Usefulness of Applying Partial Least Squares Regression to T2 Relaxation Curves for Predicting the Solid form Content in Binary Physical Mixtures

Chiba, Yuya; Okada, Kotaro; Hayashi, Yoshihiro; Kumada, Shungo; Onuki, Yoshinori

doi:10.1016/j.xphs.2022.11.028

Cited by 3 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main objective of PLS is to predict the dependent variable using the independent variable and determine the structure between the two. This regression method allows the identification of underlying factors, which are linear combinations of the dependent variables that best explain the independent variable [49].…”

Section: Partial Least Squaresmentioning

confidence: 99%

Prediction of Internal Temperature in Greenhouses Using the Supervised Learning Techniques: Linear and Support Vector Regressions

García-Vázquez,

Ponce-González,

Guerrero-Osuna

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Agricultural greenhouses must accurately predict environmental factors to ensure optimal crop growth and energy management efficiency. However, the existing predictors have limitations when dealing with dynamic, non-linear, and massive temporal data. This study proposes four supervised learning techniques focused on linear regression (LR) and Support Vector Regression (SVR) to predict the internal temperature of a greenhouse. A meteorological station is installed in the greenhouse to collect internal data (temperature, humidity, and dew point) and external data (temperature, humidity, and solar radiation). The data comprises a one year, and is divided into seasons for better analysis and modeling of the internal temperature. The study involves sixteen experiments corresponding to the four models and the four seasons and evaluating the models’ performance using R2, RMSE, MAE, and MAPE metrics, considering an acceptability interval of ±2 °C. The results show that LR models had difficulty maintaining the acceptability interval, while the SVR models adapted to temperature outliers, presenting the highest forecast accuracy among the proposed algorithms.

show abstract

Section: Partial Least Squaresmentioning

confidence: 99%

Prediction of Internal Temperature in Greenhouses Using the Supervised Learning Techniques: Linear and Support Vector Regressions

García-Vázquez,

Ponce-González,

Guerrero-Osuna

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Time domain NMR for polymorphism characterization: Current status and future perspectives

Almeida,

Carneiro,

Colnago

2025

International Journal of Pharmaceutics

View full text Add to dashboard Cite

プロセス解析を目指した時間領域nmrを基盤とする製剤の物性評価

Okada

2023

YAKUGAKU ZASSHI

Self Cite

View full text Add to dashboard Cite

Here, we sought to investigate the usefulness of time-domain NMR (TD-NMR) for evaluating the physical properties of drug formulations. TD-NMR measures NMR relaxation and is mainly performed using a bench-top low-field NMR system (e.g., 20 MHz); thus, it does not require any specific sample shape for measurement if the sample is not gas. Taking advantage of these features, TD-NMR has been widely used for quality control in food science. However, it has rarely been used in the pharmaceutical field. The T 1 and T 2 relaxations are not spectra like those obtained by a high-field NMR system (e.g., 300-600 MHz) but only curves in which the NMR signal recovers or decays according to a specific rule. Therefore, selecting the equation used in the fitting analysis is crucial to estimate the time constants, T 1 and T 2 relaxation times. As the result of a series of studies, the T 1 relaxation measurement by TD-NMR was shown to help evaluate the crystallinity of drugs in solid dosage forms and the miscibility of a drug and excipient in a binary mixture. The T 2 relaxation measurement was also helpful for quantitatively evaluating the solid form of drugs in a physical mixture with or without moisture adsorption. TD-NMR is an excellent technique widely applied to evaluating the physical properties of various formulations, whether solid or liquid, and is expected to be applied to process analysis and quality control in the pharmaceutical field.

show abstract

Usefulness of Applying Partial Least Squares Regression to T2 Relaxation Curves for Predicting the Solid form Content in Binary Physical Mixtures

Cited by 3 publications

References 36 publications

Prediction of Internal Temperature in Greenhouses Using the Supervised Learning Techniques: Linear and Support Vector Regressions

Prediction of Internal Temperature in Greenhouses Using the Supervised Learning Techniques: Linear and Support Vector Regressions

Time domain NMR for polymorphism characterization: Current status and future perspectives

プロセス解析を目指した時間領域nmrを基盤とする製剤の物性評価

Contact Info

Product

Resources

About