Physical Sciences and Mathematics Commons^™

A Comparison Of Evidence Fusion Rules For Situation Recognition In Sensor-Based Environments, Susan Mckeever, Juan Ye

Conference papers

Dempster-Shafer (DS) theory, and its associated Dempster rule of combination, has been widely used to determine belief based on uncertain evi-dence sources. Variations to the original Dempster rule of combination have appeared in the literature to support particular scenarios where unreliable results may result from the use of original DS theory. While theoretical explanations of the rule variations are explained, there is a lack of empirical comparisons of the DS theory and its variations against real data sets. In this work, we examine several variations to DS theory. Using two real-world sensor data sets, we com-pare the performance of DS …

Computing The Grounded Semantics In All The Subgraphs Of An Argumentation Framework: An Empirical Evaluation, Pierpaolo Dondio

Articles

Given an argumentation framework – with a finite set of arguments and the attack relation identifying the graph – we study how the grounded labelling of a generic argument a varies in all the subgraphs of . Since this is an intractable problem of above-polynomial complexity, we present two non-naïve algorithms to find the set of all the subgraphs where the grounded semantic assigns to argument a specific label . We report the results of a series of empirical tests over graphs of increasing complexity. The value of researching the above problem is two-fold. First, knowing how an argument behaves …

Concept Drift Datasets, Patrick Lindstrom

Doctoral

This zip file contains the datasets used in the PhD thesis:

Lindstrom, P., 2013. Handling Concept Drift in the Context of Expensive Labels. Technological University Dublin. For more information about the datasets please see the README file and the aforementioned thesis.

Drift Detection Using Uncertainty Distribution Divergence, Patrick Lindstrom, Brian Mac Namee, Sarah Jane Delany

Articles

Data generated from naturally occurring processes tends to be non-stationary. For example, seasonal and gradual changes in climate data and sudden changes in financial data. In machine learning the degradation in classifier performance due to such changes in the data is known as concept drift and there are many approaches to detecting and handling it.

Most approaches to detecting concept drift, however, make the assumption that true classes for test examples will be available at no cost shortly after classification and base the detection of concept drift on measures relying on these labels. The high labelling cost in many domains …

Improving Performance By Re-Rating In The Dynamic Estimation Of Rater Reliability, Alexey Tarasov, Sarah Jane Delany, Brian Macnamee

Conference papers

Nowadays crowdsourcing is widely used in supervised machine learning to facilitate the collection of ratings for unlabelled training sets. In order to get good quality results it is worth rejecting results from noisy/unreliable raters, as soon as they are discovered. Many techniques for filtering unreliable raters rely on the presentation of training instances to the raters identified as most accurate to date. Early in the process, the true rater reliabilities are not known and unreliable raters may be used as a result. This paper explores improving the quality of ratings for train- ing instances by performing re-rating. The re-rating relies …