Context Awareness in Ambient Systems by an Adaptive Multi-Agent Approach

Guivarch, Valérian; Camps, Valérie; Péninou, André

doi:10.1007/978-3-642-34898-3_9

Cited by 15 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A first evaluation of this Amadeus version applied to a simple example gave us encouraging results [4] [5]. Nevertheless, we observed a strong weakness regarding the required learning time when the number of perceived data increases.…”

Section: Our Mas Proposition For Ambient System: Amadeusmentioning

confidence: 87%

“…We propose to make an ambient system able to provide a relevant behaviour, based on the perceived user's actions, in order to assist him by realizing his actions on his behalf. We have already proposed Amadeus [4], an Adaptive Multi-Agent System that is able to learn the user's contexts while this user is performing recurrent actions in order to act on his behalf in similar situations.…”

Section: Our Mas Proposition For Ambient System: Amadeusmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Filtering of Useless Data in an Adaptive Multi-Agent System: Evaluation in the Ambient Domain

Guivarch

Camps

Péninou

et al. 2013

Advances on Practical Applications of Agents and Multi-Agent Systems

Self Cite

View full text Add to dashboard Cite

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. Abstract. Amadeus is an Adaptive Multi-Agent System whose goal is to observe and to learn users' behaviour in an ambient system in order to perform their recurrent actions on their behalf. Considering the large number of devices (data sources) that generally compose ambient systems, performing an efficient learning in such a domain requires filtering useless data. This paper focuses on an extended version of Amadeus taking account this requirement and proposes a solution based on cooperative interactions between the different agents composing Amadeus. An evaluation of the performances of our system as well as the encouraging obtained results are then shown.

show abstract

Section: Our Mas Proposition For Ambient System: Amadeusmentioning

confidence: 87%

Section: Our Mas Proposition For Ambient System: Amadeusmentioning

confidence: 99%

Dynamic Filtering of Useless Data in an Adaptive Multi-Agent System: Evaluation in the Ambient Domain

Guivarch

Camps

Péninou

et al. 2013

Advances on Practical Applications of Agents and Multi-Agent Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…For that, we assume that if a user performs an action in a given context, his action is the correct action to perform if a similar context occurs again. This paper completes a previous work [5] that presents the functional architecture of Amadeus in order to learn the behaviour to assign to an ambient system depending on the context. Section II describes related works regarding existing learning algorithms.…”

Section: Introductionmentioning

confidence: 91%

Self-Adaptation of a Learnt Behaviour by Detecting and by Managing User's Implicit Contradictions

Guivarch

Camps

Péninou

et al. 2014

2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)

View full text Add to dashboard Cite

This paper tackles the issue of ambient systems adaptation to users' needs while the environment and users' preferences evolve continuously. We propose the adaptive multiagent system Amadeus whose goal is to learn from users' actions and contexts how to perform actions on behalf of the users in similar contexts. However, considering the possible changes of users preferences, a previously learnt behaviour may become misfit. So, Amadeus must be able to observe if its actions on the system are contradicted by the users or not, without requiring any explicit feedback. The aim of this paper is to present the introspection capabilities of Amadeus in order to detect users contradictions and to self-adapt its behaviour at runtime. These mechanisms are then evaluated through a case study.

show abstract

“…Ambient intelligence (AmI) is the vision of a ubiquitous electronic environment that is non-intrusive and proactive, when assisting people during various activities (Olaru et al 2013;Guivarch et al 2012). For the design of such complex systems, multi-agent system (MAS) approaches offer interesting frameworks, since their agents are designed to be intelligent, proactive and autonomous (Doyle 1992).…”

Section: Introductionmentioning

confidence: 99%

Learning from situated experiences for a contextual planning guidance

Chaouche

Seghrouchni

Saïdouni

2016

J Ambient Intell Human Comput

View full text Add to dashboard Cite

International audienceThis paper presents AgLOTOS as an algebraic language dedicated to the specification of agent plans in ambient systems. AgLOTOS offers two levels of plans: elementary plans which are composed to produce an intention plan; The intention plans which are, in turn, composed to build an agent plan. The composition relies on several operators such as alternative and concurrency. Consequently, the plans can be built automatically as a system of concurrent processes. At the execution level, our approach helps the agent to select an optimal plan preserving the consistency of its intentions. The selection is based on an original and formal construction called contextual planning system (CPS), which presents the potential paths with the associated contexts while removing the inconsistent options. Finally, our CPS is improved by using past-experiences for a better guidance of the agent

show abstract

Context Awareness in Ambient Systems by an Adaptive Multi-Agent Approach

Cited by 15 publications

References 9 publications

Dynamic Filtering of Useless Data in an Adaptive Multi-Agent System: Evaluation in the Ambient Domain

Dynamic Filtering of Useless Data in an Adaptive Multi-Agent System: Evaluation in the Ambient Domain

Self-Adaptation of a Learnt Behaviour by Detecting and by Managing User's Implicit Contradictions

Learning from situated experiences for a contextual planning guidance

Contact Info

Product

Resources

About