KEMNAD: A KNOWLEDGE ENGINEERING METHODOLOGY FOR NEGOTIATING AGENT DEVELOPMENT

Automated negotiation is widely applied in various domains. However, the development of such systems is a complex knowledge and software engineering task. So, a methodology there will be helpful. Unfortunately, none of existing methodologies can offer sufficient, detailed support for such system development. To remove this limitation, this paper develops a new methodology made up of (1) a generic framework (architectural pattern) for the main task, and (2) a library of modular and reusable design pattern (templates) of subtasks. Thus, it is much easier to build a negotiating agent by assembling these standardized components rather than reinventing the wheel each time. Moreover, because these patterns are identified from a wide variety of existing negotiating agents (especially high impact ones), they can also improve the quality of the final systems developed. In addition, our methodology reveals what types of domain knowledge need to be input into the negotiating agents. This in turn provides a basis for developing techniques to acquire the domain knowledge from human users. This is important because negotiation agents act faithfully on the behalf of their human users and thus the relevant domain knowledge must be acquired from the human users. Finally, our methodology is validated with one high impact system.     

Agent-based decentralised coordination for sensor networks using the max-sum algorithm

In this paper, we consider the generic problem of how a network of physically distributed, computationally constrained devices can make coordinated decisions to maximise the effectiveness of the whole sensor network. In particular, we propose a new agent-based representation of the problem, based on the factor graph, and use state-of-the-art DCOP heuristics (i.e., DSA and the max-sum algorithm) to generate sub-optimal solutions. In more detail, we formally model a specific real-world problem where energy-harvesting sensors are deployed within an urban environment to detect vehicle movements. The sensors coordinate their sense/sleep schedules, maintaining energy neutral operation while maximising vehicle detection probability. We theoretically analyse the performance of the sensor network for various coordination strategies and show that by appropriately coordinating their schedules the sensors can achieve significantly improved system-wide performance, detecting up to 50 % of the events that a randomly coordinated network fails to detect. Finally, we deploy our coordination approach in a realistic simulation of our wide area surveillance problem, comparing its performance to a number of benchmarking coordination strategies. In this setting, our approach achieves up to a 57 % reduction in the number of missed vehicles (compared to an uncoordinated network). This performance is close to that achieved by a benchmark centralised algorithm (simulated annealing) and to a continuously powered network (which is an unreachable upper bound for any coordination approach).     

Designing a successful trading agent:A fuzzy set approach

Software agents are increasingly being used to represent humans in online auctions. Such agents have the advantages of being able to systematically monitor a wide variety of auctions and then make rapid decisions about what bids to place in what auctions. They can do this continuously and repetitively without losing concentration. To provide a means of evaluating and comparing (benchmarking) research methods in this area the trading agent competition (TAC) was established. This competition involves a number of agents bidding against one another in a number of related auctions (operating different protocols) to purchase travel packages for customers. Against this background, this paper describes the design, implementation and evaluation of SouthamptonTAC, one of the most successful participants in both the Second and the Third International Competitions. Our agent uses fuzzy techniques at the heart of its decision making: to make bidding decisions in the face of uncertainty, to make predictions about the likely outcomes of auctions, and to alter the agent's bidding strategy in response to the prevailing market conditions.     

Nightly Home Hemodialysis: Fifteen Months of Experience in Lynchburg,Virginia

What constitutes adequate dialysis has been debated in the nephrology literature over the past eight years. The mortality rate of patients on dialysis in the United States is about 20% per year. We believed that short and infrequent dialysis sessions contributed to poor outcomes. To improve the results, Lynchburg Nephrology started the nightly home hemodialysis (NHHD) program in September 1997. Ten patients were trained in the first 15 months of the program. Patients dialyzed 7 – 9 hours, 6 nights/week, using the Fresenius 2008H machine. A standard dialysis solution with 2.0 mEq/L potassium, calcium concentration of 3.0 – 3.5 mEq/L was used. Dialysis solution flow rates were 200 – 300 mL/min. Serum phosphate levels were maintained above 2.5 mg/dL by adding 0 – 45 mL Fleet's Phosphosoda to the bicarbonate bath. Patients had marked improvement in quality of life as measured with the SF-36. Blood pressure was better controlled with fewer medications. All phosphate binders were eliminated. Caloric intake and protein intake increased to normal levels as measured by three-day dietary histories pre-NHHD, and at 3, 6, and 12 months on NHHD. Epoetin alfa dosages were reduced by about 50%. Nightly home hemodialysis should be considered as a valuable modality option for end-stage renal disease patients; it is potentially superior to conventional thrice-weekly hemodialysis.     

Using Multi-Layer Perceptrons to Predict Vehicle Pass-By Noise

All new vehicle designs have to pass a legislative, noise emission test – the pass-by noise test. In the highly competitive automotive industry, it is important to predict the test result early in the design process, rather than waiting until a prototype is built. Engineers can guess test results about aswell as the best, although inadequate, analytical models. They achieve this by using experience and their knowledge of acoustics and of the vehicles design. Neural networks should also be capable of pass-by noise prediction, learning from the results of previous tests. This paper describes a neural network approach to the problem. First, expert knowledge is used to select vehicle design and test parameters to present as inputs to a multi-layer perceptron. Since data is scarce, the problem is broken down into two stages, vehicle performance and pass-by noise. The two trained networks are evaluated and their performance discussed.     

TRAVOS: Trust and Reputation in the Context of Inaccurate Information Sources

In many dynamic open systems, agents have to interact with one another to achieve their goals. Here, agents may be self-interested, and when trusted to perform an action for another, may betray that trust by not performing the action as required. In addition, due to the size of such systems, agents will often interact with other agents with which they have little or no past experience. There is therefore a need to develop a model of trust and reputation that will ensure good interactions among software agents in large scale open systems. Against this background, we have developed TRAVOS (Trust and Reputation model for Agent-based Virtual OrganisationS) which models an agent’s trust in an interaction partner. Specifically, trust is calculated using probability theory taking account of past interactions between agents, and when there is a lack of personal experience between agents, the model draws upon reputation information gathered from third parties. In this latter case, we pay particular attention to handling the possibility that reputation information may be inaccurate.     

Self-organized routing for wireless microsensor networks

In this paper, we develop an energy-aware self-organized routing algorithm for the networking of simple battery-powered wireless microsensors (as found, for example, in security or environmental monitoring applications). In these networks, the battery life of individual sensors is typically limited by the power required to transmit their data to a receiver or sink. Thus, effective network-routing algorithms allow us to reduce this power and extend both the lifetime and the coverage of the sensor network as a whole. However, implementing such routing algorithms with a centralized controller is undesirable due to the physical distribution of the sensors, their limited localization ability, and the dynamic nature of such networks (given that sensors may fail, move, or be added at any time and the communication links between sensors are subject to noise and interference). Against this background, we present a distributed mechanism that enables individual sensors to follow locally selfish strategies, which, in turn, result in the self-organization of a routing network with desirable global properties. We show that our mechanism performs close to the optimal solution (as computed by a centralized optimizer), it deals adaptively with changing sensor numbers and topology, and it extends the useful life of the network by a factor of three over the traditional approach.