Nonlinear predictive model selection and model averaging using information criteria

Gu, Yu; Wei, Hua‐Liang; Balikhin, M.

doi:10.1080/21642583.2018.1496042

Cited by 27 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MSE_root indicates the error value in correlation analysis. AIC is the value suitability to the equation to determine the release kinetics. − The results of DDSolver processing are presented in Table and Figure .…”

Section: Resultsmentioning

confidence: 99%

Hydroxypropyl Methylcellulose as Hydrogel Matrix and Citric Acid-Locust Bean Gum as Negative Matrix for Controlled Release Tablet

et al. 2023

View full text Add to dashboard Cite

This study aimed at determining the optimum concentration of hydroxypropyl methylcellulose (HPMC) as hydrogel matrix and citric acid-locust bean gum (CA-LBG) as negative matrix for controlled release tablet formulation. In addition, the study was to determine the effect of CA-LBG and HPMC. CA-LBG accelerates the disintegration of tablets into granules so that the HPMC granule matrix swells immediately and controls drug release. The advantage of this method is that the tablets do not produce large HPMC gel lumps without drug (ghost matrix) but form HPMC gel granules, which can be rapidly degraded after all of the drug is released. Methods: The experiment followed the simplex lattice design to obtain the optimum tablet formula with CA-LBG and HPMC concentrations as optimization factors. Tablet production by the wet granulation method and ketoprofen is the model of the active ingredient. The kinetics of ketoprofen release was studied using several models. Results: Based on the coefficients of each polynomial equation that HPMC and CA-LBG increased the value of angle of repose (

show abstract

Section: Resultsmentioning

confidence: 99%

Hydroxypropyl Methylcellulose as Hydrogel Matrix and Citric Acid-Locust Bean Gum as Negative Matrix for Controlled Release Tablet

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Rsqr_adj shows the correlation between dissolution time and release of 3CH 2 Cl. MSE_root determinates the correlation analysis correction, while the Akaike Information Criterion (AIC) demonstrated the suitability of the equation for determining the release kinetics model. − The results of the DDSolver analysis are shown in Table and Figure (for details see Supporting Information Figures S1–S4).…”

Section: Resultsmentioning

confidence: 99%

Tablet Formulation of 2-((3-(Chloromethyl)benzoyl)oxy)benzoic Acid by Linear and Quadratic Models

et al. 2022

View full text Add to dashboard Cite

Purpose: This research determines the effect of sodium lauryl sulfate (SLS) as a surfactant, croscarmellose sodium (CS) as a disintegrating agent, and SLS–CS combinations on 2-((3-(chloromethyl)benzoyl)oxy)benzoic acid (3CH 2 Cl) (log P = 3.73) tablet formulations. In addition, this study aims to determine the optimum of the 3CH 2 Cl tablet formula. Methods: The tablets are manufactured through direct compression according to the simplex lattice design. The optimal SLS and CS concentration was determined in vitro using linear and quadratic models to achieve better tablet disintegration and dissolution. Results: The same linear and quadratic coefficient profiles of SLS and CS indicate that the combined coefficient of SLS–CS with a quadratic model can be used to predict the effect of the SLS–CS combination. Based on the linear model coefficients, SLS and CS increase the value of flow time (9.35; 7.65), Carr index (26.17; 21.17), hardness (9.84; 7.44), friability (0.38; 0.31), disintegrating time (5.74; 2.62), and drug release (84.28; 58.65). The quadratic model coefficient shows that SLS–CS combinations increase flow time (0.60), Carr index (2.00), hardness (1.00), and disintegrating time (1.04). Meanwhile, they decrease friability (−0.02) and drug release (−9.10). Conclusions: SLS, CS, and SLS–CS combinations affect the quality of tablet mass and tablets. The optimum tablet formula was 3CH 2 Cl (300 mg), Ne (9.38%), SLS (0.92%), CS (2.33%), MCC (5%), and SDL (ad 800 mg). 3CH 2 Cl has analgesic activity despite the presence of tablet excipients. The 3CH 2 Cl tablet is an innovative formulation and a new alternative for future analgesic drugs.

show abstract

“…Assume that at the (m-1)th step, a subset 1  m D , consisting of (m-1) significant bases, The model residual n r will be used to form a criterion for model selection, and the search procedure will be terminated when the norm Finally, a mean square error (MSE) based algorithm, e.g. Akaine's information criterion (AIC), Bayesian information criterion, generalized cross-validation (GCV) and adjustable prediction error sum of squares (APRESS) can be used to determine the model size [40].…”

Section: A1 the Forward Orthogonal Regression Proceduresmentioning

confidence: 99%

Modelling COVID-19 Pandemic Dynamics Using Transparent, Interpretable, Parsimonious and Simulatable (TIPS) Machine Learning Models: A Case Study from Systems Thinking and System Identification Perspectives

Wei

Billings

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Since the outbreak of COVID-19, an astronomical number of publications on the pandemic dynamics appeared in the literature, of which many use the susceptible infected removed (SIR) and susceptible exposed infected removed (SEIR) models, or their variants, to simulate and study the spread of the coronavirus. SIR and SEIR are continuous-time models which are a class of initial value problems (IVPs) of ordinary differential equations (ODEs). Discrete-time models such as regression and machine learning have also been applied to analyze COVID-19 pandemic data (e.g. predicting infection cases), but most of these methods use simplified models involving a small number of input variables pre-selected based on a priori knowledge, or use very complicated models (e.g. deep learning), purely focusing on certain prediction purposes and paying little attention to the model interpretability. There have been relatively fewer studies focusing on the investigations of the inherent time-lagged or time-delayed relationships e.g. between the reproduction number (R number), infection cases, and deaths, analyzing the pandemic spread from a systems thinking and dynamic perspective. The present study, for the first time, proposes using systems engineering and system identification approach to build transparent, interpretable, parsimonious and simulatable (TIPS) dynamic machine learning models, establishing links between the R number, the infection cases and deaths caused by COVID-19. The TIPS models are developed based on the well-known NARMAX (Nonlinear AutoRegressive Moving Average with eXogenous inputs) model, which can help better understand the COVID-19 pandemic dynamics. A case study on the UK COVID-19 data is carried out, and new findings are detailed. The proposed method and the associated new findings are useful for better understanding the spread dynamics of the COVID-19 pandemic.

show abstract

Nonlinear predictive model selection and model averaging using information criteria

Cited by 27 publications

References 56 publications

Hydroxypropyl Methylcellulose as Hydrogel Matrix and Citric Acid-Locust Bean Gum as Negative Matrix for Controlled Release Tablet

Hydroxypropyl Methylcellulose as Hydrogel Matrix and Citric Acid-Locust Bean Gum as Negative Matrix for Controlled Release Tablet

Tablet Formulation of 2-((3-(Chloromethyl)benzoyl)oxy)benzoic Acid by Linear and Quadratic Models

Modelling COVID-19 Pandemic Dynamics Using Transparent, Interpretable, Parsimonious and Simulatable (TIPS) Machine Learning Models: A Case Study from Systems Thinking and System Identification Perspectives

Contact Info

Product

Resources

About