| Autor: |
Kuderna-Iulian, Benţa, Marcel, Cremene, Valeriu, Todica |
| Zdroj: |
Ambient Assistive Health & Wellness Management in the Heart of the City; 2009, p74-81, 8p |
| Abstrakt: |
The nowadays smart homes run predefined rules, but the user΄s desired behaviour for a smart home varies, as his/her needs change over time. To edit the initial rules is a difficult task for a usual user. We propose a control mechanism that allows the system to learn the new behaviour preferences without editing the rules, but responding emotionally to the system΄s decisions. In order to capture the emotion reaction we use FaceReader, a tool for facial analyses, adapting it to read three valence levels that work as positive, negative or neutral feedback. The results in training a MLP neural network to learn the preferred behaviour from the user΄s emotional reaction are discussed. Ontology is used in order to describe the context. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
