Deakin University
Browse

File(s) under permanent embargo

A hybrid neural classifier for dimensionality reduction and data visualization and its application to fault detection and classification of induction motors

conference contribution
posted on 2011-01-01, 00:00 authored by M Nadjarpoorsiyahkaly, Chee Peng LimChee Peng Lim
In this paper, a hybrid neural classifier combining the auto-encoder neural network and the Lattice Vector Quantization (LVQ) model is described. The auto-encoder network is used for dimensionality reduction by projecting high dimensional data into the 2D space. The LVQ model is used for data visualization by forming and adapting the granularity of a data map. The mapped data are employed to predict the target classes of new data samples. To improve classification accuracy, a majority voting scheme is adopted by the hybrid classifier. To demonstrate the applicability of the hybrid classifier, a series of experiments using simulated and real fault data from induction motors is conducted. The results show that the hybrid classifier is able to outperform the Multi-Layer Perceptron neural network, and to produce very good classification accuracy rates for various fault conditions of induction motors.

History

Event

Bio-Inspired Computing : Theories and Applications. Conference (6th : 2011 : Penang, Malaysia)

Pagination

146 - 150

Publisher

IEEE Computer Society

Location

Penang, Malaysia

Place of publication

Los Alamitos, Calif.

Start date

2011-09-27

End date

2011-09-29

ISBN-13

9781457710926

Language

eng

Publication classification

E1.1 Full written paper - refereed

Title of proceedings

BIC-TA 2011 : Proceedings of the 6th International Conference on Bio-Inspired Computing: Theories and Applications

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC