M-Eco enhanced Adaptation Service (D5.3)

Ricardo Gomes Lage, Martin Leginus, Peter Dolog, Frederico Durao, Rong Pan, Ernesto Diaz-Aviles

Publikation: Bog/antologi/afhandling/rapportRapportForskning

353 Downloads (Pure)

Resumé

In this report, we present the final version of the Adaptive Tuning and Personalization (WP5)
component of the M-Eco system. This component is focused on four main areas of interest to
users of surveillance systems: presentation options for recommendation and adaptation, user
and group models, user classification and modeling algorithms, and recommendation, adaptation
and personalization strategies. In each of these areas, we propose improvements over those
presented in the previous deliverable incorporating feedback from medical surveilance experts.
The personalization component is enriched with several extensions. The multi-factor recommendation
model is incremented with more factors, including time decay, tagging activity and
location. Location is also improved with a method to predict event trajectories. Moreover, a
new family of tensor-based recommenders is presented. The tag cloud model is improved with
two new tags selection algorithms. We also introduce a propagation of the (ir)relevant terms
obtained from tag clouds usage to WP3 and WP4 in order to improve their data collections
algorithms. The evaluation part of the report summarizes the benefits and drawbacks of the
models presented and describes possible directions for the future work.
OriginalsprogEngelsk
Antal sider68
StatusUdgivet - aug. 2012

Fingerprint

tagging
trajectory
ecosystem
modeling
services
recommendation
surveillance
method
evaluation
family

Citer dette

Lage, R. G., Leginus, M., Dolog, P., Durao, F., Pan, R., & Diaz-Aviles, E. (2012). M-Eco enhanced Adaptation Service (D5.3).
Lage, Ricardo Gomes ; Leginus, Martin ; Dolog, Peter ; Durao, Frederico ; Pan, Rong ; Diaz-Aviles, Ernesto . / M-Eco enhanced Adaptation Service (D5.3). 2012. 68 s.
@book{aa763b6cf17a4a56ba780fa187243e2f,
title = "M-Eco enhanced Adaptation Service (D5.3)",
abstract = "In this report, we present the final version of the Adaptive Tuning and Personalization (WP5)component of the M-Eco system. This component is focused on four main areas of interest tousers of surveillance systems: presentation options for recommendation and adaptation, userand group models, user classification and modeling algorithms, and recommendation, adaptationand personalization strategies. In each of these areas, we propose improvements over thosepresented in the previous deliverable incorporating feedback from medical surveilance experts.The personalization component is enriched with several extensions. The multi-factor recommendationmodel is incremented with more factors, including time decay, tagging activity andlocation. Location is also improved with a method to predict event trajectories. Moreover, anew family of tensor-based recommenders is presented. The tag cloud model is improved withtwo new tags selection algorithms. We also introduce a propagation of the (ir)relevant termsobtained from tag clouds usage to WP3 and WP4 in order to improve their data collectionsalgorithms. The evaluation part of the report summarizes the benefits and drawbacks of themodels presented and describes possible directions for the future work.",
keywords = "social tagging, recommender system, tag cloud, group recommendation",
author = "Lage, {Ricardo Gomes} and Martin Leginus and Peter Dolog and Frederico Durao and Rong Pan and Ernesto Diaz-Aviles",
year = "2012",
month = "8",
language = "English",

}

Lage, RG, Leginus, M, Dolog, P, Durao, F, Pan, R & Diaz-Aviles, E 2012, M-Eco enhanced Adaptation Service (D5.3).

M-Eco enhanced Adaptation Service (D5.3). / Lage, Ricardo Gomes; Leginus, Martin; Dolog, Peter; Durao, Frederico; Pan, Rong; Diaz-Aviles, Ernesto .

2012. 68 s.

Publikation: Bog/antologi/afhandling/rapportRapportForskning

TY - RPRT

T1 - M-Eco enhanced Adaptation Service (D5.3)

AU - Lage, Ricardo Gomes

AU - Leginus, Martin

AU - Dolog, Peter

AU - Durao, Frederico

AU - Pan, Rong

AU - Diaz-Aviles, Ernesto

PY - 2012/8

Y1 - 2012/8

N2 - In this report, we present the final version of the Adaptive Tuning and Personalization (WP5)component of the M-Eco system. This component is focused on four main areas of interest tousers of surveillance systems: presentation options for recommendation and adaptation, userand group models, user classification and modeling algorithms, and recommendation, adaptationand personalization strategies. In each of these areas, we propose improvements over thosepresented in the previous deliverable incorporating feedback from medical surveilance experts.The personalization component is enriched with several extensions. The multi-factor recommendationmodel is incremented with more factors, including time decay, tagging activity andlocation. Location is also improved with a method to predict event trajectories. Moreover, anew family of tensor-based recommenders is presented. The tag cloud model is improved withtwo new tags selection algorithms. We also introduce a propagation of the (ir)relevant termsobtained from tag clouds usage to WP3 and WP4 in order to improve their data collectionsalgorithms. The evaluation part of the report summarizes the benefits and drawbacks of themodels presented and describes possible directions for the future work.

AB - In this report, we present the final version of the Adaptive Tuning and Personalization (WP5)component of the M-Eco system. This component is focused on four main areas of interest tousers of surveillance systems: presentation options for recommendation and adaptation, userand group models, user classification and modeling algorithms, and recommendation, adaptationand personalization strategies. In each of these areas, we propose improvements over thosepresented in the previous deliverable incorporating feedback from medical surveilance experts.The personalization component is enriched with several extensions. The multi-factor recommendationmodel is incremented with more factors, including time decay, tagging activity andlocation. Location is also improved with a method to predict event trajectories. Moreover, anew family of tensor-based recommenders is presented. The tag cloud model is improved withtwo new tags selection algorithms. We also introduce a propagation of the (ir)relevant termsobtained from tag clouds usage to WP3 and WP4 in order to improve their data collectionsalgorithms. The evaluation part of the report summarizes the benefits and drawbacks of themodels presented and describes possible directions for the future work.

KW - social tagging

KW - recommender system

KW - tag cloud

KW - group recommendation

M3 - Report

BT - M-Eco enhanced Adaptation Service (D5.3)

ER -

Lage RG, Leginus M, Dolog P, Durao F, Pan R, Diaz-Aviles E. M-Eco enhanced Adaptation Service (D5.3). 2012. 68 s.