A comparison study between different kernel functions in the least square support vector regression model for penicillin fermentation process

Abstract

Soft sensors are becoming increasingly important in our world today as tools for inferring difficult-to-measure process variables to achieve good operational performance and economic benefits. Recent advancement in machine learning provides an opportunity to integrate machine learning models for soft sensing applications, such as Least Square Support Vector Regression (LSSVR) which copes well with nonlinear process data. However, the LSSVR model usually uses the radial basis function (RBF) kernel function for prediction, which has demonstrated its usefulness in numerous applications. Thus, this study extends the use of non-conventional kernel functions in the LSSVR model with a comparative study against widely used partial least square (PLS) and principal component regression (PCR) models, measured with root mean square error (RMSE), mean absolute error (MAE) and error of approximation (Ea) as the performance benchmark. Based on the empirical result from the case study of the penicillin fermentation process, the Ea of the multiquadric kernel (MQ) is lowered by 63.44% as compared to the RBF kernel for the prediction of penicillin concentration. Hence, the MQ kernel LSSVR has outperformed the RBF kernel LSSVR. The study serves as empirical evidence of LSSVR performance as a machine learning model in soft sensing applications and as reference material for further development of non-conventional kernels in LSSVR-based models because many other functions can be used as well in the hope to increase the prediction accuracy.

A Comparative Study of Different Artificial Intelligence Models and Response Surface Methodology for Heptachlor Removal Using Fe/Cu Nanoparticles

“…In the LW-KPLS model, by applying an appropriate Kernel function, the data of the case study are mapped into an infinitedimensional space. In this study, the mapping of the case study's data into an infinite-dimensional space was done using the log Kernel function displayed in Equation (1) [15,16].…”

Introduction of LSSVR for the Prediction of the Yellowness Index

“…Moreover, a soft sensor is one of the advances in modern statistics and computing technology that can bring new chances to form novel or improved evaluation techniques [3]. A soft sensor utilizes regression analysis that involves a set of machine learning techniques allowing the prediction of a continuous output variable based on the value of one or multiple predictor variables or input variables [4], [5]. To be more specific, the soft sensor model is used for the forecast of future targeted data based on the correlation between individual variables to have an optimized and productive operating process when it is incorporated into a processing system [6].…”