<link rel="Stylesheet" href="/infosci/styles.css" type="text/css">
<h2>Information Science Discussion Papers Series: 2005 Abstracts</h2>
<hr>
<h3><a name="dp2005-01">2005/01: A rule language for modelling and monitoring social expectations in multi-agent systems</a></h3>
<h4>S. Cranefield</h4>
<p>This paper proposes a rule language for defining social expectations based on a metric interval temporal logic with past and future modalities and a current time binding operator. An algorithm for run-time monitoring compliance of rules in this language based on formula progression is also presented.</p>
<p><a href="papers/dp2005-01.pdf">Download</a> (PDF, 192 KB)</p>
<hr>
<h3><a name="dp2005-02">2005/02: An application of Bayesian network for predicting object-oriented software maintainability</a></h3>
<h4>C. van Koten and A. Gray</h4>
<p>As the number of object-oriented software systems increases, it becomes more important for organizations to maintain those systems effectively. However, currently only a small number of maintainability prediction models are available for objectoriented systems. This paper presents a Bayesian network maintainability prediction model for an object-oriented software system. The model is constructed using object-oriented metric data in Li and Henry’s datasets, which were collected from two different object-oriented systems. Prediction accuracy of the model is evaluated and compared with commonly used regression-based models. The results suggest that the Bayesian network model can predict maintainability more accurately than the regression-based models for one system, and almost as accurately as the best regression-based model for the other system.</p>
<p><a href="papers/dp2005-02.pdf">Download</a> (PDF, 289 KB)</p>
<hr>
<h3><a name="dp2005-03">2005/03: Self-adaptation and dynamic environment experiments with evolvable virtual machines</a></h3>
<h4>M. Nowostawski, L. Epiney and M. Purvis</h4>
<p>Increasing complexity of software applications forces researchers to look for automated ways of programming and adapting these systems. Self-adapting, self-organising software system is one of the possible ways to tackle and manage higher complexity. A set of small independent problem solvers, working together in a dynamic environment, solving multiple tasks, and dynamically adapting to changing requirements is one way of achieving true self-adaptation in software systems. Our work presents a dynamic multi-task environment and experiments with a self-adapting software system. The Evolvable Virtual Machine (EVM) architecture is a model for building complex hierarchically organised software systems. The intrinsic properties of EVM allow the independent programs to evolve into higher levels of complexity, in a way analogous to multi-level, or hierarchical evolutionary processes. The EVM is designed to evolve structures of self-maintaining, self-adapting ensembles, that are open-ended and hierarchically organised. This article discusses the EVM architecture together with different statistical exploration methods that can be used with it. Based on experimental results, certain behaviours that exhibit self-adaptation in the EVM system are discussed.</p>
<p><a href="papers/dp2005-03.pdf">Download</a> (PDF, 877 KB)</p>
<hr>
<h3><a name="dp2005-04">2005/04: A lightweight data integration architecture using Atom</a></h3>
<h4>D. Williamson and N. Stanger</h4>
<p>Cost is a major obstacle to the adoption of large-scale data integration solutions by small to medium enterprises (SME’s). We therefore propose a lightweight data integration architecture built around the Atom XML syndication format, which may provide a cost-effective alternative technology for SME’s to facilitate data integration, compared to expensive enterprise grade systems. The paper discusses the underlying principles and motivation for the architecture, the structure of the architecture itself, and our research goals.</p>
<p><a href="papers/dp2005-04.pdf">Download</a> (PDF, 301 KB)</p>
<hr>
<h3><a name="dp2005-05">2005/05: Agent-based integration of web services with workflow management systems</a></h3>
<h4>B.T.R. Savarimuthu, M. Purvis, M. Purvis and S. Cranefield</h4>
<p>Rapid changes in the business environment call for more flexible and adaptive workflow systems. Researchers have proposed that Workflow Management Systems (WfMSs) comprising multiple agents can provide these capabilities. We have developed a multi-agent based workflow system, JBees, which supports distributed process models and the adaptability of executing processes. Modern workflow systems should also have the flexibility to integrate available web services as they are updated. In this paper we discuss how our agent-based architecture can be used to bind and access web services in the context of executing a workflow process model. We use an example from the diamond processing industry to show how our agent architecture can be used to integrate web services with WfMSs.</p>
<p><a href="papers/dp2005-05.pdf">Download</a> (PDF, 439 KB)</p>
<hr>
<h3><a name="dp2005-06">2005/06: A graphical notation for physical database modelling</a></h3>
<h4>A. Pillay and N. Stanger</h4>
<p>In this paper we describe a graphical notation for physical database modelling. This notation provides database administrators with a means to model the physical structure of new and existing databases, thus enabling them to make more proactive and informed tuning decisions, compared to existing database monitoring tools.</p>
<p><a href="papers/dp2005-06.pdf">Download</a> (PDF, 337 KB)</p>
<hr>
<h3><a name="dp2005-07">2005/07: Framework for intrusion detection inspired by the immune system</a></h3>
<h4>M. Middlemiss</h4>
<p>The immune system is a complex and distributed system. It provides a multilevel form of defence, capable of identifying and reacting to harmful pathogens that it does not recognise as being part of its “self”. The framework proposed in this paper incorporates a number of immunological principles, including the multilevel defence and the cooperation between cells in the adaptive immune system. It is proposed that this approach could be used to provide a high level of intrusion detection, while minimising the level of false negative detections.</p>
<p><a href="papers/dp2005-07.pdf">Download</a> (PDF, 264 KB)</p>
<hr>
<h3><a name="dp2005-08">2005/08: Bayesian statistical models for predicting software development effort</a></h3>
<h4>C. van Koten</h4>
<p>Constructing an accurate effort prediction model is a challenge in Software Engineering. This paper presents new Bayesian statistical models, in order to predict development effort of software systems in the International Software Benchmarking Standards Group (ISBSG) dataset. The first model is a Bayesian linear regression (BR) model and the second model is a Bayesian multivariate normal distribution (BMVN) model. Both models are calibrated using subsets randomly sampled from the dataset. The models’ predictive accuracy is evaluated using other subsets, which consist of only the cases unknown to the models. The predictive accuracy is measured in terms of the absolute residuals and magnitude of relative error. They are compared with the corresponding linear regression models. The results show that the Bayesian models have predictive accuracy equivalent to the linear regression models, in general. However, the advantage of the Bayesian statistical models is that they do not require a calibration subset as large as the regression counterpart. In the case of the ISBSG dataset it is confirmed that the predictive accuracy of the Bayesian statistical models, in particular the BMVN model is significantly better than the linear regression model, when the calibration subset consists of only five or smaller number of software systems. This finding justifies the use of Bayesian statistical models in software effort prediction, in particular, when the system of interest has only a very small amount of historical data.</p>
<p><strong>Keywords: </strong>Effort prediction,
Bayesian statistics,
Regression,
Software metrics</p>
<p><a href="papers/dp2005-08.pdf">Download</a> (PDF, 287 KB)</p>
<hr>
<h3><a name="dp2005-09">2005/09: Bayesian statistical effort prediction models for data-centred 4GL software development</a></h3>
<h4>C. van Koten and A. Gray</h4>
<p>Constructing an accurate effort prediction model is a challenge in Software Engineering. This paper presents three Bayesian statistical software effort prediction models for database-oriented software systems, which are developed using a specific 4GL tool suite. The models consist of specification-based software size metrics and development team’s productivity metric. The models are constructed based on the sub jective knowledge of human expert and calibrated using empirical data collected from 17 software systems developed in the target environment. The models’ predictive accuracy is evaluated using subsets of the same data, which were not used for the models’ calibration. The results show that the models have achieved very good predictive accuracy in terms of MMRE and pred measures. Hence it is confirmed that the Bayesian statistical models can predict effort successfully in the target environment. In comparison with commonly used multiple linear regression models, the Bayesian statistical models’ predictive accuracy is equivalent in general. However, when the number of software systems used for the models’ calibration becomes smaller than five, the predictive accuracy of the best Bayesian statistical models are significantly better than the multiple linear regression model. This result suggests that the Bayesian statistical models would be a better choice when software organizations/practitioners do not posses sufficient empirical data for the models’ calibration. The authors expect those findings encourage more researchers to investigate the use of Bayesian statistical models for predicting software effort.</p>
<p><strong>Keywords: </strong>Effort prediction,
4GL,
Bayesian statistics,
Regression,
Software metrics</p>
<p><a href="papers/dp2005-09.pdf">Download</a> (PDF, 331 KB)</p>
