Transductive Confidence Machine and its application to Medical Data Sets

TL;DR

This paper introduces the Transductive Confidence Machine Nearest Neighbours algorithm, evaluates its performance on medical datasets with various parameters, and compares it to SVMs and neural networks.

Contribution

It presents a new transductive confidence machine algorithm for medical data analysis and compares its effectiveness with existing methods like SVMs and neural networks.

Findings

TCMNN performance varies with parameter settings

Different Minkowski metrics and kernels impact results

Neural networks offer a useful comparison

Abstract

The Transductive Confidence Machine Nearest Neighbours (TCMNN) algorithm and a supporting, simple user interface was developed. Different settings of the TCMNN algorithms' parameters were tested on medical data sets, in addition to the use of different Minkowski metrics and polynomial kernels. The effect of increasing the number of nearest neighbours and marking results with significance was also investigated. SVM implementation of the Transductive Confidence Machine was compared with Nearest Neighbours implementation. The application of neural networks was investigated as a useful comparison to the transductive algorithms.