Machine learning approach to an otoneurological classification problem

Henry Joutsijoki; Kirsi Varpa; Kati Iltanen; Martti Juhola

doi:10.1109/EMBC.2013.6609745

Machine learning approach to an otoneurological classification problem

Annu Int Conf IEEE Eng Med Biol Soc. 2013:2013:1294-7. doi: 10.1109/EMBC.2013.6609745.

Authors

Henry Joutsijoki, Kirsi Varpa, Kati Iltanen, Martti Juhola

PMID: 24109932
DOI: 10.1109/EMBC.2013.6609745

Abstract

In this paper we applied altogether 13 classification methods to otoneurological disease classification. The main point was to use Half-Against-Half (HAH) architecture in classification. HAH structure was used with Support Vector Machines (SVMs), k-Nearest Neighbour (k-NN) method and Naïve Bayes (NB) methods. Furthermore, Multinomial Logistic Regression (MNLR) was tested for the dataset. HAH-SVM with the linear kernel achieved clearly the best accuracy being 76.9% which was a good result with the dataset tested. From the other classification methods HAH-k-NN with cityblock metric, HAH-NB and MNLR methods achieved above 60% accuracy. Around 77% accuracy is a good result compared to previous researches with the same dataset.

MeSH terms

Algorithms
Artificial Intelligence*
Bayes Theorem
Cluster Analysis
Humans
Models, Statistical
Nervous System Diseases / diagnosis*
Regression Analysis
Reproducibility of Results
Support Vector Machine
Vertigo / diagnosis*