Classification of human membrane protein types using optimal local discriminant bases feature extraction method

Nor Ashikin Mohamad Kamal, Azuraliza Abu Bakar, Suhaila Zainudin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a method of membrane protein feature extraction using a combination of the local discriminant bases (LDB) and three different classifiers. This method has adopted two dissimilarity measures of normalized energy difference and relative entropy to identify a set of orthogonal subspaces in optimal wavelet packets. The energy will be derived from the calculation of the two dissimilarity measures that have overlapping subspaces. This feature, in turn, serves as an input to support vector machine (SVM), decision tree and naïve Bayes classifiers. The proposed model yields the highest accuracy of 78.6%, 76.25%, 76.72% for dataset S1, S2, and S3 respectively by using SVM. This technique outperformed other feature extraction method for membrane protein type classification for dataset S2 and S3.

Original languageEnglish
Pages (from-to)767-771
Number of pages5
JournalJournal of Theoretical and Applied Information Technology
Volume96
Issue number3
Publication statusPublished - 15 Feb 2018

Fingerprint

Membrane Protein
Discriminant
Feature Extraction
Support vector machines
Feature extraction
Dissimilarity Measure
Classifiers
Proteins
Membranes
Support Vector Machine
Decision trees
Subspace
Bayes Classifier
Wavelet Packet
Entropy
Relative Entropy
Energy
Decision tree
Overlapping
High Accuracy

Keywords

  • Feature extraction
  • Local discriminant bases
  • Membrane proteins
  • SVM
  • Wavelet

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

@article{142714ee225f4f7c838e3c9b7e8f0610,
title = "Classification of human membrane protein types using optimal local discriminant bases feature extraction method",
abstract = "This paper presents a method of membrane protein feature extraction using a combination of the local discriminant bases (LDB) and three different classifiers. This method has adopted two dissimilarity measures of normalized energy difference and relative entropy to identify a set of orthogonal subspaces in optimal wavelet packets. The energy will be derived from the calculation of the two dissimilarity measures that have overlapping subspaces. This feature, in turn, serves as an input to support vector machine (SVM), decision tree and na{\"i}ve Bayes classifiers. The proposed model yields the highest accuracy of 78.6{\%}, 76.25{\%}, 76.72{\%} for dataset S1, S2, and S3 respectively by using SVM. This technique outperformed other feature extraction method for membrane protein type classification for dataset S2 and S3.",
keywords = "Feature extraction, Local discriminant bases, Membrane proteins, SVM, Wavelet",
author = "Kamal, {Nor Ashikin Mohamad} and {Abu Bakar}, Azuraliza and Suhaila Zainudin",
year = "2018",
month = "2",
day = "15",
language = "English",
volume = "96",
pages = "767--771",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "3",

}

TY - JOUR

T1 - Classification of human membrane protein types using optimal local discriminant bases feature extraction method

AU - Kamal, Nor Ashikin Mohamad

AU - Abu Bakar, Azuraliza

AU - Zainudin, Suhaila

PY - 2018/2/15

Y1 - 2018/2/15

N2 - This paper presents a method of membrane protein feature extraction using a combination of the local discriminant bases (LDB) and three different classifiers. This method has adopted two dissimilarity measures of normalized energy difference and relative entropy to identify a set of orthogonal subspaces in optimal wavelet packets. The energy will be derived from the calculation of the two dissimilarity measures that have overlapping subspaces. This feature, in turn, serves as an input to support vector machine (SVM), decision tree and naïve Bayes classifiers. The proposed model yields the highest accuracy of 78.6%, 76.25%, 76.72% for dataset S1, S2, and S3 respectively by using SVM. This technique outperformed other feature extraction method for membrane protein type classification for dataset S2 and S3.

AB - This paper presents a method of membrane protein feature extraction using a combination of the local discriminant bases (LDB) and three different classifiers. This method has adopted two dissimilarity measures of normalized energy difference and relative entropy to identify a set of orthogonal subspaces in optimal wavelet packets. The energy will be derived from the calculation of the two dissimilarity measures that have overlapping subspaces. This feature, in turn, serves as an input to support vector machine (SVM), decision tree and naïve Bayes classifiers. The proposed model yields the highest accuracy of 78.6%, 76.25%, 76.72% for dataset S1, S2, and S3 respectively by using SVM. This technique outperformed other feature extraction method for membrane protein type classification for dataset S2 and S3.

KW - Feature extraction

KW - Local discriminant bases

KW - Membrane proteins

KW - SVM

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=85042365432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042365432&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85042365432

VL - 96

SP - 767

EP - 771

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 3

ER -