-7517, 2012, ISSN: 1424-8220.
Abstract | Links | BibTeX | Tags: active lezi, Ambient intelligence, españavirtual, gsm-based location, lezi update, lz, prediction, recommender system, Ubiquitous computing
@article{campo009b,

title = {Study of LZ-Based Location Prediction and Its Application to Transportation Recommender Systems},

author = {Alicia Rodriguez-Carrion and Carlos García-Rubio and Celeste Campo-Vázquez and Alberto Cortés and Estrella García-Lozano },

url = {http://hdl.handle.net/10016/27902},

doi = {https://doi.org/10.3390/s120607496},

issn = {1424-8220},

year  = {2012},

date = {2012-06-04},

urldate = {2012-06-04},

journal = {Sensors },

volume = {12},

issue = {6},

pages = {7496-7517},

abstract = {Predicting users' next location allows to anticipate their future context, thus providing additional time to be ready for that context and react consequently. This work is focused on a set of LZ-based algorithms (LZ, LeZi Update and Active LeZi) capable of learning mobility patterns and estimating the next location with low resource needs, which makes it possible to execute them on mobile devices. The original algorithms have been divided into two phases, thus being possible to mix them and check which combination is the best one to obtain better prediction accuracy or lower resource consumption. To make such comparisons, a set of GSM-based mobility traces of 95 different users is considered. Finally, a prototype for mobile devices that integrates the predictors in a public transportation recommender system is described in order to show an example of how to take advantage of location prediction in an ubiquitous computing environment.},

keywords = {active lezi, Ambient intelligence, españavirtual, gsm-based location, lezi update, lz, prediction, recommender system, Ubiquitous computing},

pubstate = {published},

tppubtype = {article}

}

Close
Predicting users' next location allows to anticipate their future context, thus providing additional time to be ready for that context and react consequently. This work is focused on a set of LZ-based algorithms (LZ, LeZi Update and Active LeZi) capable of learning mobility patterns and estimating the next location with low resource needs, which makes it possible to execute them on mobile devices. The original algorithms have been divided into two phases, thus being possible to mix them and check which combination is the best one to obtain better prediction accuracy or lower resource consumption. To make such comparisons, a set of GSM-based mobility traces of 95 different users is considered. Finally, a prototype for mobile devices that integrates the predictors in a public transportation recommender system is described in order to show an example of how to take advantage of location prediction in an ubiquitous computing environment.
Close
http://hdl.handle.net/10016/27902
doi:https://doi.org/10.3390/s120607496
Close
 Rodriguez-Carrion, Alicia;  Campo-Vázquez, Celeste;  García-Rubio, Carlos
Recommendations on the Move. In: Recommender Systems for the Social Web Book Chapter 
In: pp. 179-193, Springer International Publishing, Recommender Systems for the Social Web, 2012, ISBN: 978-3-642-25693-6.
Abstract | Links | BibTeX | Tags: current location, global position system, mobile phone, prediction algorithm, recommender system
@inbook{campo012,

title = {Recommendations on the Move. In: Recommender Systems for the Social Web},

author = {Alicia Rodriguez-Carrion and Celeste Campo-Vázquez and Carlos García-Rubio},

url = {https://doi.org/10.1007/978-3-642-25694-3},

doi = {https://doi.org/10.1007/978-3-642-25694-3_9},

isbn = {978-3-642-25693-6},

year  = {2012},

date = {2012-01-21},

urldate = {2012-01-21},

pages = {179-193},

publisher = {Springer International Publishing},

edition = {Recommender Systems for the Social Web},

abstract = {Recommender systems can take advantage of the user’s current location in order to improve the recommendations about places the user may be interested in. Taking a step further, these suggestions could be based not only on the user’s current location, but also on the places where the user is supposed to be in the near future, so the recommended locations would be on the path the user is going to follow. In order to do that we need some location prediction algorithms so that we can get those future locations. In this chapter we explain how to use the algorithms belonging to LZ family (LZ, LeZi Update and Active LeZi) as recommender engines, and we propose some ways of using these algorithms in places where the user has not been before or how to take advantage of the social knowledge about certain place so as to make these recommendations richer. Finally we show a prototype implementation of a recommender system for touristic places made up of these LZ predictors.},

keywords = {current location, global position system, mobile phone, prediction algorithm, recommender system},

pubstate = {published},

tppubtype = {inbook}

}

Close
Recommender systems can take advantage of the user’s current location in order to improve the recommendations about places the user may be interested in. Taking a step further, these suggestions could be based not only on the user’s current location, but also on the places where the user is supposed to be in the near future, so the recommended locations would be on the path the user is going to follow. In order to do that we need some location prediction algorithms so that we can get those future locations. In this chapter we explain how to use the algorithms belonging to LZ family (LZ, LeZi Update and Active LeZi) as recommender engines, and we propose some ways of using these algorithms in places where the user has not been before or how to take advantage of the social knowledge about certain place so as to make these recommendations richer. Finally we show a prototype implementation of a recommender system for touristic places made up of these LZ predictors.
Close
https://doi.org/10.1007/978-3-642-25694-3
doi:https://doi.org/10.1007/978-3-642-25694-3_9
Close