Effects of data complexity on the intelligent diagnostic reasoning

Author

Marzi, Arash ; Marzi, Hosein

Author_Institution

Sch. of Electr. Eng. & Comput. Sci., Univ. of Ottawa, Ottawa, ON, Canada

fYear

2015

fDate

May 31 2015-June 4 2015

Firstpage

1

Lastpage

4

Abstract

The objective was to train several Artificial Neural Networks (ANNs) with different training functions in order to gain an understanding of the effect of dataset complexity on performance. The utilization of varying training functions permitted ANN diversity; and allowing for enhanced diagnostic reasoning in classification. This improvement is achieved by expediting training stage, calibrating classification. The proposed technique is applied to a number of dataset to verify performance improvements. Particular application of the proposed technique is demonstrated by applying methodology for medical diagnostics.

Keywords

inference mechanisms; medical diagnostic computing; neural nets; pattern classification; ANN; artificial neural network; classification; data complexity; dataset complexity; intelligent diagnostic reasoning; medical diagnostics; training function; Artificial intelligence; Artificial neural networks; Breast cancer; Classification algorithms; Diseases; Medical diagnostic imaging; Training; Classification; Diagnostics; Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Humanitarian Technology Conference (IHTC2015), 2015 IEEE Canada International

Conference_Location

Ottawa, ON

Print_ISBN

978-1-4799-8961-4

Type

conf

DOI

10.1109/IHTC.2015.7238069

Filename

7238069