Browsing School of Information Technology by Author "Madden, Michael G."
Now showing items 120 of 20

Analysis of the Effects of Unexpected Outliers in the Classification of Spectroscopy Data
Glavin, Frank G.; Madden, Michael G. (2009)Multiclass classification algorithms are very widely used, but we argue that they are not always ideal from a theoretical perspective, because they assume all classes are characterised by the data, whereas in many ... 
Arrhythmia Identification from ECG Signals with a Neural Network Classifier Based on a Bayesian Framework
Lyons, Gerard J.; Chambers, Des; Schukat, Michael; Madden, Michael G.; Gao, Dayong (2004)This paper presents an ANNbased diagnostic system for arrhythmia using Neural Network Classifier with Bayesian framework by time series biosignals. The Neural Network Classifier is built by the use of logistic regression ... 
Bayesian ANN Classifier for ECG Arrhythmia Diagnostic System: A Comparison Study
Lyons, Gerard J.; Chambers, Des; Madden, Michael G.; Gao, Dayong (2005)Abstract¿This paper outlines a system for detection of cardiac arrhythmias within ECG signals, based on a Bayesian Artificial Neural Network (ANN) classifier. The Bayesian (or Probabilistic) ANN Classifier is built by the ... 
Classification of a Target Analyte in Solid Mixtures using Principal Component Analysis, Support Vector Machines and Raman Spectroscopy
Madden, Michael G.; Leger, Marc N.; Ryder, Alan G.; Howley, Tom; O Connell, MarieLouise (2005)The quantitative analysis of illicit materials using Raman spectroscopy is of widespread interest for law enforcement and healthcare applications. One of the difficulties faced when analysing illicit mixtures is the ... 
A DataDriven Exploration of Factors Affecting Student Performance in a ThirdLevel Institution
Madden, Michael G.; Lyons, William; Kavanagh, Ita (2008)This paper describes an application of data mining techniques to the analysis of student academic records, collected at Limerick Institute of Technology, with the goal of acquiring clearer, evidencebased ... 
The Effect of Principal Component Analysis on Machine Learning Accuracy with High Dimensional Spectral Data
Ryder, Alan G.; O Connell, MarieLouise; Madden, Michael G.; Howley, Tom (2005)The classi¿cation of high dimensional data, such as images, geneexpression data and spectral data, poses an interesting challenge to machine learning, as the presence of high numbers of redundant or highly correlated ... 
The Evolution of a KernelBased Distance Metric for kNN Regression
Madden, Michael G.; Howley, Tom (2007)kNearest Neighbours (kNN) is a well understood and widelyused approach to classification and regression problems. In many cases, such applications of kNN employ the standard Euclidean distance metric for the determination ... 
An Evolutionary Approach to Automatic Kernel Construction
Madden, Michael G.; Howley, Tom (2006)Abstract. Kernelbased learning presents a unified approach to machine learning problems such as classification and regression. The selection of a kernel and associated parameters is a critical step in the application of ... 
The Genetic Evolution of Kernels for Support Vector Machine Classifiers
Madden, Michael G.; Howley, Tom (2004)Abstract. The Support Vector Machine (SVM) has emerged in recent years as a popular approach to the classi¿cation of data. One problem that faces the user of an SVM is how to choose a kernel and the speci¿c parameters for ... 
A Machine Learning Application for Classification of Chemical Spectra
Madden, Michael G.; Howley, Tom (2008)This paper presents a software package that allows chemists to analyze spectroscopy data using innovative machine learning (ML) techniques. The package, designed for use in conjunction with labbased spectroscopic ... 
MultiClass and SingleClass Classification Approaches to Vehicle Model Recognition from Images
Madden, Michael G.; Munroe, Daniel T. (2005)This paper investigates the use of machine learning classification techniques applied to the task of recognising the make and model of vehicles. Although a number of vehicle classification systems already exist, most of ... 
Neural Network Approach to Predicting Stock Exchange Movements using External Factors
Madden, Michael G.; O'Connor, Niall (2005)The aim of this study is to evaluate the effectiveness of using external indicators, such as commodity prices and currency exchange rates, in predicting movements in the Dow Jones Industrial Average index. The performance ... 
On the Classification Performance of TAN and General Bayesian Networks
Madden, Michael G. (2008)Over a decade ago, Friedman et al. introduced the Tree Augmented Naïve Bayes (TAN) classifier, with experiments indicating that it significantly outperformed Naïve Bayes (NB) in terms of classification ... 
On the Classification Performance of TAN and General Bayesian Networks
Madden, Michael G. (Elsevier, 2009)Over a decade ago, Friedman et al. introduced the Tree Augmented Naïve Bayes (TAN) classifier, with experiments indicating that it significantly outperformed Naïve Bayes (NB) in terms of classification accuracy, ... 
OneClass Support Vector Machine Calibration Using Particle Swarm Optimisation
Liu, Yang; Madden, Michael G. (2007)Abstract. Populationbased search methods such as evolutionary algorithms, shuffled complex algorithms, simulated annealing and ant colony search are increasingly used as automatic calibration methods ... 
Probabilistic Detection of Short Events, with Application to Critical Care Monitoring
Manley, Geoffrey; Cohen, Mitchell; Staudenmayer, Kristan; Morabito, Diane; Madden, Michael G.; Russell, Stuart; Aleks, Norm (2008)We describe an application of probabilistic modeling and inference technology to the problem of analyzing sensor data in the setting of an intensive care unit (ICU). In particular, we consider the arterialline blood ... 
Probabilistic Modeling of Sensor Artifacts in Critical Care
Manley, Geoffrey; Staudenmayer, Kristan; Cohen, Mitchell; Madden, Michael G.; Morabito, Diane; Aleks, Norm; Russell, Stuart (2008)We describe an application of probabilistic modeling and inference technology to the problem of analyzing sensor data in the setting of an intensive care unit (ICU). In particular, we consider the arterialline blood ... 
Qualitative and Quantitative Analysis of Chlorinated Solvents using Raman Spectroscopy and Machine Learning
Madden, Michael G.; Hennessey, Kenneth; Leger, Marc N.; Ryder, Alan G.; Conroy, Jennifer (2005)The unambiguous identification and quantification of hazardous materials is of increasing importance in many sectors such as waste disposal, pharmaceutical manufacturing, and environmental protection. One particular ... 
Revealing the Origin and Nature of Drug Resistance of Dynamic Tumour Systems
SantiagoMozos, Ricardo; Khan, Imtiaz A.; Madden, Michael G. (2010)In this paper, the authors identify the strategies that resistant subpopulations of cancer cells undertake to overcome the effect of the anticancer drug Topotecan. For the analyses of cell lineage data encoded from timelapse ... 
A Survey of Recent Trends in One Class Classi cation
Khan, Shehroz S.; Madden, Michael G. (Springer Verlag  LNAI, 200908)The One Class Classification (OCC) problem is di fferent from the conventional binary/multiclass classi fication problem in the sense that in OCC, the negative class is either not present or not properly sampled. The ...