A fuzzy clustering algorithm enhancing local model interpretability

In this work, simple modifications on the cost index of particular local-model fuzzy clustering algorithms are proposed in order to improve the readability of the resulting models. The final goal is simultaneously providing local linear models (reasonably close to the plant’s Jacobian) and clustering in the input space so that desirable characteristics (regarding final model accuracy, and convexity and smoothness of the cluster membership functions) are improved with respect to other proposals in literature. Some examples illustrate the proposed approach.     

An Information Security Strategy for Networkable Devices

Networkable Windows-based operating system devices present information security challenges to both vendors and users of such devices. This article highlights some of those threats and offers measures to improve the link between a firm's business strategy, its operational activities, and its information security strategy.     

Ab<Emphasis Type="Italic"> initio</Emphasis> investigation of boron diffusion paths in germanium

Boron is observed to diffuse very slowly in germanium, as opposed to its behaviour in silicon where it exhibits Transient Enhanced Diffusion effects in implanted samples. As a result of this slow diffusion, boron is a very stable dopant, allowing devices to be created with very well-defined doping regions. To understand this superior performance, calculations were performed on a variety of boron diffusion paths, within vacancy and interstitial mediated methods. It was found that the vacancy mediated diffusion which is associated with the fast diffusion of many other species in germanium exhibits a total barrier of 5.8 eV. Interstitial-mediated diffusion had a total barrier for migration of 3.4 eV in the neutral and singly negative charge states, 3.2 eV for the positive charge state, but a formation barrier of 4.1 eV. Thus the barrier for interstitial-mediated diffusion is dominated by the formation energy of the self-interstitial.     

Perceptual Temporal Quality Metric for Compressed Video

This paper presents a metric to quantify frame loss according to the impact on perceived temporal quality. This metric particularly aims at measuring the temporal quality degradation caused by both regular and irregular frame loss. Experimental results with subjective viewing demonstrate high performance on prediction of perceptual temporal quality.     

Dialogical Argument as an Interface to Complex Debates

The Magtalo prototype environment harnesses dialogue protocols to support flexible, intuitive interaction with data in complex, contentious domains and provides mechanisms for eliciting structured knowledge. Magtalo represents the first example of an implemented online system that uses a closely specified argument-based dialogue protocol combined with a rich language for representing monologic argument to provide a tool for intuitive user exploration of a disagreement space. This approach also enables the expansion of argument resources through knowledge elicitation, which is structured by the argument dialogue protocol. The continuing aim of our research is to use advances in argumentation theory to push the practice of argumentation technology in providing tools and interfaces that have wide appeal.     

Mining for trigger events with survival analysis

This paper discusses a new application of data mining, quantifying the importance of responding to trigger events with reactive contacts. Trigger events happen during a customer’s lifecycle and indicate some change in the relationship with the company. If detected early, the company can respond to the problem and retain the customer; otherwise the customer may switch to another company. It is usually easy to identify many potential trigger events. What is needed is a way of prioritizing which events demand interventions. We conceptualize the trigger event problem and show how survival analysis can be used to quantify the importance of addressing various trigger events. The method is illustrated on four real data sets from different industries and countries.