Andrei Olaru

A Context-Aware Multi-Agent System as a Middleware for Ambient Intelligence

There is currently a lot of work in Ambient Intelligence—or AmI—reporting on specific scenarios, or on implementations of particular cases. In the same time, there is a common agreement of the fact that AmI applications should be pervasive, covering a large number of devices, assisting a large number of people, and serving a large number of purposes. In an attempt to achieve scalable scenarios and implementations, we have focused our research on the development of a generic middleware layer for the context-aware transfer and exchange of information between devices. This paper presents a model for a such middleware, based on software agents, in which context-awareness is implemented both in the agent’s representation of context information, and in the logical topology of the agent system. The model is oriented towards decentralization of the system and relies mostly on local behavior. The paper also reports on several proof-of-concept applications that have been developed and tested using the proposed model, proving thus the validity of the approach.

Ao dai: agent oriented design for ambient intelligence

In this paper we present mobile Multi-Agent Systems (MAS) as a specific paradigm to design intelligent and distributed applications in the context of Ambient Intelligence (AmI). We discuss how mobility, coupled with MAS, can be useful to meet the requirements of AmI. Indeed, the main features of mobile MAS, such as natural distribution of the system, inherent intelligence of the agents, and their mobility help to address a large scope of distributed applications in the domain of AmI. Other features of MAS, like multi-agent planning, context-awareness and self-adaptation are also very useful to bring an added value to AmI applications. They allow the implementation of both intelligent and collaborative agent behavior. This paper presents the Ao Dai project, that employs the mobile MAS paradigm, and serves as a prototype AmI environment. We also illustrate the functioning of the application through a scenario of user guidance in a smart environment.

Graphs and Patterns for Context-Awareness

A central issue in the domain of Ambient Intelligence is context - awareness. While previous research in the field presents complex context-aware infrastructures, but with little flexibility and fixed context representations, this paper presents a simple, flexible and decentralized representation of context, for the detection of appropriate context-aware action. This representation is inspired from notions like concept maps and conceptual graphs. A formalism for context patterns, that allows the detection and solution of problems, based on the user’s context, is also proposed.

Multi-Agent Systems: A Paradigm to Design Ambient Intelligent Applications

In this paper we present a Multi-Agent System (MAS) paradigm and discuss how it can be used to design intelligent and distributed systems. The main features of this MAS, such as natural distribution of the system, inherent intelligence of its agents, and their mobility help address a large scope of distributed applications including the domain of ambient intelligence. Other features of the MAS, like multiagent planning, context-awareness and adaptation are also very useful since they bring added value, by allowing to implement intelligent and collective behavior. The paper also presents a scenario of ambient intelligence and shows how it could be designed using the MAS paradigm.

Local mining of Association Rules with Rule Schemas

One of the central problems in Knowledge Discovery in Databases, more precisely in the field of Association Rule Mining, relies on the very large number of rules that classic rule mining systems extract. This problem is usually solved by means of a post-processing step, that filters the entire volume of extracted rules, in order to output only a few potentially interesting ones. This article presents a new approach that allows the user to explore the rule space locally, incrementally, without the need to extract and post-process all rules in the database. This solution is based on Rule Schemas, a new formalism designed in order to improve the representation of user beliefs and expectations, and on a novel algorithm for local association rule mining starting from Schemas. The proposed algorithm has been successfully tested on the database provided by Nantes Habitat.

Context Matching for Ambient Intelligence Applications

Reliable and scalable Ambient Intelligence means a distributed system of agents that are capable of working together or autonomously, depending on the requirements of the situation. In previous research we have argued in favor of the use of a representation for context information that can be distributed among agents, so that each agent knows only the information that is relevant to its activity. Recognizing interesting information or relevant situations is done by using context patterns -- graph patterns with potentially unknown nodes and edges labeled with regular expressions. In this context, a major challenge is for agents to use a graph matching algorithm that is adequate to the possibilities of the devices on which the agents are running. Moreover, it is necessary that the algorithm is able to provide partial matches. This paper presents an algorithm specifically designed for this problem, that uses growing partial matches to obtain the maximum sub-graph of the context graph that matches (part of) the context pattern. Experiments were performed with the algorithm and its performance has been compared with that of other algorithms adapted to our problem.

Ambient Intelligence: From Scenario Analysis towards a Bottom-Up Design

In the domain of Ambient Intelligence, research goals are many times driven by scenarios that help envisage a world enriched by ambient, pervasive, intelligent services. So far, scenarios have most times presented the perception that one person has upon the system, with few details on how the system should work in the background in order to deal with realistic requirements. In this paper, starting from scenarios presented in previous research, we identify features and requirements for AmI systems and propose two new scenarios, focusing on the way information is exchanged beyond the perspective of, and transparent to, the user of the system.We also agentify one of the scenarios, giving insight on how an AmI system may be built, using software agents, in order to fulfill the requirements.

Context-Awareness in Multi-agent Systems for Ambient Intelligence

There is a large body of research that lies at the intersection of the domains of context-awareness, multi-agent systems (MAS) and Ambient Intelligence (AmI)/Ubiquitous Computing (UbiComp). This is because, while multi-agent systems are an appropriate architecture for AmI implementations, one essential requirement for AmI is to be aware of the user’s context and to act accordingly. In order to implement context-awareness in a MAS for AmI applications, one must on the one hand choose an appropriate representation for context, that is suitable for agents of all sizes and functions, and, on the other hand, create an agent-based architecture that facilitates communication between agents that share context. This chapter presents a model, mechanisms and methods for integrating context-awareness in multi-agent systems for AmI. The model is based on experience with several implementations of MAS dealing with various aspects of context-awareness.

tATAmI-2 -- A Flexible Framework for Modular Agents

The paper introduces tATAmI-2, an agent development framework that allows the creation of modular agents and permits a great deal of flexibility with respect to the manner in which various functionality, such as agent communication, is implemented. The framework strikes a good balance between flexibility and ease of use, by offering several pre-implemented agent components and communication platforms. The architecture of the framework relies on three elements: the ability to simultaneously start multiple platforms for agent management and communication, the ability to load agents in a number of manners, and, in the case of composite agents, the ability to customize the component set of an agent, including the possibility to add application-specific components, or to use components recommended by the platform for certain functionalities (such as communication).

tATAmI: A Platform for the Development and Deployment of Agent-based AmI Applications

In the vision of a future pervaded by Ambient Intelligence (AmI), innovative solutions are required in order to facilitate the development of applications able to fulfill the real needs of the users. In using agents for building AmI applications, there is a lack of platforms and languages that strike a good balance between flexibility and power of expression, on the one hand, and ease of use and quick deployment, on the other hand. We introduce the tATAmI platform, which together with the S-CLAIM AOP language presents a suitable solution for these issues. This paper presents the architecture of tATAmI together with a brief description of two scenarios that were implemented using the platform and some other important technical aspects concerning it.