Application Of Dimensionality Reduction On Classification Of Colon Cancer Using Ica And K-Nn Algorithm
Journal Title: Annals. Computer Science Series - Year 2018, Vol 16, Issue 1
Abstract
Several sectors including engineering, health, academics and so on deals with very large number of information and few specimens. This highlight the need of a technique to improve data accuracy in order to enable professionals such as biologists, clinicians and so on to comprehend the structure of a complex microarray dataset and the gene expression in cells when reduced. This study employs Independent Component Analysis for feature extraction before using k-Nearest Neighbor algorithm to classify colon cancer dataset which contains DNA microarray gene expression data with 2000 features and 62 samples. The experiment was performed using MATLAB 2015a. The result shows that the dimensionality reduction applied improve the classification performance in terms of accuracy, sensitivity, specificity and precision by 11.3%, 25.2%, 36.3% and 12.8% respectively.
Authors and Affiliations
Rasheed Gbenga JIMOH, Ridwan Moyosore YUSUF, Yusuf Owolabi OLATUNDE, Yakub Kayode SAHEED
Keywords
Related Articles
- EP ID EP521473
- DOI -
- Views 71
- Downloads 0
How does the Shift-insertion sort behave when the sorting elements follow a Normal distribution?
The present paper examines the behavior of Shift-insertion sort (insertion sort with shifting) for normal distribution inputs and is in continuation of our earlier work on this new algorithm for discrete distribution inp...
The Usefulness of Multilevel Hash Tables with Multiple Hash Functions in Large Databases<br />
In this work, attempt is made to select three good hash functions which uniformly distribute hash values that permute their internal states and allow the input bits to generate different output bits. These functions are...
Genetic Algorithm Approach for Fabric Pattern Generation in Textile Industries
It is a known fact that there are more possibilities in nature than human brain can conceive. This phenomenon is more pronounced in fabric industry where experts struggle daily for creation of new fabric patterns when in...
Rotation Invariant Skin Detection Approach based on Combination of Probabilistic Distribution Estimation and Single Scale Retinex
Skin detection is one of the main steps in many image processing systems such as face detection, human identicaton, etc. Since now, many methods are proposed to done it accurately. Most of previous methods have tried to...
Variable Selection in the Modeling of Nigeria Economic Growth
This study aimed at identifying and retaining factors that contributed immensely to economic growth in Nigeria based on some variable selection methods. Stepwise regressions are often not efficient when there is multicol...