http://hdl.handle.net/10379/386 2017-10-30T00:00:04Z 2017-10-30T00:00:04Z Heitmann, Benjamin Hayes, Conor http://hdl.handle.net/10379/6560 2017-06-03T01:01:11Z 2010-07-20T00:00:00Z

Enabling case-based reasoning on the web of data Heitmann, Benjamin; Hayes, Conor While Case-based reasoning (CBR) has successfully been deployed on the Web, its data models are typically inconsistent with existing information infrastructure and standards. In this paper, we examine how CBR can operate on the emerging Web of Data, with mutual benefits. The expense of knowledge engineering and curating a case base can be reduced by using Linked Data from the Web of Data. While Linked Data provides experiential data from many different domains, it also contains inconsistencies, missing data and noise which provide challenges for logic-based reasoning. CBR is well suited to provide alternative and robust reasoning approaches. We introduce (i) a lightweight CBR vocabulary which is suited for the open ecosystem of the emerging Web of Data, and provide (ii) a detailed example of a case base using data from multiple sources. We propose that for the first time the Web of Data provides data and a real context for open CBR systems.

2010-07-20T00:00:00Z Felzmann, Heike Murphy, Kathy Casey, Dympna Beyan, Oya http://hdl.handle.net/10379/4982 2016-08-15T13:25:50Z 2015-01-01T00:00:00Z

Robot-assisted care for elderly with dementia: is there a potential for genuine end-user empowerment? Felzmann, Heike; Murphy, Kathy; Casey, Dympna; Beyan, Oya Working paper

2015-01-01T00:00:00Z Hromic, Hugo Hayes, Conor http://hdl.handle.net/10379/4828 2015-10-15T12:59:04Z 2014-09-29T00:00:00Z

Constructing Twitter Datasets using Signals for Event Detection Evaluation Hromic, Hugo; Hayes, Conor Twitter is a very attractive real-time platform for research on event detection. However, despite the great amount of interest, datasets suitable for evaluating such methods are not easily available. The two most important reasons for this are Twitter's strict Terms and Conditions for data distribution and the vast amount of Tweets data generated at every minute. In this paper we show a rst exploration of a signal processing method suitable for generating datasets for event detection evaluation. Our proposal is based on the notion of ADSR (attack-decay-sustain-release) envelopes commonly used in acoustics signals modelling and applied to Twitter dynamics such as hashtags usage. We show preliminary results over real-world data that support this idea and the potential of our method for the event detection task itself. Conference paper (workshop)

2014-09-29T00:00:00Z Karnstedt, Marcel Hayes, Conor http://hdl.handle.net/10379/1122 2015-10-15T11:43:29Z 2009-01-01T00:00:00Z

Towards Cross-Community Effects in Scientific Communities Karnstedt, Marcel; Hayes, Conor Community effects on the behaviour of individuals, the community itself and other communities can be observed in a wide range of applications. This is true in scientific research, where communities of researchers have increasingly to justify their impact and progress to funding agencies. Previous work has tried to explain these phenomena by analysing co-citation graphs with methods from social network analysis and graph mining. More recent approaches have supplemented this with techniques from textual clustering. How- ever, there is still a great potential for increasing the quality and accuracy of this analysis, especially in the context of cross-community effects. In this work, we present existing approaches and discuss their strengths and weaknesses. Based on this, we choose two closely related communities and propose novel ideas to detect and ex- plain cross-community effects with a special focus on their characteristics in a given timeline. The outcome is a roadmap for advanced analysis of cross-community effects, which promises valuable insights for all areas of scientific research.

2009-01-01T00:00:00Z