Personnalisation

Résumé

La personnalisation peut être une action d'ordre matériel (modification impliquant une activité physique sur l'objet) ou phénomène psychologique quasi-anthropologique d'identification d'un artefact à une forme humaine, une personne, une fonction sociale. Description Dans le langage courant moderne la personnalisation est l'appropriation d'un médium électronique, écrit ou d’un produit de consommation effectuée selon des données personnelles fournies par un usager, ou par la volonté de l'utilisateur lui-même. Il y a trois grandes familles de personnalisations : *personnalisation active : l'utilisateur prend en charge le produit manufacturé et le modifie intuitivement ou logiquement pour l'adapter à son utilisation. *passive : le fournisseur, l'industriel, le prestataire de service ajuste son produit fini en fonction de paramètres qui caractérisent ses utilisateurs. *interactive : La personnalisation de contenu est en train d'évoluer à très grande vitesse grâce aux progrès d

Source officielle

https://fr.wikipedia.org/wiki/Personnalisation

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (21)

Privacy-preserving and Personalized Federated Machine Learning for Medical Data

Felix Hans Michel Grimberg

The federated learning setting is prone to suffering from non-identically distributed data across participating agents. This gives rise to the task of model personalization, where agents collaborate to train several different machine learning models instead of training only one global model. The aim of model personalization is to minimize the sum of the generalization error incurred from training on small data sets, and the transfer error incurred from applying a globally-trained model to a specific local distribution. In this report, two novel approaches to personalized cross-silo federated learning are introduced and discussed from a theoretical perspective: the adapted Ndoye factor, and the Weight Erosion aggregation scheme. The latter is implemented and compared to two baseline aggregation schemes in two case studies: training a diagnostic model on real-world medical data, and predicting the survival of passengers on the publicly available Titanic data set. The models trained using the Weight Erosion aggregation scheme are compared to those trained using the baseline aggregation schemes, both in terms of their classification accuracy on the local test set and in terms of the learned parameters. We demonstrate that the novel Weight Erosion scheme can outperform both baseline aggregation schemes for some specific tasks.

2020

Chargement

Personalizing behavior change (BC) strategies to motivate increased physical activity is especially important for the diverse older adult population. However, there is a lack of knowledge about how to profile older users to most effectively personalize BC solutions. Self-awareness and social awareness are BC strategies commonly used in commercially available applications to promote physical activities. Through a randomized controlled trial (N = 53), we studied the effect of some personal factors on the physical activity of older adults under these two strategies. For this purpose, each BC strategy was implemented in a mobile application. Based on the statistical analysis of the measured step data and the collected questionnaire data, we identified a list of personal factors to personalize each BC strategy towards improved physical activity. Hereby we suggest how to create effective motivational profiles and provide design recommendations to personalize these BC strategies toward increased physical activity for older users.

2021

Chargement

EHR: a Sensing Technology Readiness Model for Lifestyle Changes

Yu Chen, Danni Le, Pearl Pu Faltings, Zerrin Yumak

Interest in developing user-centered sensing technologies for personalized behavior change has gained significant momentum. However, very little research work has been done to understand issues relative to user readiness and adoption of the sensing technologies to change their behaviors, especially the motivations as well as the concerns and impediments for adoption. We have developed a model called EHR (e-health readiness), to understand and explain the relationship between user habits, perceived healthiness and beliefs towards sensing technologies, and how these factors influence user readiness to use sensing technologies to manage their wellness. We then validate the model using psychometric methods by a large-scale user study (N = 541). Results show overall readiness to sensing technologies is positively influenced by readiness to monitor health conditions, share data within social networks, and receive recommendations. Additionally, readiness is significantly impacted by perceptions of healthiness, technology satisfaction and usefulness of such technology. Finally, we summarize user motivations and concerns for pervasive sensing tools through qualitative analysis on their comments. We present this model and the results of this survey to shed light on designing future sensing technologies for behavior change.

Springer2017

Chargement

Afficher plus

Personnes associées (2)

Personnes associées

Chargement

Unités associées (3)

Unités associées

Chargement

Concepts associés (5)

Concepts associés

Chargement

Cours associés (6)

1ère année: bases nécessaires à la représentation informatique 2D (3D). Passage d'un à plusieurs logiciels: compétence de choisir les outils adéquats en 2D et en 3D. Mise en relation des outils de CAO et DIM: regard critique et aptitude à choisir les méthodes nécessaires au résultat recherché.

Ce cours a pour objectif de présenter la fonction logistique de l'entreprise dans le cadre d'une approche globale, de la logistique au supply chain management, en insistant sur l'importance de la demande "client" tirant tous processus de la chaîne d'ajout de valeur du produit ou du service

Computer environments such as educational games, interactive simulations, and web services provide large amounts of data, which can be analyzed and serve as a basis for adaptation. This course will cover the core methods of user modeling and personalization, with a focus on educational data.

Afficher plus

Cours associés

Chargement

Séances de cours associées (8)

Séances de cours associées

Chargement