scholarly journals An Efficient Compressive Hyperspectral Imaging Algorithm Based on Sequential Computations of Alternating Least Squares

2019 ◽  
Vol 11 (24) ◽  
pp. 2932 ◽  
Author(s):  
Geunseop Lee
Keyword(s):  
Least Squares ◽  
Hyperspectral Imaging ◽  
Optimization Problems ◽  
Tensor Decomposition ◽  
Alternating Least Squares ◽  
Low Rank ◽  
Imaging Data ◽  
Significant Difference ◽  
Multilinear Rank ◽  
Value Decomposition

Hyperspectral imaging is widely used to many applications as it includes both spatial and spectral distributions of a target scene. However, a compression, or a low multilinear rank approximation of hyperspectral imaging data, is required owing to the difficult manipulation of the massive amount of data. In this paper, we propose an efficient algorithm for higher order singular value decomposition that enables the decomposition of a tensor into a compressed tensor multiplied by orthogonal factor matrices. Specifically, we sequentially compute low rank factor matrices from the Tucker-1 model optimization problems via an alternating least squares approach. Experiments with real world hyperspectral imaging revealed that the proposed algorithm could compute the compressed tensor with a higher computational speed, but with no significant difference in accuracy of compression compared to the other tensor decomposition-based compression algorithms.

A novel multivariate curve resolution-alternating least squares (MCR-ALS) methodology for application in hyperspectral Raman imaging analysis

The Analyst ◽  
2019 ◽  
Vol 144 (18) ◽  
pp. 5425-5438 ◽  
Author(s):  
Joseph P. Smith ◽  
Erin C. Holahan ◽  
Frank C. Smith ◽  
Veronica Marrero ◽  
Karl S. Booksh
Keyword(s):  
Least Squares ◽  
Hyperspectral Imaging ◽  
Chemical Constituents ◽  
Alternating Least Squares ◽  
Model Complexity ◽  
Multivariate Curve Resolution ◽  
Imaging Analysis ◽  
Imaging Data ◽  
Optimal Model ◽  
Curve Resolution

A new multivariate curve resolution-alternating least squares (MCR-ALS) methodology is presented that uses approximate reference spectra to determine optimal model complexity for identifying chemical constituents within hyperspectral imaging data.

scholarly journals Simultaneous Determination of Over-the-Counter Pain Relievers in Commercial Pharmaceutical Products Utilizing Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) Multivariate Calibration Model

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Heba Shaaban ◽  
Ahmed Mostafa ◽  
Zahra Almatar ◽  
Reem Alsheef ◽  
Safia Alrubh
Keyword(s):  
Least Squares ◽  
Multivariate Calibration ◽  
Pharmaceutical Products ◽  
Alternating Least Squares ◽  
Multivariate Curve Resolution ◽  
Calibration Model ◽  
Over The Counter ◽  
Curve Resolution ◽  
Relative Standard ◽  
Significant Difference

The quality of over-the-counter (OTC) pain relievers is important to ensure the safety of the marketed products in order to maintain the overall health care of patients. In this study, the multivariate curve resolution-alternating least squares (MCR-ALS) chemometric method was developed and validated for the resolution and quantification of the most commonly consumed OTC pain relievers (acetaminophen, acetylsalicylic acid, ibuprofen, naproxen, and caffeine) in commercial drug formulations. The analytical performance of the developed chemometric methods such as root mean square error of prediction, bias, standard error of prediction, relative error of prediction, and coefficients of determination was calculated for the developed model. The obtained results are linear with concentration in the range of 0.5–7 μg/mL for acetaminophen and 0.5–3.5 and 0.5–3 μg/mL for naproxen and caffeine, respectively, while the linearity ranges for acetyl salicylic acid and ibuprofen were 1–15 μg/mL. High values of coefficients of determination ≥0.9995 reflected high predictive ability of the developed model. Good recoveries ranging from 98.0% to 99.7% were obtained for all analytes with relative standard deviations (RSDs) not higher than 1.62%. The optimized method was successfully applied for the analysis of the studied drugs either in their single or coformulated pharmaceutical products without any separation step. The optimized method was also compared with a reported HPLC method using paired t-test and F-ratio at 95% confidence level, and the results showed no significant difference regarding accuracy and precision. The developed method is eco-friendly, simple, fast, and amenable for routine analysis. It could be used as a cost-effective alternative to chromatographic techniques for the analysis of the studied drugs in commercial formulations.

scholarly journals Simultaneous Determination of Drugs Affecting Central Nervous System (CNS) in Bulk and Pharmaceutical Formulations Using Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS)

2020 ◽  
Vol 2020 ◽  
pp. 1-8 ◽  
Author(s):  
Heba Shaaban ◽  
Ahmed Mostafa ◽  
Bushra Al-Zahrani ◽  
Bushra Al-Jasser ◽  
Raghad Al-Ghamdi
Keyword(s):  
Central Nervous System ◽  
Nervous System ◽  
Least Squares ◽  
Pharmaceutical Formulations ◽  
Pharmaceutical Products ◽  
Alternating Least Squares ◽  
Multivariate Curve Resolution ◽  
Pharmaceutical Dosage Forms ◽  
Curve Resolution ◽  
Significant Difference

The quality of medications is important to maintain the overall health care of patients. This study aims to develop and validate a spectrophotometric method using multivariate curve resolution-alternating least squares (MCR-ALS) with correlation constraint for simultaneous resolution and quantification of selected drugs affecting the central nervous system (imipramine, carbamazepine, chlorpromazine, haloperidol, and phenytoin) in different pharmaceutical dosage forms. Figures of merit such as root-mean-square error of prediction, bias, standard error of prediction, and relative error of prediction for the developed method were calculated. High values of correlation coefficients ranged between 0.9993 and 0.9998 reflected high predictive ability of the developed method. The results are linear in the concentration range of 0.3–5 μg/mL for carbamazepine, 0.3–15 μg/mL for chlorpromazine, 0.5–10 μg/mL for haloperidol, 0.5–10 μg/mL for imipramine, and 3–20 μg/mL for phenytoin. The optimized method was successfully applied for the analysis of the studied drugs in their pharmaceutical products without any separation step. The optimized method was also compared with a reported HPLC method using Student’s t test and F ratio at 95% confidence level, and the results showed no significant difference regarding accuracy and precision. The proposed chemometric method is fast, reliable, and cost-effective and can be used as an eco-friendly alternative to chromatographic techniques for the analysis of the studied drugs in commercial pharmaceutical products.

Sign in / Sign up

Export Citation Format

Share Document