Realisable Classifiers: Improving Operating Performance on Variable Cost Problems

@inproceedings{Scott1998RealisableCI,
  title={Realisable Classifiers: Improving Operating Performance on Variable Cost Problems},
  author={M. Scott and M. Niranjan and R. Prager},
  booktitle={BMVC},
  year={1998}
}
A novel method is described for obtaining superior classification performance over a variable range of classification costs. [...] Key Result Empirical results are presented for artificial data, and for two real world data sets: an image segmentation task and the diagnosis of abnormal thyroid condition.Expand
Combination of support vector machines using genetic programming
TLDR
This paper describes the combination of support vector machine (SVM) classifiers using Genetic Programming (GP) for gender classification problem and shows that OCC is more informative and robust as compared to their individual SVM classifiers. Expand
Combining Classifiers Using Their Receiver Operating Characteristics and Maximum Likelihood Estimation
TLDR
This work describes a simple strategy to combine results from classifiers that have not been applied to a common data set, and therefore can not undergo this type of joint training. Expand
Parcel: Feature Subset Selection in Variable Cost Domains
TLDR
A design method for feature selection in the presence of varying costs, starting from the Wilcoxon nonparametric statistic for the performance of a classification system, is presented, and a concept called the maximum realisable receiver operating characteristic is introduced and proved. Expand
Boolean Combination of Classifiers in the ROC Space
TLDR
The results of computer simulations conducted on synthetic and real-world host-based intrusion detection data indicate that combining the responses from multiple HMMs with IBC can achieve a significantly higher level of performance than with the AND and OR combinations. Expand
Evolving Receiver Operating Characteristics for Data Fusion
TLDR
Genetic programming can automatically produce a combination of classifiers whose ROC is better than the convex hull of the supplied classifier's ROCs. Expand
Multiobjective genetic programming for maximizing ROC performance
TLDR
This paper proposes multiobjective genetic programming (MOGP) to obtain a group of nondominated classifiers, with which the maximum ROCCH can be achieved, and proposes a memetic approach into GP by defining two local search strategies specifically designed for classification problems. Expand
Improving performance of nearest neighborhood classifier using genetic programming
TLDR
Genetic Programming is used to improve the performance of nearest neighbor classifier by replacing predefined k nearest neighbors with the number of men and women in the first two quartiles in Euclidean space for voting. Expand
Combination and optimization of classifiers in gender classification using genetic programming
TLDR
It is found that using only two features, the OCC has comparable performance to that of original classifier using 20 macro features, and heterogeneous combination of classifiers is more promising than the homogenous combination. Expand
Nonlinear Feature Construction with Evolved Neural Networks for Classification Problems
TLDR
This paper presents a new method for generating a nonlinear function for feature construction using multi-layer perceptrons whose weights are shaped by evolution, and evaluates the suggested neural feature construction on four commonly used data sets and reports an improvement in classification accuracy. Expand
Iterative Boolean combination of classifiers in the ROC space: An application to anomaly detection with HMMs
TLDR
The results of computer simulations indicate that the iterative Boolean combination (IBC) of responses from multiple HMMs can achieve a significantly higher level of performance than the Boolean conjunction and disjunction combinations, especially when training data are limited and imbalanced. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 20 REFERENCES
Parcel: Feature Subset Selection in Variable Cost Domains
TLDR
A design method for feature selection in the presence of varying costs, starting from the Wilcoxon nonparametric statistic for the performance of a classification system, is presented, and a concept called the maximum realisable receiver operating characteristic is introduced and proved. Expand
On the use of Expected Attainable Discrimination for feature selection in large scale medical risk p
TLDR
This report investigates the use of expected attainable discrimination (EAD) as a measure to select discrete valued features in two-class prediction problems and explores the usefulness of EAD for feature selection. Expand
Supervised and Unsupervised Discretization of Continuous Features
TLDR
Binning, an unsupervised discretization method, is compared to entropy-based and purity-based methods, which are supervised algorithms, and it is found that the performance of the Naive-Bayes algorithm significantly improved when features were discretized using an entropy- based method. Expand
Feature Selection: Evaluation, Application, and Small Sample Performance
TLDR
This work studies the problem of choosing an optimal feature set for land use classification based on SAR satellite images using four different texture models and shows that pooling features derived from different texture Models, followed by a feature selection results in a substantial improvement in the classification accuracy. Expand
Book review: Machine Learning, Neural and Statistical Classification Edited by D. Michie, D.J. Spiegelhalter and C.C. Taylor (Ellis Horwood Limited, 1994)
TLDR
This well-edited book provides an up-to-date review of different approaches to classification, compares their performance on a wide range of challenging datasets, and draws conclusions on their applicability to realistic industrial problems. Expand
Design, construction and evaluation of systems to predict risk in obstetrics.
TLDR
It is shown that better prediction performance requires more discriminative clinical information rather than improved modelling techniques, and that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy. Expand
Construction and Assessment of Classification Rules
TLDR
Basic Ideas Introduction Constructing Rules Fisher's LDA and Other Methods Based on Covariance Matrices Recursive Partitioning Methods Nonparametric Smoothing Methods Practical Issues Some Special Problems Some Illustrative Applications. Expand
The quickhull algorithm for convex hulls
TLDR
This article presents a practical convex hull algorithm that combines the two-dimensional Quickhull algorithm with the general-dimension Beneath-Beyond Algorithm, and provides empirical evidence that the algorithm runs faster when the input contains nonextreme points and that it used less memory. Expand
Computational Geometry in C
TLDR
The first edition of this book is recognised as one of the definitive sources on the subject of Computational Geometry and the second edition is a welcome addition to my bookshelf. Expand
Machine Learning, Neural and Statistical Classification
Survey of previous comparisons and theoretical work descriptions of methods dataset descriptions criteria for comparison and methodology (including validation) empirical results machine learning onExpand
...
1
2
...