Laser-induced breakdown spectroscopy spectral feature selection to enhance classification capabilities: A t-test filter approach

Huffman, Curtis; Sobral, H.; Terán-Hinojosa, E.

doi:10.1016/j.sab.2019.105721

Cited by 14 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature selection can be performed in a number of ways, ranging from methods such as t tests (Chu, Hsu, Chou, Bandettini, & Lin, 2012; Huffman, Sobral, & Teran‐Hinojosa, 2019; Wang, 2012; Wang, Zhang, Liu, Lv, & Wang, 2014; Zhou & Wang, 2007) to more complex methods utilizing PCA, mutual information, L1 norms, regression [such as LASSO (Zhao & Yu, 2006) and AdaBoost (Wang, 2012)], and so on. Our current choice of using the t test as a way to rank and select the most separable features is a standard method in the field as evidenced by existing literature (Damoulas & Girolami, 2008b; Shawe‐Taylor & Cristianini, 2004; Varol, Gaonkar, Erus, Schultz, & Davatzikos, 2012).…”

Section: Discussionmentioning

confidence: 99%

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Popuri

Wang

et al. 2020

Human Brain Mapping

View full text Add to dashboard Cite

Biomarkers for dementia of Alzheimer's type (DAT) are sought to facilitate accurate prediction of the disease onset, ideally predating the onset of cognitive deterioration. T1‐weighted magnetic resonance imaging (MRI) is a commonly used neuroimaging modality for measuring brain structure in vivo, potentially providing information enabling the design of biomarkers for DAT. We propose a novel biomarker using structural MRI volume‐based features to compute a similarity score for the individual's structural patterns relative to those observed in the DAT group. We employed ensemble‐learning framework that combines structural features in most discriminative ROIs to create an aggregate measure of neurodegeneration in the brain. This classifier is trained on 423 stable normal control (NC) and 330 DAT subjects, where clinical diagnosis is likely to have the highest certainty. Independent validation on 8,834 unseen images from ADNI, AIBL, OASIS, and MIRIAD Alzheimer's disease (AD) databases showed promising potential to predict the development of DAT depending on the time‐to‐conversion (TTC). Classification performance on stable versus progressive mild cognitive impairment (MCI) groups achieved an AUC of 0.81 for TTC of 6 months and 0.73 for TTC of up to 7 years, achieving state‐of‐the‐art results. The output score, indicating similarity to patterns seen in DAT, provides an intuitive measure of how closely the individual's brain features resemble the DAT group. This score can be used for assessing the presence of AD structural atrophy patterns in normal aging and MCI stages, as well as monitoring the progression of the individual's brain along with the disease course.

show abstract

Section: Discussionmentioning

confidence: 99%

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Popuri

Wang

et al. 2020

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…Therefore, the characteristics and functions of these features in the classications were not exactly the same, especially the morphological features of the spectrum, which were not weaker than the traditional spectral intensity features. 29,47 Based on the above results, we have reason to believe that these different kinds of features contain different and valuable information. 48 Fusion and reconstruction using specic methods can positively improve the classication accuracy.…”

Section: Classication Using a Single Type Of Featurementioning

confidence: 95%

A polynomial interactive reconstruction method based on spectral morphological features for the classification of gem minerals using portable LIBS

Yan

Qin

et al. 2022

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

“…As a result, a prediction model is produced as an ensemble of weak prediction models. Every step evaluates the model values at each training data point, using the residuals of previous steps to minimize the loss function [ 50 ]. A GBM utilizes the best practices to avoid overfitting the classification machine.…”

Section: Methodsmentioning

confidence: 99%

“…Averaging the improvements made by each variable over every tree that uses that variable follows. In the split criterion, the variables with the greatest average decrease are listed as the most significant [ 50 ].When it comes to GBM modeling, there are a variety of tuning parameters available. The following variables were used in this study: (boosting_type = ‘gbdt’, num_leaves = 31, max_depth = −1, learning_rate = 0.1, n_estimators = 100).…”

Section: Methodsmentioning

confidence: 99%

Heavy Metal Detection in Fritillaria thunbergii Using Laser-Induced Breakdown Spectroscopy Coupled with Variable Selection Algorithm and Chemometrics

Kabir

Guindo

Chen

et al. 2023

Foods

View full text Add to dashboard Cite

Environmental and health risks associated with heavy metal pollution are serious. Human health can be adversely affected by the smallest amount of heavy metals. Modeling spectrum requires the careful selection of variables. Hence, simple variables that have a low level of interference and a high degree of precision are required for fast analysis and online detection. This study used laser-induced breakdown spectroscopy coupled with variable selection and chemometrics to simultaneously analyze heavy metals (Cd, Cu and Pb) in Fritillaria thunbergii. A total of three machine learning algorithms were utilized, including a gradient boosting machine (GBM), partial least squares regression (PLSR) and support vector regression (SVR). Three promising wavelength selection methods were evaluated for comparison, namely, a competitive adaptive reweighted sampling method (CARS), a random frog method (RF), and an uninformative variable elimination method (UVE). Compared to full wavelengths, the selected wavelengths produced excellent results. Overall, RC2, RV2, RP2, RSMEC, RSMEV and RSMEP for the selected variables are as follows: 0.9967, 0.8899, 0.9403, 1.9853 mg kg−1, 11.3934 mg kg−1, 8.5354 mg kg−1; 0.9933, 0.9316, 0.9665, 5.9332 mg kg−1, 18.3779 mg kg−1, 11.9356 mg kg−1; 0.9992, 0.9736, 0.9686, 1.6707 mg kg−1, 10.2323 mg kg−1, 10.1224 mg kg−1 were obtained for Cd Cu and Pb, respectively. Experimental results showed that all three methods could perform variable selection effectively, with GBM-UVE for Cd, SVR-RF for Pb, and GBM-CARS for Cu providing the best results. The results of the study suggest that LIBS coupled with wavelength selection can be used to detect heavy metals rapidly and accurately in Fritillaria by extracting only a few variables that contain useful information and eliminating non-informative variables.

show abstract

Laser-induced breakdown spectroscopy spectral feature selection to enhance classification capabilities: A t-test filter approach

Cited by 14 publications

References 42 publications

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

A polynomial interactive reconstruction method based on spectral morphological features for the classification of gem minerals using portable LIBS

Heavy Metal Detection in Fritillaria thunbergii Using Laser-Induced Breakdown Spectroscopy Coupled with Variable Selection Algorithm and Chemometrics

Contact Info

Product

Resources

About