Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis

The tensile strength (TS) of compacted ribbon is a critical quality attribute in the roller compaction process that impacts the quality of the finished product. This study investigated the use of Near Infrared Hyperspectral Imaging Spectroscopy (NIR-HIS) technology for predicting TS of compacted rib...

Full description

Saved in:
Bibliographic Details
Main Authors: Juthamat Wanfueangfu, Jetsada Posom, Duchdoune Teerasukaporn, Panuwat Supprung, Jomjai Peerapattana
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024158690
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846167011929882624
author Juthamat Wanfueangfu
Jetsada Posom
Duchdoune Teerasukaporn
Panuwat Supprung
Jomjai Peerapattana
author_facet Juthamat Wanfueangfu
Jetsada Posom
Duchdoune Teerasukaporn
Panuwat Supprung
Jomjai Peerapattana
author_sort Juthamat Wanfueangfu
collection DOAJ
description The tensile strength (TS) of compacted ribbon is a critical quality attribute in the roller compaction process that impacts the quality of the finished product. This study investigated the use of Near Infrared Hyperspectral Imaging Spectroscopy (NIR-HIS) technology for predicting TS of compacted ribbons, considering the effects of surface curvature, different spectral preprocessing methods, and variable selection methods on a predictive model based on Partial Least Squares regression (PLSr). The spectral preprocessing methods evaluated were Mean Centering (MC) and Standard Normal Variate (SNV). The variable selection methods were Filter by Regression Coefficient (REG), Variable Importance in Projection (VIP), Competitive Adaptive Reweighted Sampling (CARS), and Genetic Algorithm (GA). The results indicated that curved surfaces had no significant impact on the predictive performance of the model (p-value of 0.39 for RMSEP). The PLSr-CARS method, combined with MC spectral preprocessing, was successful in selecting and reducing the number of wavelengths from 182 to 5, as indicated by high values of R2pred and RPD, and a low RMSEP value (0.97, 5.75, and 7.60 %, respectively). An MLR model using the 5 wavelengths was also developed, showing similar performance to the PLSr model. Both the MLR and PLSr models demonstrated high predictive accuracy and reliability. These models can perform well even when developed using only a few wavelengths, leading to significant reductions in processing time and measurement costs, making them valuable tools for quality control in the pharmaceutical industry.
format Article
id doaj-art-f3f379ad4a834a2ba03398d2d9f96898
institution Kabale University
issn 2405-8440
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-f3f379ad4a834a2ba03398d2d9f968982024-11-15T06:13:44ZengElsevierHeliyon2405-84402024-11-011021e39838Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysisJuthamat Wanfueangfu0Jetsada Posom1Duchdoune Teerasukaporn2Panuwat Supprung3Jomjai Peerapattana4Division of Pharmaceutical Technology, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, ThailandDepartment of Agricultural Engineering, Faculty of Engineering, Khon Kaen University, Khon Kaen, 40002, ThailandMedica Innova Research and Development, Medica Innova Co., Ltd., Bangkok, 10310, ThailandDepartment of Postharvest and Agricultural Process Engineering, Faculty of Engineering, Rajamangala University of Technology Isan, Khon Kaen Campus, Khon Kaen 40000, ThailandDivision of Pharmaceutical Technology, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand; Corresponding author.The tensile strength (TS) of compacted ribbon is a critical quality attribute in the roller compaction process that impacts the quality of the finished product. This study investigated the use of Near Infrared Hyperspectral Imaging Spectroscopy (NIR-HIS) technology for predicting TS of compacted ribbons, considering the effects of surface curvature, different spectral preprocessing methods, and variable selection methods on a predictive model based on Partial Least Squares regression (PLSr). The spectral preprocessing methods evaluated were Mean Centering (MC) and Standard Normal Variate (SNV). The variable selection methods were Filter by Regression Coefficient (REG), Variable Importance in Projection (VIP), Competitive Adaptive Reweighted Sampling (CARS), and Genetic Algorithm (GA). The results indicated that curved surfaces had no significant impact on the predictive performance of the model (p-value of 0.39 for RMSEP). The PLSr-CARS method, combined with MC spectral preprocessing, was successful in selecting and reducing the number of wavelengths from 182 to 5, as indicated by high values of R2pred and RPD, and a low RMSEP value (0.97, 5.75, and 7.60 %, respectively). An MLR model using the 5 wavelengths was also developed, showing similar performance to the PLSr model. Both the MLR and PLSr models demonstrated high predictive accuracy and reliability. These models can perform well even when developed using only a few wavelengths, leading to significant reductions in processing time and measurement costs, making them valuable tools for quality control in the pharmaceutical industry.http://www.sciencedirect.com/science/article/pii/S2405844024158690Near infrared hyperspectral imaging spectroscopyVariable importance in projectionCompetitive adaptive reweighted samplingGenetic algorithmRoller compactorVariable selection method
spellingShingle Juthamat Wanfueangfu
Jetsada Posom
Duchdoune Teerasukaporn
Panuwat Supprung
Jomjai Peerapattana
Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
Heliyon
Near infrared hyperspectral imaging spectroscopy
Variable importance in projection
Competitive adaptive reweighted sampling
Genetic algorithm
Roller compactor
Variable selection method
title Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
title_full Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
title_fullStr Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
title_full_unstemmed Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
title_short Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis
title_sort optimization of a tensile strength prediction model for compacted ribbons using nir his analysis
topic Near infrared hyperspectral imaging spectroscopy
Variable importance in projection
Competitive adaptive reweighted sampling
Genetic algorithm
Roller compactor
Variable selection method
url http://www.sciencedirect.com/science/article/pii/S2405844024158690
work_keys_str_mv AT juthamatwanfueangfu optimizationofatensilestrengthpredictionmodelforcompactedribbonsusingnirhisanalysis
AT jetsadaposom optimizationofatensilestrengthpredictionmodelforcompactedribbonsusingnirhisanalysis
AT duchdouneteerasukaporn optimizationofatensilestrengthpredictionmodelforcompactedribbonsusingnirhisanalysis
AT panuwatsupprung optimizationofatensilestrengthpredictionmodelforcompactedribbonsusingnirhisanalysis
AT jomjaipeerapattana optimizationofatensilestrengthpredictionmodelforcompactedribbonsusingnirhisanalysis