UTHM Institutional Repository

Modification of continuous and binary ICU data in form models

Rusiman, Mohd Saifullah and Adnan, Robiah and Nasibov, Efendi N. and Jacob, Kavikumar (2011) Modification of continuous and binary ICU data in form models. In: International Seminar on the Application of Science & Mathematics 2011, 1 - 3 November 2011, Putra World Trade Centre, KL, Malaysia.

[img]
Preview
PDF
4.pdf

Download (151kB)

Abstract

This research is an attempt to present a proper methodology in data modification by using analytical hierarchy process (AHP) technique and fuzzy c-mean (FCM) model. The continuous data were built from b inary data using analytical hierarchy process (AHP). Whereas, the binary data were created from continuous data using fuzzy cmeans (FCM) model. The models used in this research are fuzzy c-regression models (FCRM). A case study in scale of health at an intensive care unit (ICU) ward using the AHP, FCM model and FCRM models was carried out. There are six independent variables involved in this study. There are four cases considered as a result of using AHP technique and FCM model toward independent data. After comparing the four cases, it was found that case 4 appeared to be the best model, having the lowest mean square error (MSE). The orig inal data have the MSE value of 97.33, wh ile the data of case 4 have MSE by 83.48. Th is means that the AHP technique can lower the MSE, while the FCM model cannot lower the MSE in modelling scale of health in the ICU. In other words, it can be claimed that the AHP technique can increase the accuracy of modelling prediction.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Analytical hierarchy process (AHP), fuzzy c-means (FCM) model, fuzzy c-regression models (FCRM), mean square error (MSE)
Subjects: T Technology > T Technology (General)
Depositing User: M.Iqbal Zainal A
Date Deposited: 07 May 2012 01:02
Last Modified: 07 May 2012 01:02
URI: http://eprints.uthm.edu.my/id/eprint/2362
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year