Kuderna-Iulian Benta

Agent based smart house platform with affective control

In this paper, we describe our work in developing an agent based smart house platform using TAOM4E development methodology and the JADE-platform with the Jadex-extension. In order to remotely monitor its functions we implemented a Jade-Leap mobile application. We developed a central ontology for context representation and the support for behavior changes according to users affective feedback. We also emphasize the issues related to ontologies supporting agent communication, sensor integration and affective sensing. Experimental results have showed the proper functioning of this system, whose novelty consists in merging together a multi-agent system, an ontology-based mixed environment representation and reasoning engine, and a rule-based model of the users affective feedback.

Towards Real-Life Facial Expression Recognition Systems

Facial expressions are a set of symbols of great importance for human-to-human communication. Spontaneous in their nature, diverse and personal, facial expressions demand for real-time ...

Training the Behaviour Preferences on Context Changes

Personalized ambient intelligent systems should meet changes in user’s needs, which evolve over time. Our objective is to create an adaptive system that learns the user behaviour preferences. We propose *BAM – * Behaviour Adaptation Mechanism, a neural-network based control system that is trained, supervised by user’s (affective) feedback in real-time. The system deduces the preferred behaviour, based on the detection of affective state’s valence (negative, neutral and positive) from facial features analysis. The neural network is retrained periodically with the updated training set, obtained from the interpretation of the user’s reaction to the system’s decisions. We investigated how many training examples, rendered from user’s behaviour, are required in order to train the neural network so that it reaches an accuracy of at least 75%. We present the evolution of behaviour preference learning parameters when the number of context elements increases.