会议论文详细信息
International Conference on Chemical and Bioprocess Engineering | |
A review on intelligent sensory modelling | |
地球科学;化学;生物科学 | |
Tham, H.J.^1 ; Tang, S.Y.^1 ; Teo, K.T.K.^2 ; Loh, S.P.^3 | |
Chemical Engineering Program, Faculty of Engineering, Universiti Malaysia Sabah, Jalan, Kota Kinabalu, Sabah | |
88400, Malaysia^1 | |
Electrical and Electronic Engineering Program, Faculty of Engineering, Universiti Malaysia Sabah, Jalan, Kota Kinabalu, Sabah | |
88400, Malaysia^2 | |
Department of Nutrition and Dietetics, Faculty of Medical and Health Sciences, Universiti Putra Malaysia, Serdang, Selangor | |
43400, Malaysia^3 | |
关键词: Modelling techniques; Multiple regressions; Multivariate methods; Partial least square (PLS); Principle component analysis; Response surface method; Sensory data analysis; Vagueness and uncertainty; | |
Others : https://iopscience.iop.org/article/10.1088/1755-1315/36/1/012065/pdf DOI : 10.1088/1755-1315/36/1/012065 |
|
学科分类:生物科学(综合) | |
来源: IOP | |
![]() |
【 摘 要 】
Sensory evaluation plays an important role in the quality control of food productions. Sensory data obtained through sensory evaluation are generally subjective, vague and uncertain. Classically, factorial multivariate methods such as Principle Component Analysis (PCA), Partial Least Square (PLS) method, Multiple Regression (MLR) method and Response Surface Method (RSM) are the common tools used to analyse sensory data. These methods can model some of the sensory data but may not be robust enough to analyse nonlinear data. In these situations, intelligent modelling techniques such as Fuzzy Logic and Artificial neural network (ANNs) emerged to solve the vagueness and uncertainty of sensory data. This paper outlines literature of intelligent sensory modelling on sensory data analysis.【 预 览 】
Files | Size | Format | View |
---|---|---|---|
A review on intelligent sensory modelling | 1103KB | ![]() |