ABSTRACT In this paper we present an approach for reusing agent-based reasoning capabilities by m... more ABSTRACT In this paper we present an approach for reusing agent-based reasoning capabilities by making them available for invocation as Web services. In this way, we provide the missing link between the highly interoperable Web services and the autonomicity and intelligence of agent-based systems, so that the latter can be seamlessly integrated into the knowledge-rich Semantic Web environment without being compromised by isolated communication platforms and languages or restricted to only one or just few reasoning formalisms. We have achieved this by extending the EMERALD framework for agent based reasoning with a Web service interface. Our approach is exemplified by the development of an online system for intelligent brokering of apartment rentals. The broker intelligence is captured as a defeasible knowledge base, while its problem solving process involves the invocation of third party defeasible reasoning Web services included into the EMERALD framework.
ABSTRACT This paper identifies “island model” as the state of the art approach for distributing A... more ABSTRACT This paper identifies “island model” as the state of the art approach for distributing Ant Colony Optimization algorithms. We present a comparison of the island model with our own distribution model called ACODA. For this purpose we expanded our initial ACODA framework to accommodate the implementation of the island model, and then we carried out a series of experiments to support our comparison. Our results show that our approach offers better scalability and execution times without sacrificing solution quality in the case of the Traveling Salesman Problem.
ABSTRACT There is great concern today about what our society can do to protect itself from all ki... more ABSTRACT There is great concern today about what our society can do to protect itself from all kinds of environmental hazards ranging from man-made disasters, like chemical spills to natural disasters, like earthquakes or floods. Luckily, numerous experts specifically trained to handle such situations, can come in our aid. However, a potentially troublesome challenge still presents itself: coordinating the environmental experts and ensuring that the most appropriate one(s) answer the call. In this paper, a modern technological model is proposed which combines the robustness of the JADE multi-agent framework with the versatility of the ANDROID mobile operating system to provide its users with automated negotiation protocols for experts' selection, while maintaining a variable degree of the experts' autonomy according to their stated preferences. In order to compute the estimated travel times between the various locations, the system uses the Google Directions API which is perfectly fit for the small-scale experimental scenario we have conducted, but it could also suit larger-scale applications if necessary.
Swarm Intelligence(SI) is the emergent collective intelligence of groups of simple agents. Econom... more Swarm Intelligence(SI) is the emergent collective intelligence of groups of simple agents. Economy is an example of SI. Simulating an economy using Ant Colony algorithms would allow prediction and control of fluctuations in the complex emergent behavior of the simulated system. Such a simulation is far beyond SI's capabilities, which is still in its infancy. This paper presents a distributed approach implementing Ant Colony Optimization(ACO). We present our agent based architecture of ACO and initial experimental results on the Travelling Salesman Problem. The innovation of our work consists of: i)representing network nodes as software agents, ii) representing software agents as software objects that are passed as messages between the nodes according to ACO rules.
Abstract This paper presents a framework of ICT solutions developed in the EU research project DI... more Abstract This paper presents a framework of ICT solutions developed in the EU research project DIADEM that supports environmental management for chemical hazards in industrial areas, with an enhanced capacity to assess population exposure and health risks, alert relevant groups and organize efficient response. The emphasis is on advanced solutions which are economically feasible and maximally exploit the existing communication, computing and sensing resources.
Abstract This paper introduces a multi-agent framework for distributed multiplayer game developme... more Abstract This paper introduces a multi-agent framework for distributed multiplayer game development and simulations. The framework allows the incorporation and experimentation with different strategies of the Players, possibly including intelligent behaviors. The framework consists of a set of generic agent types that must be specialized and configured for a specific game. The framework uses a generic agent that enforces the rules of the game, as well as generic bot-agents that represent the game Players. To support our claims of ...
Abstract This paper presents a configurable distributed architecture for Ant Colony Optimization.... more Abstract This paper presents a configurable distributed architecture for Ant Colony Optimization. We represent the problem environment as a distributed multi-agent system and we reduce ant management to messages that are asynchronously exchanged between agents. The experimental setup allows the deployment of the system on computer clusters, as well as on ordinary computer networks. We present experimental results that we obtained by utilizing our system to solve nontrivial instances of the Traveling Salesman Problem. ...
Abstract Recently we were involved in the development of a distributed agent-based English auctio... more Abstract Recently we were involved in the development of a distributed agent-based English auction server. The focus of the work was on emphasizing the advantages brought by the multi-agent systems technology to the high-level of abstraction, modularity and performance of the server architecture, and its implementation. Less effort was spent on the analysis of its external functionalities and usability, as well as on approaching the implementation of a realistic system for online auctions. Therefore, in this paper we present our solution, in ...
Collaboration between human experts during distributed problem solving for disaster management re... more Collaboration between human experts during distributed problem solving for disaster management requires advanced self-configuration mechanisms for selection of potentially good service providers. Self-configuration is based on a framework for development of cooperative multi-issue one-to-many service negotiations. The framework allows the definition of: negotiation protocols, negotiation subjects composed of multiple negotiation issues, properties of negotiation issues, and utility functions of participant stakeholders. ...
… Collective Intelligence. Semantic Web, Social Networks …, Jan 1, 2009
Abstract. Nowadays organizations are willing to share and cooperate in building better services a... more Abstract. Nowadays organizations are willing to share and cooperate in building better services and products. A distributed framework is needed to support these current trends. An ant colony metaphor is a great source of inspiration to build such a framework. This paper proposes a study of Ant Colony Optimization on handling dynamic networks. The novelty of our work consists in using a multi-agent architecture to model the dynamic network and artificial intelligence to decide on the type of ants needed. Our approach allows greater ...
Abstract This paper presents a distributed agent-based server architecture for English auctions. ... more Abstract This paper presents a distributed agent-based server architecture for English auctions. Bids of auction participants are handled by a hierarchical organization of agents that can be efficiently distributed on a computer network. This approach avoids the bottlenecks of bid processing that might occur during periods of heavy bidding, like for example snipping. We present experimental results that show a significant improvement of the server throughput compared with the architecture where one auction manager agent is ...
ABSTRACT In this paper we present an approach for reusing agent-based reasoning capabilities by m... more ABSTRACT In this paper we present an approach for reusing agent-based reasoning capabilities by making them available for invocation as Web services. In this way, we provide the missing link between the highly interoperable Web services and the autonomicity and intelligence of agent-based systems, so that the latter can be seamlessly integrated into the knowledge-rich Semantic Web environment without being compromised by isolated communication platforms and languages or restricted to only one or just few reasoning formalisms. We have achieved this by extending the EMERALD framework for agent based reasoning with a Web service interface. Our approach is exemplified by the development of an online system for intelligent brokering of apartment rentals. The broker intelligence is captured as a defeasible knowledge base, while its problem solving process involves the invocation of third party defeasible reasoning Web services included into the EMERALD framework.
ABSTRACT This paper identifies “island model” as the state of the art approach for distributing A... more ABSTRACT This paper identifies “island model” as the state of the art approach for distributing Ant Colony Optimization algorithms. We present a comparison of the island model with our own distribution model called ACODA. For this purpose we expanded our initial ACODA framework to accommodate the implementation of the island model, and then we carried out a series of experiments to support our comparison. Our results show that our approach offers better scalability and execution times without sacrificing solution quality in the case of the Traveling Salesman Problem.
ABSTRACT There is great concern today about what our society can do to protect itself from all ki... more ABSTRACT There is great concern today about what our society can do to protect itself from all kinds of environmental hazards ranging from man-made disasters, like chemical spills to natural disasters, like earthquakes or floods. Luckily, numerous experts specifically trained to handle such situations, can come in our aid. However, a potentially troublesome challenge still presents itself: coordinating the environmental experts and ensuring that the most appropriate one(s) answer the call. In this paper, a modern technological model is proposed which combines the robustness of the JADE multi-agent framework with the versatility of the ANDROID mobile operating system to provide its users with automated negotiation protocols for experts' selection, while maintaining a variable degree of the experts' autonomy according to their stated preferences. In order to compute the estimated travel times between the various locations, the system uses the Google Directions API which is perfectly fit for the small-scale experimental scenario we have conducted, but it could also suit larger-scale applications if necessary.
Swarm Intelligence(SI) is the emergent collective intelligence of groups of simple agents. Econom... more Swarm Intelligence(SI) is the emergent collective intelligence of groups of simple agents. Economy is an example of SI. Simulating an economy using Ant Colony algorithms would allow prediction and control of fluctuations in the complex emergent behavior of the simulated system. Such a simulation is far beyond SI's capabilities, which is still in its infancy. This paper presents a distributed approach implementing Ant Colony Optimization(ACO). We present our agent based architecture of ACO and initial experimental results on the Travelling Salesman Problem. The innovation of our work consists of: i)representing network nodes as software agents, ii) representing software agents as software objects that are passed as messages between the nodes according to ACO rules.
Abstract This paper presents a framework of ICT solutions developed in the EU research project DI... more Abstract This paper presents a framework of ICT solutions developed in the EU research project DIADEM that supports environmental management for chemical hazards in industrial areas, with an enhanced capacity to assess population exposure and health risks, alert relevant groups and organize efficient response. The emphasis is on advanced solutions which are economically feasible and maximally exploit the existing communication, computing and sensing resources.
Abstract This paper introduces a multi-agent framework for distributed multiplayer game developme... more Abstract This paper introduces a multi-agent framework for distributed multiplayer game development and simulations. The framework allows the incorporation and experimentation with different strategies of the Players, possibly including intelligent behaviors. The framework consists of a set of generic agent types that must be specialized and configured for a specific game. The framework uses a generic agent that enforces the rules of the game, as well as generic bot-agents that represent the game Players. To support our claims of ...
Abstract This paper presents a configurable distributed architecture for Ant Colony Optimization.... more Abstract This paper presents a configurable distributed architecture for Ant Colony Optimization. We represent the problem environment as a distributed multi-agent system and we reduce ant management to messages that are asynchronously exchanged between agents. The experimental setup allows the deployment of the system on computer clusters, as well as on ordinary computer networks. We present experimental results that we obtained by utilizing our system to solve nontrivial instances of the Traveling Salesman Problem. ...
Abstract Recently we were involved in the development of a distributed agent-based English auctio... more Abstract Recently we were involved in the development of a distributed agent-based English auction server. The focus of the work was on emphasizing the advantages brought by the multi-agent systems technology to the high-level of abstraction, modularity and performance of the server architecture, and its implementation. Less effort was spent on the analysis of its external functionalities and usability, as well as on approaching the implementation of a realistic system for online auctions. Therefore, in this paper we present our solution, in ...
Collaboration between human experts during distributed problem solving for disaster management re... more Collaboration between human experts during distributed problem solving for disaster management requires advanced self-configuration mechanisms for selection of potentially good service providers. Self-configuration is based on a framework for development of cooperative multi-issue one-to-many service negotiations. The framework allows the definition of: negotiation protocols, negotiation subjects composed of multiple negotiation issues, properties of negotiation issues, and utility functions of participant stakeholders. ...
… Collective Intelligence. Semantic Web, Social Networks …, Jan 1, 2009
Abstract. Nowadays organizations are willing to share and cooperate in building better services a... more Abstract. Nowadays organizations are willing to share and cooperate in building better services and products. A distributed framework is needed to support these current trends. An ant colony metaphor is a great source of inspiration to build such a framework. This paper proposes a study of Ant Colony Optimization on handling dynamic networks. The novelty of our work consists in using a multi-agent architecture to model the dynamic network and artificial intelligence to decide on the type of ants needed. Our approach allows greater ...
Abstract This paper presents a distributed agent-based server architecture for English auctions. ... more Abstract This paper presents a distributed agent-based server architecture for English auctions. Bids of auction participants are handled by a hierarchical organization of agents that can be efficiently distributed on a computer network. This approach avoids the bottlenecks of bid processing that might occur during periods of heavy bidding, like for example snipping. We present experimental results that show a significant improvement of the server throughput compared with the architecture where one auction manager agent is ...
Uploads
Papers by Sorin Ilie