Membrane computing inspired feature selection model for microarray cancer data

Naeimeh Elkhani, Ravie Chandren Muniyandi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Cancer is the main public health issue in most places of the world due to the difficulties in its early diagnosis and to begin early treatment. In the recent years many techniques have been proposed to tackle the high dimensionality in microarray cancer datasets. This paper proposed a membrane-inspired feature selection method to utilize the potentials of membrane computing. In this regard, Kernel P system is modelled based on multi objective binary particle swarm optimization feature selection method through nine modeling steps briefly involving objects of compartments, labels of compartments, multiset of objects in the environment, system structure, and rules involved in each compartment. The proposed model evaluated by cell line data of colorectal cancer. As the initial attempt to come out with a model, division rule and sequential computation on Matlab are used as tools to define potential of membrane computing in trading space against time computation. The evaluation results through Weka indicate that selected marker genes through the proposed model generate high classification accuracy, precision, and recall metrics in compared with pure multi objective binary particle swarm optimization feature selection.

Original languageEnglish
Pages (from-to)S137-S157
JournalIntelligent Data Analysis
Volume21
Issue numberS1
DOIs
Publication statusPublished - 2017

Fingerprint

Membrane Computing
Selection Model
Feature Model
Microarrays
Microarray
Feature Selection
Feature extraction
Cancer
Membranes
Particle swarm optimization (PSO)
Particle Swarm Optimization
Binary
Colorectal Cancer
P Systems
Multiset
Public Health
Public health
Dimensionality
MATLAB
Labels

Keywords

  • feature selection
  • Kernel P system
  • Membrane computing
  • microarray cancer data
  • multi objective binary particle swarm optimization feature selection

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Membrane computing inspired feature selection model for microarray cancer data. / Elkhani, Naeimeh; Muniyandi, Ravie Chandren.

In: Intelligent Data Analysis, Vol. 21, No. S1, 2017, p. S137-S157.

Research output: Contribution to journalArticle

@article{599f32692bc04f08a01433b1a3c56245,
title = "Membrane computing inspired feature selection model for microarray cancer data",
abstract = "Cancer is the main public health issue in most places of the world due to the difficulties in its early diagnosis and to begin early treatment. In the recent years many techniques have been proposed to tackle the high dimensionality in microarray cancer datasets. This paper proposed a membrane-inspired feature selection method to utilize the potentials of membrane computing. In this regard, Kernel P system is modelled based on multi objective binary particle swarm optimization feature selection method through nine modeling steps briefly involving objects of compartments, labels of compartments, multiset of objects in the environment, system structure, and rules involved in each compartment. The proposed model evaluated by cell line data of colorectal cancer. As the initial attempt to come out with a model, division rule and sequential computation on Matlab are used as tools to define potential of membrane computing in trading space against time computation. The evaluation results through Weka indicate that selected marker genes through the proposed model generate high classification accuracy, precision, and recall metrics in compared with pure multi objective binary particle swarm optimization feature selection.",
keywords = "feature selection, Kernel P system, Membrane computing, microarray cancer data, multi objective binary particle swarm optimization feature selection",
author = "Naeimeh Elkhani and Muniyandi, {Ravie Chandren}",
year = "2017",
doi = "10.3233/IDA-170875",
language = "English",
volume = "21",
pages = "S137--S157",
journal = "Intelligent Data Analysis",
issn = "1088-467X",
publisher = "IOS Press",
number = "S1",

}

TY - JOUR

T1 - Membrane computing inspired feature selection model for microarray cancer data

AU - Elkhani, Naeimeh

AU - Muniyandi, Ravie Chandren

PY - 2017

Y1 - 2017

N2 - Cancer is the main public health issue in most places of the world due to the difficulties in its early diagnosis and to begin early treatment. In the recent years many techniques have been proposed to tackle the high dimensionality in microarray cancer datasets. This paper proposed a membrane-inspired feature selection method to utilize the potentials of membrane computing. In this regard, Kernel P system is modelled based on multi objective binary particle swarm optimization feature selection method through nine modeling steps briefly involving objects of compartments, labels of compartments, multiset of objects in the environment, system structure, and rules involved in each compartment. The proposed model evaluated by cell line data of colorectal cancer. As the initial attempt to come out with a model, division rule and sequential computation on Matlab are used as tools to define potential of membrane computing in trading space against time computation. The evaluation results through Weka indicate that selected marker genes through the proposed model generate high classification accuracy, precision, and recall metrics in compared with pure multi objective binary particle swarm optimization feature selection.

AB - Cancer is the main public health issue in most places of the world due to the difficulties in its early diagnosis and to begin early treatment. In the recent years many techniques have been proposed to tackle the high dimensionality in microarray cancer datasets. This paper proposed a membrane-inspired feature selection method to utilize the potentials of membrane computing. In this regard, Kernel P system is modelled based on multi objective binary particle swarm optimization feature selection method through nine modeling steps briefly involving objects of compartments, labels of compartments, multiset of objects in the environment, system structure, and rules involved in each compartment. The proposed model evaluated by cell line data of colorectal cancer. As the initial attempt to come out with a model, division rule and sequential computation on Matlab are used as tools to define potential of membrane computing in trading space against time computation. The evaluation results through Weka indicate that selected marker genes through the proposed model generate high classification accuracy, precision, and recall metrics in compared with pure multi objective binary particle swarm optimization feature selection.

KW - feature selection

KW - Kernel P system

KW - Membrane computing

KW - microarray cancer data

KW - multi objective binary particle swarm optimization feature selection

UR - http://www.scopus.com/inward/record.url?scp=85017364797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017364797&partnerID=8YFLogxK

U2 - 10.3233/IDA-170875

DO - 10.3233/IDA-170875

M3 - Article

VL - 21

SP - S137-S157

JO - Intelligent Data Analysis

JF - Intelligent Data Analysis

SN - 1088-467X

IS - S1

ER -