Feature extraction techniques using multivariate analysis for identification of lung cancer volatile organic compounds

Thriumani,, Reena and Zakaria, Ammar and Hashim, Yumi Zuhanis Has-Yun and Helmy, Khaled Mohamed and Omar, Mohammad Iqbal and Jeffree, Amanina Iymia and Adom, Abdul Hamid and Md Shakaff, Ali Yeon and Kamarudin, Latifah Munirah (2017) Feature extraction techniques using multivariate analysis for identification of lung cancer volatile organic compounds. In: "11th Asian Conference on Chemical Sensors, ACCS 2015", 16- 18 November 2015, Rasa Sayang Resort- Shangri- La PenangPenang; Malaysia.

	PDF (Abstract- Evidence from publishers' website for MYRA) - Published Version Restricted to Repository staff only Download (405kB) | Request a copy
	PDF (SCOPUS) - Supplemental Material Restricted to Repository staff only Download (73kB) | Request a copy
	PDF (WOS) - Supplemental Material Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

In this experiment, three different cell cultures (A549, WI38VA13 and MCF7) and blank medium (without cells) as a control were used. The electronic nose (E-Nose) was used to sniff the headspace of cultured cells and the data were recorded. After data pre-processing, two different features were extracted by taking into consideration of both steady state and the transient information. The extracted data are then being processed by multivariate analysis, Linear Discriminant Analysis (LDA) to provide visualization of the clustering vector information in multi-sensor space. The Probabilistic Neural Network (PNN) classifier was used to test the performance of the E-Nose on determining the volatile organic compounds (VOCs) of lung cancer cell line. The LDA data projection was able to differentiate between the lung cancer cell samples and other samples (breast cancerrmal cell and blank medium) effectively. The features extracted from the steady state response reached 100% of classification rate while the transient response with the aid of LDA dimension reduction methods produced 100% classification performance using PNN classifier with a spread value of 0.1. The results also show that E-Nose application is a promising technique to be applied to real patients in further work and the aid of Multivariate Analysis; it is able to be the alternative to the current lung cancer diagnostic methods.

Item Type:	Conference or Workshop Item (Plenary Papers)
Additional Information:	3774/57495
Uncontrolled Keywords:	Feature extraction; Multivariate analysis; Identification of lung cancer, Organic compounds
Subjects:	Q Science > QD Chemistry T Technology > TD Environmental technology. Sanitary engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering Kulliyyah of Engineering > Department of Biotechnology Engineering
Depositing User:	DR YUMI ZUHANIS HAS-YUN HASHIM
Date Deposited:	05 Jul 2017 16:48
Last Modified:	17 Aug 2019 23:44
URI:	http://irep.iium.edu.my/id/eprint/57495

Actions (login required)

View Item