Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Analysis (1)
- Articulators (1)
- Classification Algorithms (1)
- Classification (1)
- Data Mining (1)
-
- Deep Learning (1)
- GIScience (1)
- GMDH-based classifiers (1)
- Gender bias (1)
- Health Social Networks (1)
- Human-computer-interaction (1)
- ISL (1)
- Image Processing (1)
- Kay Supercomputer (1)
- Kinect (1)
- Landscape and resource values; blanket peat; wind power; Delphi survey; landowners (1)
- Machine Learning (1)
- Motion analysis (1)
- Motion capture (1)
- NMF (1)
- Natural Language Processing (1)
- Non-Manual (1)
- Safety hazard near miss reporting (1)
- Sign Language (1)
- Training data (1)
- Verbs (1)
- Video games (1)
Articles 1 - 7 of 7
Full-Text Articles in Physical Sciences and Mathematics
Exploring The Impact Of Gender Bias Mitigation Approaches On A Downstream Classification Task, Nasim Sobhani, Sarah Jane Delany
Exploring The Impact Of Gender Bias Mitigation Approaches On A Downstream Classification Task, Nasim Sobhani, Sarah Jane Delany
Conference Papers
Natural language models and systems have been shown to reflect gender bias existing in training data. This bias can impact on the downstream task that machine learning models, built on this training data, are to accomplish. A variety of techniques have been proposed to mitigate gender bias in training data. In this paper we compare different gender bias mitigation approaches on a classification task. We consider mitigation techniques that manipulate the training data itself, including data scrubbing, gender swapping and counterfactual data augmentation approaches. We also look at using de-biased word embeddings in the representation of the training data. We …
Machine Learning With Kay, Lasith Niroshan, James Carswell
Machine Learning With Kay, Lasith Niroshan, James Carswell
Conference Papers
Computational power is very important when training Deep Learning (DL) models with large amounts of data (Wooldridge, 2021). Hence, High-Performance Computing (HPC) can be leveraged to reduce computational cost, and the Irish Centre for High-End Computing (ICHEC) provides significant infrastructure and services for research and development to both academia and industry. A portion of ICHEC's HPC system has been allocated for institutional access, and this paper presents a case study of how to use Kay (Ireland's national supercomputer) in the remote sensing domain. Specifically, this study uses clusters of Kay Graphics Processing Units (GPUs) for training DL models to extract …
Non-Manual Articulators In Irish Sign Language Verbs: An Analysis With Data Mining Association Rules, Robert G. Smith, Markus Hofmann
Non-Manual Articulators In Irish Sign Language Verbs: An Analysis With Data Mining Association Rules, Robert G. Smith, Markus Hofmann
Conference Papers
The Signs of Ireland (SOI) corpus (Leeson et al., 2006) deploys a complex multi-tiered temporal data structure. The process of manually analyzing such data is laborious, cannot eliminate bias and often, important patterns can go completely unnoticed. In addition to this, as a result of the complex nature of grammatical structures contained in the corpus, identifying complex linguistic associations or patterns across tiers is simply too intricate a task for a human to carry out in an acceptable timeframe. This work explores the application of data mining techniques on a set of multi-tiered temporal data from the SOI corpus. Building …
Building Classifiers With Gmdh For Health Social Networks (Bd Askapatient), John Cardiff, Liliya Akhtyamova, Mikhail Alexandrov
Building Classifiers With Gmdh For Health Social Networks (Bd Askapatient), John Cardiff, Liliya Akhtyamova, Mikhail Alexandrov
Conference Papers
Health social media offer useful data for patients and doctors concerning both various medicines and treatments. Usually, these data are accompanied by their assessments in 5- star scale. But such a detail classification has small usefulness because patients and doctors, first of all, want to know about negative cases and to study in detail the extreme ones. In the paper we build classifiers of texts just for these cases using combined classes as negative, all others and worst, satisfactory, best. For this, we study possibilities of different GMDH-based algorithms and compare them with the results of other methods. The selection …
A Pilot Study Of Comparison Gesture Analysis In Motion Driven Video Games, Fabrizio Valerio Covone, Brian Vaughan, Charlie Cullen
A Pilot Study Of Comparison Gesture Analysis In Motion Driven Video Games, Fabrizio Valerio Covone, Brian Vaughan, Charlie Cullen
Conference Papers
This study investigates whether there are significant differences in the gestures made by gamers and non-gamers whilst playing commercial games that employ gesture inputs. Specifically, the study focuses on testing a prototype of multimodal capture tool that we used to obtain real-time audio, video and skeletal gesture data. Additionally, we developed an experimental design framework for the acquisition of spatio-temporal gesture data and analysed the vector magnitude of a gesture to compare the relative displacement of each participant whilst playing a game.
Landscape Values And Wind Generation In West Mayo, Ireland, Ken Boyle
Landscape Values And Wind Generation In West Mayo, Ireland, Ken Boyle
Conference Papers
The landscape of west Mayo, in North West Ireland, is dominated and shrouded by an extensive area, 3,539Km2, of blanket peat soils. The landscape and its habitats have multiple values associated with them including a source of peat for fuel, agriculture, forestry, conservation, tourism, biomass production, tourism, cultural and archaeological. Historically communities have relied on peat as a source of energy and in the 20th century the state harvested peat on an industrial scale to generate electricity. Biomass production using willow (Salix spp) on cutover blanket peat and extensive planting, on deep peat, of Picea sitchensis and Pinus contorta was …
Safety And/Or Hazard Near Miss Reporting In An International Energy Company, Paul Clancy, Maria Chiara Leva, Victor Hrymak, Michael Sherlock
Safety And/Or Hazard Near Miss Reporting In An International Energy Company, Paul Clancy, Maria Chiara Leva, Victor Hrymak, Michael Sherlock
Conference Papers
This paper presents the preliminary progress of an industry driven programme to improve the data monitoring of safety/hazard near miss reporting from front line staff of a branch of a multinational energy supply company in Ireland. The paper discusses the main factors that emerged as possible causes for underreporting and the course of action selected for addressing them. The initiative, which is only in operation for 4 months has already led to an increase in reporting of “near misses” by a factor of nine. Furthermore, the level and detail of the reports is far greater than had previously being received.