Cooperative Software Agents Research Articles

Knowledge Management in Multimedia Communication Using Software Agents

This paper presents the problem of knowledge management related to software agents and agent systems (i.e. systems composed of communicating and cooperating software agents). The author presents basic theoretical issues, but the main focus is on the areas of application of software agents in multimedia communication - both existing and prospective applications. Particular attention has been paid to the applications of software agents for: supporting customer service processes through the Contact Centre system; supporting the distance learning system; creating virtual assistants in the form of conversation bots; searching for information in the Semantic Web, and assisting in setting up a video conference call. Software agents are often referred to as 'intelligent' - due to their intelligent behaviour. At their core, they involve: perception, reasoning, learning, communication and operation in complex environments, using all multimedia techniques and procedures. Software agents and agent systems, as presented in this article, represent a new approach to the analysis, design and implementation of complex (usually decentralised and distributed) computer systems, offering a whole range of concepts, techniques and tools to significantly improve the software development process. The ability of software agents to make autonomous decisions have been a subject of considerations. Among other things, they are based on the example of cognitive sciences, which deal with modelling real processes of information processing in humans and building programmes that imitate these processes. Research on the common understanding of shared knowledge and knowledge management in agent-based systems focuses on ontologies, understood as a description of the relationship between the way knowledge is represented and the concept represented by that knowledge. In contrast, research on knowledge sharing has focused on communication languages and their associated - interaction protocol and message transport protocol.

Policy-based Awareness Management (PAM): Case study of a wireless communication system at a hospital

The present paper evaluates the use of software agents to identify relevance of information, called awareness. This evaluation is based on existing policies and scenarios in the context of wireless communication of a hospital in Norway. The study is to address the lack of literature for experimental studies on a method to employ software agents for awareness identification. Research in computer supported cooperative work indicates the significant contributions of software agents to assist individuals. There are bodies of work that show awareness provides the means for software agents in which effective cooperation can take place. In addition, the role of the methods to identify awareness is emphasized in the literature of both computer supported cooperative work and software agents. This paper explains a step-wise process, called Policy-based Awareness Management, which allows agents to use policies as a source to identify awareness and thus change their behaviors accordingly. The contribution of this method is based on the concepts proposed by the logic of general awareness. The present study applies Directory Enabled Networks-next generation as the policy structure for the method. The paper evaluates the process via its application to identify the relevance of information in wireless communication scenarios in a hospital. The present study conducts observations, interviews and discussions on the wireless communication system of the hospital to identify the different scenarios happening in the system. The paper presents a set of simulations on these scenarios and concludes that the method is effective and cost-efficient.

Autonomic tracing of production processes with mobile and agent-based computing

Tracing items in a supply chain, across different enterprises and through the full processes scope, is today an inherently complex design task. Enterprises are typically comprised of hundreds of applications that are custom built at different times, acquired from third parties and parts of legacy systems, and also operating in multiple tiers of different manufacturing and information system platforms. Further, traceability is characterized by a goal-oriented approach, in which business-process analyses are driven by goal achievements rather than by systematic engineering processes. The use of a classical enterprise integration approach mostly needs tailoring to different applications. Due to the number and diversity of the systems and of their interactions, and to their dynamicity, it is difficult, costly, and therefore often not convenient to develop in large scale distributed systems. To overcome these issues, a supply chain traceability system with a high level of automation is discussed in this paper. In particular, the system adopts an agent-based approach, in which cooperative software agents find solutions to back-end tracing problems by self-organization. Such cooperative agents are based on a business process aware traceability model, and on a service-oriented composition paradigm. Furthermore, an interface agent assists each user to carry out the front-end tracking activities. Interface agents rely on the context-awareness paradigm to gain self-configurability and self-adaptation of the user interface, and on ubiquitous computing technology, i.e., mobile devices and radio-frequency identification, to perform agile and automatic lot identification. The paper comprises real-world experiences on the fashion supply chain.

An Ontology Driven Multi-Agent Approach to Integrated e-Health Systems

One aim of an integrated e-Health system is to improve the quality of healthcare by providing transparent access to patient information. The current health information management environment has numerous systems with varying techniques for representing and managing patient data. The increasing mobility of patients results in patient information being spread across these systems. Presented in this paper is a conceptual architecture for the interoperability of e-Health systems. This architecture uses multiple cooperating software agents that actively access, recognize, and associate the information in distributed, heterogeneous e-health systems. Using a layered ontology structure we show how ontology based multi-agent systems can be used to resolve discrepancies in terminology and/or structure. This involves a case study in a distributed Electronic Health Record (EHR) environment.

FUZZY STATE AGGREGATION AND POLICY HILL CLIMBING FOR STOCHASTIC ENVIRONMENTS

Reinforcement learning is one of the more attractive machine learning technologies, due to its unsupervised learning structure and ability to continually learn even as the operating environment changes. Additionally, by applying reinforcement learning to multiple cooperative software agents (a multi-agent system) not only allows each individual agent to learn from its own experience, but also opens up the opportunity for the individual agents to learn from the other agents in the system, thus accelerating the rate of learning. This research presents the novel use of fuzzy state aggregation, as the means of function approximation, combined with the fastest policy hill climbing methods of Win or Lose Fast (WoLF) and policy-dynamics based WoLF (PD-WoLF). The combination of fast policy hill climbing and fuzzy state aggregation function approximation is tested in two stochastic environments: Tileworld and the simulated robot soccer domain, RoboCup. The Tileworld results demonstrate that a single agent using the combination of FSA and PHC learns quicker and performs better than combined fuzzy state aggregation and Q-learning reinforcement learning alone. Results from the multi-agent RoboCup domain again illustrate that the policy hill climbing algorithms perform better than Q-learning alone in a multi-agent environment. The learning is further enhanced by allowing the agents to share their experience through a weighted strategy sharing.

UBIQUITOUS TRAVEL SERVICE DELIVERY

Free independent travelers require flexible, reactive service delivery due to their regularly changing location and activities and the lack of a wired Internet connection. A ubiquitous travel service delivery system that is able to dynamically deliver services in response to relevant events, such as changing location, availability of new last-minute specials, work opportunities, and safety issues can provide added value while retaining the flexibility that is so important to independent travelers. This article describes such a system. An engineering design research approach has been adopted to design the system. Issues addressed include traveler and service states and events, contexts, situations, and situation-action rules. An architecture is proposed that is based on distributed, cooperating software agents and mobile data technologies. The role of these agents is to continuously monitor situations that are occurring in the physical and virtual service spaces and to take the required action for any situations that are relevant to the traveler.

An architecture for dynamic and evolving cooperative software agents

This paper presents an architectural model to construct cooperative and evolutionary agent-based software systems. Here, a software system is defined as one consisting of a set of agents which interact by executing actions and by determining system functionality. Because the agents need intercommunication and coordination, we propose a model that allows this communication between agents and preserves system activity. This coordination model uses a blackboard as the means of communication between the system agents. The system architecture presented is dynamic in the sense that the modelled system can evolve and be adapted to its new functions. To do this, we distinguish two levels in the architecture: the system and the meta-system levels. The system level describes the system's structure and its functionality, while the meta-system level allows us to effect changes in the system in such a way as to preserve the system's integrity and restrictions. Modifications at the system level are carried out when the developer interacts at the meta-system level. System users interact only at the system level.

VISUAL SPECIFICATION AND MONITORING OF SOFTWARE AGENTS IN DECENTRALIZED PROCESS-CENTRED ENVIRONMENTS

Distributed, cooperating software agents are useful in many problem domains, such as task automation and work coordination in process-centered environments. We describe a visual language for specifying such software agents, which uses the composition of event-based software components. These specifications may contain interfaces to remotely executing agents, and agents may be run locally or on distributed machines using a decentralized software architecture. As facilities to configure and monitor the state and activities of such distributed, cooperating software agents is essential, we provide primarily visual capabilities to achieve this. Our static and dynamic software agent visualization techniques have been used on several projects where distributed information processing, system interfacing, work coordination and task automation are required. We illustrate our visualization techniques with examples from these domains.

A framework for building cooperative software agents in medical applications

Exploiting the information technology may have a great impact on improving cooperation and interoperability among the different professionals taking part to the process of delivering health care services. New paradigms are therefore being devised considering software systems as autonomous agents able to help professionals in accomplishing their duties. To this aim those systems should encapsulate the skills for solving a given set of tasks and possess the social ability to cooperate in order to fetch the required information and knowledge. This paper illustrates a methodology facilitating the development of interoperable intelligent software agents for medical applications and proposes a generic computational model for implementing them. That model may be specialized in order to support all the different information and knowledge related requirements of a Hospital Information System. The architecture is being tested for implementing a prototype system able to coordinate the joint efforts of the professionals involved in managing patients affected by Acute Myeloid Leukemia.

Cooperating agents for 3-D scientific data interpretation

Many organizations collect vast quantities of 3D scientific data in volumetric form for a range of purposes, including resource exploration, market forecasting and process modeling. Traditionally, these data have been interpreted by human experts with only minimal software assistance. However, such manual interpretation is a painstakingly slow and tedious process. Moreover, since interpretation involves subjective judgments and each interpreter has different scientific knowledge and experience, the formulation of an effective interpretation often requires the cooperation of numerous such experts. Hence there is a pressing need for a software system in which individual interpretations can be generated automatically and then refined through the use of cooperative reasoning and information sharing. To this end, a prototype system, SurfaceMapper, has been developed in which a community of cooperating software agents automatically locate and display interpretations in a volume of 3D scientific data. The challenges and experiences in designing and building such a system are discussed. Particular emphasis is given to the agents' interactions and an empirical evaluation of the effectiveness of different cooperation strategies is presented.

Constraint-based protocols for distributed problem solving

Distributed Problem Solving (DPS) approaches decompose problems into subproblems to be solved by interacting, cooperative software agents. Thus, DPS is suitable for solving problems characterized by many interdependencies among subproblems in the context of parallel and distributed architectures. Concurrent Constraint Programming (CCP) provides a powerful execution framework for DPS where constraints define local problem solving and the exchange of information among agents declaratively. To optimize DPS, the protocol for constraint communication must be tuned to the specific kind of DPS problem and the characteristics of the underlying system architecture. In this paper, we provide a formal framework for modeling different problems and we show how the framework applies to simple yet generalizable examples.

Cooperative software agents for the Unix domain

The paper presents an agent architecture that integrates multiple capabilities into a single intelligent agent allowing it to interact both with other agents through an expressive agent communications language and with humans through a human agent interface, and to satisfy external requests either through the direct execution of a set of actions or through a plan defined by an internal planner. This agent architecture has been implemented using a programming environment which takes advantage of object-oriented programming features, and has been experimented with in the Unix domain specializing it to define an agent able to perform a set of Unix commands and to execute actions in cooperation with other agents.