Nathan Griffiths

The boss online submission and assessment system

Computer programming lends itself to automated assessment. With appropriate software tools, program correctness can be measured, along with an indication of quality according to a set of metrics. Furthermore, the regularity of program code allows plagiarism detection to be an integral part of the tools that support assessment. In this paper, we describe a submission and assessment system, called BOSS, that supports coursework assessment through collecting submissions, performing automatic tests for correctness and quality, checking for plagiarism, and providing an interface for marking and delivering feedback. We describe how automated assessment is incorporated into BOSS such that it supports, rather than constrains, assessment. The pedagogic and administrative issues that are affected by the assessment process are also discussed.

From Agent Theory to Agent Construction: A Case Study

There is a growing body of work that concentrates on theoretical aspects of agents and multi-agent systems, and a complementary body of work concerned with building practical systems. However, the two have typically been unrelated. This gap between the theory and practice of intelligent agents has only relatively recently begun to be addressed. In this paper we describe the construction of an agent simulation environment that is based strongly on a formal theory of agent systems, but which is intended to serve in exactly this way as a basis for practical development. The paper briefly introduces the theory, then describes the system and the simple reactive agents built with it, but most importantly shows how it reflects the theoretical framework and how it facilitates incremental agent design and implementation. Using this example as a case-study, some possibilities for a methodology for the development of agent systems are discussed.

Fuzzy Trust for Peer-to-Peer Systems

Peer-to-peer (P2P) systems are based upon the cooperative interactions of member peers. Typically, peers are both autonomous and self-interested, meaning that there is no hierarchy of control or power, and that individuals seek to maximise their own goal achievement, rather than acting in a benevolent or socially-oriented manner. Consequently, interaction outcomes are uncertain, since peers can break their commitments or provide sub-standard contributions or services. Thus, when a peer cooperates it is entering into an uncertain interaction, that has an associated risk of failure or reduced performance. For peers to be effective they need some mechanism for managing this risk of failure. In this paper we show how peers can use trust to manage this risk. Our model of trust uses fuzzy logic to allow peers to represent and reason with uncertain and imprecise information regarding others’ trustworthiness.

Analysis of grid service composition with BPEL4WS

The open grid services infrastructure (OGSI) defines a distributed system framework by integrating grid and Web services technologies to facilitate resource sharing. In OGSI, Web services are supplemented with additional features in order to meet the requirements of grid computing. However, the issue of grid service composition is not well addressed in the OGSI framework. We apply BPEL4WS (business process execution language for Web services) as a business workflow description language for the composition of grid services. We provide an in depth analysis of BPEL4WS and OGSI in terms of their similarities and differences in areas such as life cycle management, Web service instantiation and instance group management. Based on our analysis we propose a high-level architecture to compliment OGSI with BPEL4WS for defining process workflow among grid services. We describe a prototype system which shows how the proposed architecture can be used in modelling or orchestrating grid services with BPEL4WS.

Cooperative Plan Selection Through Trust

Cooperation plays a fundamental role in multi-agent systems in which individual agents must interact for the overall system to function effectively. However, cooperation inherently involves an element of risk, due to the unpredictable nature of others behaviour In this paper, we consider the information needed by an agent to be able to assess the degree of risk involved in a particular course of action. In particular, we consider how this information can be used in the process of plan selection in BDI-like agents.

Manipulating convention emergence using influencer agents

Coordination in open multi-agent systems (MAS) can reduce costs to agents associated with conflicting goals and actions, allowing artificial societies to attain higher levels of aggregate utility. Techniques for increasing coordination typically involve incorporating notions of conventions, namely socially adopted standards of behaviour, at either an agent or system level. As system designers cannot necessarily create high quality conventions a priori, we require an understanding of how agents can dynamically generate, adopt and adapt conventions during their normal interaction processes. Many open MAS domains, such as peer-to-peer and mobile ad-hoc networks, exhibit properties that restrict the application of the mechanisms that are often used, especially those requiring the incorporation of additional components at an agent or society level. In this paper, we use Influencer Agents (IAs) to manipulate convention emergence, which we define as agents with strategies and goals chosen to aid the emergence of high quality conventions in domains characterised by heterogeneous ownership and uniform levels of agent authority. Using the language coordination problem (Steels in Artif Life 2(3):319–392, 1995), we evaluate the effect of IAs on convention emergence in a population. We show that relatively low proportions of IAs can (i) effectively manipulate the emergence of high-quality conventions, and (ii) increase convention adoption and quality. We make no assumptions involving agent mechanism design or internal architecture beyond the usual assumption of rationality. Our results demonstrate the fragility of convention emergence in the presence of malicious or faulty agents that attempt to propagate low quality conventions, and confirm the importance of social network structure in convention adoption.

Trust and Reputation

Trust and reputation have become standard approaches for supporting the management of interactions in distributed environments. Several alternative approaches have been proposed that take a wide range of approaches, including socio-cognitive, computational, and reputational mechanisms. In this chapter we introduce the various approaches to trust and reputation, and discuss how they relate to agents in a service-oriented computing context.

Enhancing peer-to-peer collaboration using trust

Distributed systems generally require their component parts to interact cooperatively, in order for the system as a whole to function effectively. For any given activity, there are typically several alternative components that have the required capabilities. In decentralised systems, where there is no overarching control, individual components are responsible for selecting other components with which to cooperate. However, the candidate components may be unreliable or dishonest, and are typically locally controlled. Such decentralised systems can be viewed as multi-agent systems, comprising autonomous agents that must cooperate for the system to be effective. Peer-topeer (P2P) systems are a subclass of decentralised distributed systems, in which not only is there no overarching control, but neither is there any hierarchy of control, power, or responsibly among the system components. Selecting appropriate peers to cooperate with is a challenging problem, since the candidate peers are autonomous and may be unreliable or dishonest. Peers need a mechanism for task delegation that takes the uncertainly of interactions into account. In this paper we present a mechanism, called MDT-R, that enables peers to delegate activities appropriately, using trust and the recommendations of other peers to meet individual preferences, such as minimising risk and maximising quality.

A simple trust model for on-demand routing in mobile ad-hoc networks

In a mobile ad-hoc network, nodes cannot rely on any fixed infrastructure for routing purposes. Rather, they have to cooperate to achieve this objective. However, the absence of any trusted third party in such networks may result in nodes deviating from the routing protocol for selfish or malicious reasons. The concept of trusted routing has been promoted to handle the problems selfish and malicious nodes cause to the network. In this paper, we focus on using trust in routing, and show how trust can mitigate against malicious behaviour.

Students' Perceptions of the Factors Leading to Unsuccessful Group Collaboration

A nationwide sample of university students completed a survey that asked questions about their perceptions of the factors that can cause problems which exist with online or general group work. Data were obtained from 173 students at more than 18 different universities in the United Kingdom. Three main problems that exist in group collaboration are identified through an extensive review of literature and addressed as problem scenarios in the survey. These include: poor motivation, lack of individual accountability and negative interdependence. Findings from the survey include that on average more than five factors are acknowledged by the students for each subcategory of problem, and for each scenario the factors that affect the group work are ranked by importance level. Furthermore, we find no statistically significant association between the students’ backgrounds and their perceptions of the factors identified.