Classification of skin disease using ensemble-based classifier
by K. Thenmozhi; M. Rajesh Babu
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 28, No. 4, 2018

Abstract: Cancerous skin disease such as melanoma and nevi typically results from environmental factors (such as exposure to sunlight) among other causes. The necessary tools needed for early detection of these diseases are still not a reality in most communities. In this paper, the framework is proposed to deal with the detection and classification of various skin diseases. The two techiques commonly used for reduction of dimensionality are feature extraction and feature selection. In feature extraction, features are extracted from original data using principal component analysis and linear discrimant analysis and then extracted feature is reduced by feature selection technique called Fisher ratio method in which the subset of sufficient features is selected for classification. This technique improves the performance and enhances the speed of classifier. The ensemble-based classifier such as Bayesian, self-organised map and support vector machine are used to classify the various skin diseases from the data set. The proposed technique achieves better accuracy and less execution time than existing approach.

Online publication date: Tue, 06-Nov-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com