Prediction of the melt flow index using partial least squares and support vector regression in high-density polyethylene (HDPE) process

2010 ◽  
Vol 27 (6) ◽  
pp. 1662-1668 ◽  
Author(s):  
Tae Chang Park ◽  
Tae Young Kim ◽  
Yeong Koo Yeo
Keyword(s):  
Least Squares ◽  
Support Vector Regression ◽  
Partial Least Squares ◽  
High Density Polyethylene ◽  
Melt Flow Index ◽  
High Density ◽  
Flow Index ◽  
Support Vector ◽  
Melt Flow

Effects of fluoropolymer and calcium stearate on melt flow index and mechanical properties of high-density polyethylene

2018 ◽  
Author(s):  
Mohamad Zaki Abdullah ◽  
Jad Safwan Jemsee ◽  
Muhammad Shazwan Mahmud ◽  
Hamdan Ya
Keyword(s):  
Mechanical Properties ◽  
High Density Polyethylene ◽  
Melt Flow Index ◽  
High Density ◽  
Calcium Stearate ◽  
Flow Index ◽  
Melt Flow

scholarly journals Determination of Cefoperazone Sodium in Presence of Related Impurities by Linear Support Vector Regression and Partial Least Squares Chemometric Models

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Ibrahim A. Naguib ◽  
Eglal A. Abdelaleem ◽  
Hala E. Zaazaa ◽  
Essraa A. Hussein
Keyword(s):  
Least Squares ◽  
Support Vector Regression ◽  
Partial Least Squares ◽  
Multivariate Calibration ◽  
Drug Product ◽  
Support Vector ◽  
Control Analysis ◽  
Least Squares Regression ◽  
Significant Difference ◽  
Cefoperazone Sodium

A comparison between partial least squares regression and support vector regression chemometric models is introduced in this study. The two models are implemented to analyze cefoperazone sodium in presence of its reported impurities, 7-aminocephalosporanic acid and 5-mercapto-1-methyl-tetrazole, in pure powders and in pharmaceutical formulations through processing UV spectroscopic data. For best results, a 3-factor 4-level experimental design was used, resulting in a training set of 16 mixtures containing different ratios of interfering moieties. For method validation, an independent test set consisting of 9 mixtures was used to test predictive ability of established models. The introduced results show the capability of the two proposed models to analyze cefoperazone in presence of its impurities 7-aminocephalosporanic acid and 5-mercapto-1-methyl-tetrazole with high trueness and selectivity (101.87 ± 0.708 and 101.43 ± 0.536 for PLSR and linear SVR, resp.). Analysis results of drug products were statistically compared to a reported HPLC method showing no significant difference in trueness and precision, indicating the capability of the suggested multivariate calibration models to be reliable and adequate for routine quality control analysis of drug product. SVR offers more accurate results with lower prediction error compared to PLSR model; however, PLSR is easy to handle and fast to optimize.

Anwendung spektroskopischer Messverfahren und Multivariater Datenanalyse zur Bewertung und Beobachtung von Bioprozessen

2017 ◽  
Author(s):  
Jan-Patrick Voß
Keyword(s):  
Pichia Pastoris ◽  
Least Squares ◽  
Support Vector Regression ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Process Analytical Technology ◽  
Support Vector ◽  
Least Squares Regression ◽  
Analytical Technology

Die vorliegende Arbeit befasst sich mit dem Bioprozessmonitoring unter Verwendung spektroskopischer Messverfahren und multivariater Datenanalyse nach den Grundsätzen von PAT – Process Analytical Technology. Mit NIR-Spektroskopie und dem Verfahren Soft Independent Modelling of Class Analogy (SIMCA) wurde eine Quali¬tätsbewertung von Hefeextrakten realisiert. Im Vordergrund stand jedoch die Quanti¬fizierung nicht direkt messbarer Größen aus NIR-, Raman- und 2D-Fluoreszenzspektren in pharmazeutischen Produktionsprozessen mit Pichia pastoris. Eine entsprechende Online-Bestimmung mit der Methode Partial Least Squares Regression (PLSR) kam weiterführend zur Regelung der Glycerolkonzentration zum Einsatz. Darüber hinaus wurde die Verwendung nichtspektraler Online-Daten zur Prozessbeobachtung erprobt. Dabei gelang mit Hilfe des nichtlinearen Verfahrens Support Vector Regression (SVR) unter anderem die Bestimmung zellspezifischer Reaktionsraten. ...

Thermal and Thermorheologic Characterization of Different Polyolefin Waste Fractions

2017 ◽  
Vol 907 ◽  
pp. 74-79
Author(s):  
Adela Lazar ◽  
Catalin Croitoru ◽  
Mircea Horia Tierean ◽  
Liana Sanda Baltes
Keyword(s):  
Molecular Mass ◽  
High Density Polyethylene ◽  
Melt Flow Index ◽  
Household Waste ◽  
Flow Index ◽  
Melt Flow ◽  
Polymer Waste ◽  
Lower Molecular Mass ◽  
Low Shear

In this study, melt flow index values from several household waste fractions containing mainly polypropylene and high-density polyethylene, were measured at 190 °C for polyethylene and 230 °C for polypropylene-rich fractions. High values of MFI (low shear viscosities) have been reported probably due to the lower molecular mass of the polymer waste and/or the presence of surfactant compounds on the surface of the polymer flakes. Also, by extruding the same batch in different cycles at the same temperature values, the number of processing cycles on which the polymer could be recycled has been determined.

Partial Least-Squares and Linear Support Vector Regression Chemometric Methods for Simultaneous Determination of Amoxicillin Trihydrate and Dicloxacillin Sodium in the Presence of Their Common Impurity

2016 ◽  
Vol 99 (4) ◽  
pp. 972-979
Author(s):  
Ibrahim A Naguib ◽  
Eglal A Abdelaleem ◽  
Hala E Zaazaa ◽  
Essraa A Hussein
Keyword(s):  
Least Squares ◽  
Support Vector Regression ◽  
Partial Least Squares ◽  
Dosage Form ◽  
Support Vector ◽  
Prediction Ability ◽  
Pharmaceutical Dosage Form ◽  
Significant Difference ◽  
Amoxicillin Trihydrate ◽  
Plsr Model

Abstract Two multivariate chemometric models, namely, partial least-squares regression (PLSR) and linear support vector regression (SVR), are presented for the analysis of amoxicillin trihydrate and dicloxacillin sodium in the presence of their common impurity (6-aminopenicillanic acid) in raw materials and in pharmaceutical dosage form via handling UV spectral data and making a modest comparison between the two models, highlighting the advantages and limitations of each. For optimum analysis, a three-factor, four-level experimental design was established, resulting in a training set of 16 mixtures containing different ratios of interfering species. To validate the prediction ability of the suggested models, an independent test set consisting of eight mixtures was used. The presented results show the ability of the two proposed models to determine the two drugs simultaneously in the presence of small levels of the common impurity with high accuracy and selectivity. The analysis results of the dosage form were statistically compared to a reported HPLC method, with no significant difference regarding accuracy and precision, indicating the ability of the suggested multivariate calibration models to be reliable and suitable for routine analysis of the drug product. Compared to the PLSR model, the SVR model gives more accurate results with a lower prediction error, as well as high generalization ability; however, the PLSR model is easy to handle and fast to optimize.

Sign in / Sign up

Export Citation Format

Share Document