Institutions
|
About Us
|
Help
|
Gaeilge
0
1000
Home
Browse
Advanced Search
Search History
Marked List
Statistics
A
A
A
Author(s)
Institution
Publication types
Funder
Year
Limited By:
Subject = Neural Networks;
22 items found
Sort by
Title
Author
Item type
Date
Institution
Peer review status
Language
Order
Ascending
Descending
25
50
100
per page
Bibtex
CSV
EndNote
RefWorks
RIS
XML
Displaying Results 1 - 22 of 22 on page 1 of 1
Marked
Mark
A Semi-Automatic Indexing System for Cell Images
(2008)
AHMAD, KHURSHID; Zheng, Choaxin; KELLEHER, DERMOT P
A Semi-Automatic Indexing System for Cell Images
(2008)
AHMAD, KHURSHID; Zheng, Choaxin; KELLEHER, DERMOT P
Abstract:
A method is described that can be used for annotating and indexing an arbitrary set of images with texts collateral to the images. The collateral texts comprise digitised texts, e.g. journal papers and newspapers in which the images appear, and digitised speech, e.g. a commentary on the contents of the images. The annotation dasiavectorpsila comprises image features and keywords in the collateral texts; our method can be used to generate both the image features and keywords automatically. Terminology extraction techniques are incorporated into the system to form a domain specific lexicon, which can then be used or help to annotate the images. Our method can be used as the basis of the autonomous learning of associations between images and their collateral descriptions, for example using Kohonen feature maps. We focus on images that show the migration and the division of cells within live systems. We show how the annotations can be collected by using the state-of-the-art speech recog...
http://hdl.handle.net/2262/38883
Marked
Mark
Ab initio and homology based prediction of protein domains by recursive neural networks
(2009)
Walsh, Ian; Martin, Alberto J. M.; Mooney, Catherine; Rubagotti, Enrico; Vullo, Alessan...
Ab initio and homology based prediction of protein domains by recursive neural networks
(2009)
Walsh, Ian; Martin, Alberto J. M.; Mooney, Catherine; Rubagotti, Enrico; Vullo, Alessandro; Pollastri, Gianluca
Abstract:
Background: Proteins, especially larger ones, are often composed of individual evolutionary units, domains, which have their own function and structural fold. Predicting domains is an important intermediate step in protein analyses, including the prediction of protein structures. Results: We describe novel systems for the prediction of protein domain boundaries powered by Recursive Neural Networks. The systems rely on a combination of primary sequence and evolutionary information, predictions of structural features such as secondary structure, solvent accessibility and residue contact maps, and structural templates, both annotated for domains (from the SCOP dataset) and unannotated (from the PDB). We gauge the contribution of contact maps, and PDB and SCOP templates independently and for different ranges of template quality. We find that accurately predicted contact maps are informative for the prediction of domain boundaries, while the same is not true for contact maps predicted ab...
http://hdl.handle.net/10197/3396
Marked
Mark
Ab initio and template-based prediction of multi-class distance maps by two-dimensional recursive neural networks
(2009)
Walsh, Ian; Baù, Davide; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro; P...
Ab initio and template-based prediction of multi-class distance maps by two-dimensional recursive neural networks
(2009)
Walsh, Ian; Baù, Davide; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro; Pollastri, Gianluca
Abstract:
Background: Prediction of protein structures from their sequences is still one of the open grand challenges of computational biology. Some approaches to protein structure prediction, especially ab initio ones, rely to some extent on the prediction of residue contact maps. Residue contact map predictions have been assessed at the CASP competition for several years now. Although it has been shown that exact contact maps generally yield correct three-dimensional structures, this is true only at a relatively low resolution (3–4 Å from the native structure). Another known weakness of contact maps is that they are generally predicted ab initio, that is not exploiting information about potential homologues of known structure. Results: We introduce a new class of distance restraints for protein structures: multi-class distance maps. We show that C trace reconstructions based on 4-class native maps are significantly better than those from residue contact maps. We then build two predictors o...
http://hdl.handle.net/10197/3409
Marked
Mark
Accurate prediction of protein secondary structure and solvent accessibility by consensus combiners of sequence and structure information
(2007)
Pollastri, Gianluca; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro
Accurate prediction of protein secondary structure and solvent accessibility by consensus combiners of sequence and structure information
(2007)
Pollastri, Gianluca; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro
Abstract:
Background : Structural properties of proteins such as secondary structure and solvent accessibility contribute to three-dimensional structure prediction, not only in the ab initio case but also when homology information to known structures is available. Structural properties are also routinely used in protein analysis even when homology is available, largely because homology modelling is lower throughput than, say, secondary structure prediction. Nonetheless, predictors of secondary structure and solvent accessibility are virtually always ab initio. Results: Here we develop high-throughput machine learning systems for the prediction of protein secondary structure and solvent accessibility that exploit homology to proteins of known structure, where available, in the form of simple structural frequency profiles extracted from sets of PDB templates. We compare these systems to their state-of-the-art ab initio counterparts, and with a number of baselines in which secondary structures a...
http://hdl.handle.net/10197/3394
Marked
Mark
An Oscillatory Neural Network Scheme for Temporal Encoding and Stimulus Recognition
(1999)
Ward, T.
An Oscillatory Neural Network Scheme for Temporal Encoding and Stimulus Recognition
(1999)
Ward, T.
Abstract:
A novel computational neuro-architecture based on the phase resetting properties of physiologically based neural oscillators is proposed. Analog input variables are encOded in the patterns of the firing times with individual recognition units operating as radial basis-functions.
http://eprints.maynoothuniversity.ie/1364/
Marked
Mark
Computational models of cognition
(2005)
Doris, Thomas Francis
Computational models of cognition
(2005)
Doris, Thomas Francis
Abstract:
Existing connectionist computational models of neural networks idealise the biological process in the neuron to a discrete summation, and fail to provide an efficient substrate for computation involving the spectral data that is the input to the biological perceptual process. This work presents a computational model of neural function that introduces a continuous analogue process and explores the computational uses of sub-threshold oscillations of the membrane potential. The goal of tins work is to present an in itial examination of the advantages to the practitioner that are afforded by a new computational model of the neuron that includes sub-threshold oscillations as a component on an equal footing with axonal impulses themselves. The relevant. evidence that these effects are important in a biological neural network is presented. The new resonate-and-fire model is presented and mathematically defined, and shown to be a superset of the ubiquitous integrate-and-fire model. The beha...
http://doras.dcu.ie/17423/
Marked
Mark
Critical Comparison of the Classification Ability of Deep Convolutional Neural Network Frameworks with Support Vector Machine Techniques in the Image Classification Process
(2017)
Kelly, Robert
Critical Comparison of the Classification Ability of Deep Convolutional Neural Network Frameworks with Support Vector Machine Techniques in the Image Classification Process
(2017)
Kelly, Robert
Abstract:
<p>Recently, a number of new image classification models have been developed to diversify the number of options available to prospective machine learning classifiers, such as Deep Learning. This is particularly important in the field of medical image classification as a misdiagnosis could have a severe impact on the patient. However, an assessment on the level to which a deep learning based Convolutional Neural Network can outperform a Support Vector Machine has not been discussed. In this project, the use of CNN and SVM classifiers is used on a dataset of approx. 55,000 images. This dataset was used to assess the classification potential of each methodology, in terms of training, implementation, and the ability to engineer parameters and features for successful classifications on a very large dataset. The use of CNN approaches is further broken down into the use of different frameworks, in this case Theano and Torch implementations. These are then compared to an SVM classifie...
http://arrow.dit.ie/scschcomdis/96
Marked
Mark
Distill : a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins
(2006)
Baù, Davide; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro; Walsh, Ian; P...
Distill : a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins
(2006)
Baù, Davide; Martin, Alberto J. M.; Mooney, Catherine; Vullo, Alessandro; Walsh, Ian; Pollastri, Gianluca
Abstract:
We describe Distill, a suite of servers for the prediction of protein structural features: secondary structure; relative solvent accessibility; contact density; backbone structural motifs; residue contact maps at 6, 8 and 12 Angstrom; coarse protein topology. The servers are based on large-scale ensembles of recursive neural networks and trained on large, up-to-date, non- redundant subsets of the Protein Data Bank. Together with structural feature predictions, Distill includes a server for prediction of Cα traces for short proteins (up to 200 amino acids). The servers are state-of-the-art, with secondary structure predicted correctly for nearly 80% of residues (currently the top performance on EVA), 2-class solvent accessibility nearly 80% correct, and contact maps exceeding 50% precision on the top non-diagonal contacts. A preliminary implementation of the predictor of protein Cα traces featured among the top 20 Novel Fold predictors at the last CASP6 experiment as group Distill (I...
http://hdl.handle.net/10197/3444
Marked
Mark
Emotion Tracking for Remote Conferencing Applications using Neural Networks.
(2014)
Paul Smith and Sam Redfern; Smith, Paul; Redfern, Sam
Emotion Tracking for Remote Conferencing Applications using Neural Networks.
(2014)
Paul Smith and Sam Redfern; Smith, Paul; Redfern, Sam
Abstract:
Conference paper
In face-to-face work, discussion and negotiation relies strongly on non-verbal feedback, which provides important clues to negotiation states such as agreement/disagreement and understanding/confusion, as well as indicating the emotional states and reactions of those around us. With the continued rise of virtual teams, collaborative work increasingly requires tools to manage the reality of distributed and remote work, which is often hampered by a lack of social cohesion and such phenomena as participants multi-tasking rather than paying full attention. This paper discu sses the use of a neural network-based emotion recognition system and describes its application to the monitoring of presence and emotional states of participants in virtual meetings. Experimental analysis shows our Emotion Tracking Agent (ETA) to have marginally better accuracy at recognising universal emotions than human subjects presented with the same data.
http://hdl.handle.net/10379/4084
Marked
Mark
Robustness and prediction accuracy of machine learning for objective visual quality assessment
(2014)
HINES, ANDREW
Robustness and prediction accuracy of machine learning for objective visual quality assessment
(2014)
HINES, ANDREW
Abstract:
Machine Learning (ML) is a powerful tool to support the development of objective visual quality assessment metrics, serving as a substitute model for the perceptual mechanisms acting in visual quality appreciation. Nevertheless, the reli- ability of ML-based techniques within objective quality as- sessment metrics is often questioned. In this study, the ro- bustness of ML in supporting objective quality assessment is investigated, specifically when the feature set adopted for prediction is suboptimal. A Principal Component Regres- sion based algorithm and a Feed Forward Neural Network are compared when pooling the Structural Similarity Index (SSIM) features perturbed with noise. The neural network adapts better with noise and intrinsically favours features ac- cording to their salient content.
http://hdl.handle.net/2262/72315
Marked
Mark
Experimental Assessment of an Emotion Tracking Software Agent (ETA) for Assisting Communicative Interactions of Multitasking Users in Groupware
(2014)
Smith, Paul; Redfern, Sam
Experimental Assessment of an Emotion Tracking Software Agent (ETA) for Assisting Communicative Interactions of Multitasking Users in Groupware
(2014)
Smith, Paul; Redfern, Sam
Abstract:
Conference paper
Interactions such as discussion and negotiation in face-to-face work contexts strongly rely on non-verbal feedback. Such feedback provides indications of important negotiation states such as agreement or disagreement and understanding or confusion. The increasing popularity of groupware and its use by virtual teams for collaborative remote work necessitates the development of appropriate tools to manage the reality of distributed and remote work. Such remote collaboration is often hampered by a lack of social cohesion and such phenomena as participant multi-tasking. This paper outlines the experimental assessment of a proof of concept AI based software agent (Emotion Tracking Agent or ETA) for the real-time tracking of groupware user¿s facial expressions of emotion during virtual meetings. The software agent is designed as a novel approach to the removal of negative or unwanted effects of user multitasking and attention distracting behaviours in virtual collabo...
http://hdl.handle.net/10379/4081
Marked
Mark
Identification and control of marine vehicles using artificial intelligence techniques
(2005)
Van de Ven, Pepijn
Identification and control of marine vehicles using artificial intelligence techniques
(2005)
Van de Ven, Pepijn
Abstract:
In this thesis a novel approach to the identification of marine craft dynamics using neural networks is described. From a literature review it emerged that augmented controllers, in which a conventional controller is augmenter with neural network, which accounts for unmodelled phenomena and/or unmodelled operation regions, are most likely to be used for future neural controller architectures. Such controllers are appealing, as neural networks can be used to identify the unknown phenomena with a high accuracy. However, at th ecurrent time, neural networks are predominantlz used to identify unknown phenomena in a lumped way. As a result, it is difficult, or even impossible, to use these neural networks in a conventional controller. A novel approach, involving the use of several neural networks for the identification of individual model parameters, is presented. The new approach is tested, first in simulations and consecutively in an experiment, and found to offer increased accuracy co...
http://hdl.handle.net/10344/5170
Marked
Mark
Idiom Token Classification using Sentential Distributed Semantics
(2016)
Salton, Giancarlo; Ross, Robert J.; Kelleher, John
Idiom Token Classification using Sentential Distributed Semantics
(2016)
Salton, Giancarlo; Ross, Robert J.; Kelleher, John
Abstract:
<p>Idiom token classification is the task of deciding for a set of potentially idiomatic phrases whether each occurrence of a phrase is a literal or idiomatic usage of the phrase. In this work we explore the use of Skip-Thought Vectors to create distributed representations that encode features that are predictive with respect to idiom token classification. We show that classifiers using these representations have competitive performance compared with the state of the art in idiom token classification. Importantly, however, our models use only the sentence containing the tar- get phrase as input and are thus less dependent on a potentially inaccurate or in- complete model of discourse context. We further demonstrate the feasibility of using these representations to train a competitive general idiom token classifier.</p>
http://arrow.dit.ie/scschcomcon/203
Marked
Mark
Neural modelling, control and optimisation of an industrial grinding process
(2005)
Govindhasamy, James J.; McLoone, Sean F.; Irwin, George W.; French, John J.; Doyle, Ric...
Neural modelling, control and optimisation of an industrial grinding process
(2005)
Govindhasamy, James J.; McLoone, Sean F.; Irwin, George W.; French, John J.; Doyle, Richard P.
Abstract:
This paper describes the development of neural model-based control strategies for the optimisation of an industrial aluminium substrate disk grinding process. The grindstone removal rate varies considerably over a stone life and is a highly nonlinear function of process variables. Using historical grindstone performance data, a NARX-based neural network model is developed. This model is then used to implement a direct inverse controller and an internal model controller based on the process settings and previous removal rates. Preliminary plant investigations show that thickness defects can be reduced by 50% or more, compared to other schemes employed.
http://eprints.maynoothuniversity.ie/684/
Marked
Mark
Output-based objective measure for non-intrusive speech quality evaluation
(2004)
Mahdi, Abdulhussain E; Picovici, Dorel
Output-based objective measure for non-intrusive speech quality evaluation
(2004)
Mahdi, Abdulhussain E; Picovici, Dorel
Abstract:
This paper describes a newly developed output-based method for non-intrusive evaluation of speech quality of voice communication systems, and evaluates its performance. The method, which uses only the output of the system, is based on measuring perceptually motivated objective auditory distances between the voiced parts of the speech signal whose quality to be evaluated to appropriately matching reference vectors extracted from a pre-formulated codebook. The codebook is formed by optimally clustering large number of perceptually-based parametric vectors extracted from a database of clean speech signals. The auditory distance measures are then mapped into equivalent subjective score, represented by the Mean Opinion scores (MOS), using regression. The required clustering and matching processes are achieved by using an efficient neural network based data mining technique known as the Self-Organizing Map. Perceptual, speaker-independent parametric representation of the speech is achieve...
http://hdl.handle.net/10344/5114
Marked
Mark
Power system parameters forecasting using Hilbert-Huang transform and machine learning
(2014)
Kurbatsky, Victor G.; Spiryaev, Vadim A.; Tomin, Nikita V.; Leahy, Paul G.; Sidorov, De...
Power system parameters forecasting using Hilbert-Huang transform and machine learning
(2014)
Kurbatsky, Victor G.; Spiryaev, Vadim A.; Tomin, Nikita V.; Leahy, Paul G.; Sidorov, Denis N.; Zhukov, Alexei V.
Abstract:
A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine ...
http://hdl.handle.net/10468/1791
Marked
Mark
Prediction of pile settlement using artificial neural networks based on standard penetration test data
(2017)
Nejad, F. Pooya; Jaksa, Mark B.; Kakhi, M.; McCabe, Bryan A.
Prediction of pile settlement using artificial neural networks based on standard penetration test data
(2017)
Nejad, F. Pooya; Jaksa, Mark B.; Kakhi, M.; McCabe, Bryan A.
Abstract:
In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on standard penetration test (SPT) data. Approximately 1000 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions. (C) 2009 Elsevier Ltd. All rights reserved.
http://hdl.handle.net/10379/6341
Marked
Mark
Profiling side-channel attacks on cryptographic algorithms
(2014)
Hanley, Neil John
Profiling side-channel attacks on cryptographic algorithms
(2014)
Hanley, Neil John
Abstract:
Traditionally, attacks on cryptographic algorithms looked for mathematical weaknesses in the underlying structure of a cipher. Side-channel attacks, however, look to extract secret key information based on the leakage from the device on which the cipher is implemented, be it smart-card, microprocessor, dedicated hardware or personal computer. Attacks based on the power consumption, electromagnetic emanations and execution time have all been practically demonstrated on a range of devices to reveal partial secret-key information from which the full key can be reconstructed. The focus of this thesis is power analysis, more specifically a class of attacks known as profiling attacks. These attacks assume a potential attacker has access to, or can control, an identical device to that which is under attack, which allows him to profile the power consumption of operations or data flow during encryption. This assumes a stronger adversary than traditional non-profiling attacks such as differen...
http://hdl.handle.net/10468/1921
Marked
Mark
Protein structural motif prediction in multidimensional φ-ψ space leads to improved secondary structure prediction
(2006)
Mooney, Catherine; Vullo, Alessandro; Pollastri, Gianluca
Protein structural motif prediction in multidimensional φ-ψ space leads to improved secondary structure prediction
(2006)
Mooney, Catherine; Vullo, Alessandro; Pollastri, Gianluca
Abstract:
A significant step towards establishing the structure and function of a protein is the prediction of the local conformation of the polypeptide chain. In this article, we present systems for the prediction of three new alphabets of local structural motifs. The motifs are built by applying multidimensional scaling (MDS) and clustering to pair-wise angular distances for multiple φ-ψ angle values collected from high-resolution protein structures. The predictive systems, based on ensembles of bidirectional recurrent neural network architectures, and trained on a large non-redundant set of protein structures, achieve 72%, 66%, and 60% correct motif prediction on an independent test set for di-peptides (six classes), tri-peptides (eight classes) and tetra-peptides (14 classes), respectively, 28–30% above baseline statistical predictors. We then build a further system, based on ensembles of two-layered bidirectional recurrent neural networks, to map structural motif predictions into a tradi...
http://hdl.handle.net/10197/3393
Marked
Mark
Using Neural Networks to Reduce Entity State Updates in Distributed Interactive Applications
(2006)
McCoy, Aaron; Ward, Tomas; McLoone, Seamus; Delaney, Declan
Using Neural Networks to Reduce Entity State Updates in Distributed Interactive Applications
(2006)
McCoy, Aaron; Ward, Tomas; McLoone, Seamus; Delaney, Declan
Abstract:
Dead reckoning is the most commonly used predictive contract mechanism for the reduction of network traffic in Distributed Interactive Applications (DIAs). However, this technique often ignores available contextual information that may be influential to the state of an entity, sacrificing remote predictive accuracy in favour of low computational complexity. In this paper, we present a novel extension of dead reckoning by employing neuralnetworks to take into account expected future entity behaviour during the transmission of entity state updates (ESUs) for remote entity modeling in DIAs. This proposed method succeeds in reducing network traffic through a decrease in the frequency of ESU transmission required to maintain consistency. Validation is achieved through simulation in a highly interactive DIA, and results indicate significant potential for improved scalability when compared to the use of the IEEE DIS Standard dead reckoning technique. The new method exhibits relatively low ...
http://eprints.maynoothuniversity.ie/1446/
Marked
Mark
Variable interactions in risk factors for dementia
(2016)
O'Donoghue, Jim; Roantree, Mark; McCarren, Andrew
Variable interactions in risk factors for dementia
(2016)
O'Donoghue, Jim; Roantree, Mark; McCarren, Andrew
Abstract:
Current estimates predict 1 in 3 people born today will develop dementia, suggesting a major impact on future population health. As such, research needs to connect specialist clinicians, data scientists and the general public. The In-MINDD project seeks to address this through the provision of a Profiler, a socio-technical information system connecting all three groups. The public interact, providing raw data; data scientists develop and refine prediction algorithms; and clinicians use in-built services to inform decisions. Common across these groups are Risk Factors, used for dementia-free survival prediction. Risk interactions could greatly inform prediction but determining these interactions is a problem underpinned by massive numbers of possible combinations. Our research employs a machine learning approach to automatically select best performing hyperparameters for prediction and learns variable interactions in a non-linear survival-analysis paradigm. Demonstrating effectivenes...
http://doras.dcu.ie/21189/
Displaying Results 1 - 22 of 22 on page 1 of 1
Bibtex
CSV
EndNote
RefWorks
RIS
XML
Institution
Dublin City University (2)
Dublin Institute of Technology (2)
Maynooth University (3)
NUI Galway (3)
Trinity College Dublin (3)
University College Cork (2)
University College Dublin (5)
University of Limerick (2)
Item Type
Conference item (7)
Doctoral thesis (3)
Journal article (11)
Master thesis (taught) (1)
Peer Review Status
Peer-reviewed (19)
Non-peer-reviewed (3)
Year
2017 (2)
2016 (2)
2014 (5)
2009 (2)
2008 (2)
2007 (1)
2006 (3)
2005 (3)
2004 (1)
1999 (1)
built by Enovation Solutions