CHEMOMETRICS AND STATISTICS | Multivariate Calibration Techniques

Hanrahan, Grady; Udeh, F.; Patil, Deepa G.

doi:10.1016/b0-12-369397-7/00077-7

Cited by 18 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A terminating rule is employed to identify the optimal number of components. But, unlike PCR, PLSR considers the response variable when creating the components to explain the observed variability in the predictor variables [86]. This will often lead to the development of models that are able to fit the response variable with a fewer number of components [43], [87].…”

Section: E ML Algorithmsmentioning

confidence: 99%

Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment

Zolfaghari

Pahlevan

Binding

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Cyanobacterial harmful algal blooms are an increasing threat to coastal and inland waters. These blooms can be detected using optical radiometers due to the presence of phycocyanin (PC) pigments. The spectral resolution of bestavailable multispectral sensors limits their ability to diagnostically detect PC in the presence of other photosynthetic pigments. To assess the role of spectral resolution in the determination of PC, a large (N = 905) database of colocated in situ radiometric spectra and PC are employed. We first examine the performance of selected widely used machine-learning (ML) models against that of benchmark algorithms for hyperspectral remote sensing reflectance (R rs ) spectra resampled to the spectral configuration of the Hyperspectral Imager for the Coastal Ocean (HICO) with a full-width at half-maximum (FWHM) of < 6 nm. Results show that the multilayer perceptron (MLP) neural network applied to HICO spectral configurations (median errors < 65%)

show abstract

Section: E ML Algorithmsmentioning

confidence: 99%

Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment

Zolfaghari

Pahlevan

Binding

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…For this purpose, inverse modeling requires that all the constituents present in the sample are also present in the set used to train the model. [35][36][37] Another requirement of MLR is that the number of variables must be smaller than the number of samples, with the variables preferably not being correlated.…”

Section: Resultsmentioning

confidence: 99%

A rapid and direct method for dating blue pen ink in documents using multiset modeling of infrared spectroscopy and mass spectrometry data

Braga,

Maciel,

Vaz

et al. 2023

Anal. Methods

View full text Add to dashboard Cite

show abstract

“…Several methods derived from LSM include Partial-least Squares (PLS) and Regularized-least Squares (RLS) with each having varying performance results based on the given scenario. PLS run time is slower than other methods and is only efficient when variable number are more than compound numbers in the data set [47] and RLS is more efficient only when the coefficients are penalized or else it has more run time for same efficiency [48]. This example highlights the importance of the given scenarios and parameters on the performance of the employed algorithm.…”

Section: Precision Of Algorithmsmentioning

confidence: 97%

Challenges and Solutions for Engineering Applications on Smartphones

Khoury,

Kaddaha,

Saade

et al. 2023

Software

View full text Add to dashboard Cite

This paper starts by presenting the concept of a mobile application. A literature review is conducted, which shows that there is still a certain lack with regard to smartphone applications in the domain of engineering as independent simulation applications and not only as extensions of smartphone tools. The challenges behind this lack are then discussed. Subsequently, three case studies of engineering applications for both smartphones and the internet are presented, alongside their solutions to the challenges presented. The first case study concerns an engineering application for systems control. The second case study focuses on an engineering application for composite materials. The third case study focuses on the finite element method and structure generation. The solutions to the presented challenges are then described through their implementation in the applications. The three case studies show a new system of thought concerning the development of engineering smartphone applications.

show abstract

CHEMOMETRICS AND STATISTICS | Multivariate Calibration Techniques

Cited by 18 publications

References 0 publications

Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment

Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment

A rapid and direct method for dating blue pen ink in documents using multiset modeling of infrared spectroscopy and mass spectrometry data

Challenges and Solutions for Engineering Applications on Smartphones

Contact Info

Product

Resources

About