Sparse Partial Least Squares Classification for High Dimensional Data

Chung, Dongjun; Keleş, Sündüz

doi:10.2202/1544-6115.1492

Cited by 162 publications

(161 citation statements)

References 24 publications

Supporting

Mentioning

161

Contrasting

Order By: Relevance

“…To analyze the full spectrum, we chose sparse Partial Least Square Discriminant Analysis (sPLSDA) [69] and High-Dimensional Discriminant Analysis (HDDA) [28]. HDDA is a relatively new classifier [28,70] designed for high dimensional datasets.…”

Section: Classificationmentioning

confidence: 99%

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

et al. 2016

View full text Add to dashboard Cite

Hyperspectral remote sensing is an effective tool to discriminate plant species, providing vast potential to trace plant invasions for ecological assessments. However, necessary baseline information for the use of remote sensing data is missing for many high-impact invaders. Furthermore, the identification of the suitable classification algorithms and spectral regions for successfully classifying species remains an open field of research. Here, we tested the separability of the invasive tree Acacia longifolia from adjacent exotic and native vegetation in a Natura 2000 protected Mediterranean dune ecosystem. We used continuous visible, near-infrared and short wave infrared (VNIR-SWIR) data as well as vegetation indices at the leaf and canopy level for classification, comparing five different classification algorithms. We were able to successfully distinguish A. longifolia from surrounding vegetation based on vegetation indices. At the leaf level, radial-basis function kernel Support Vector Machine (SVM) and Random Forest (RF) achieved both a high Sensitivity (SVM: 0.83, RF: 0.78) and a high Positive Predicted Value (PPV) (0.86, 0.83). At the canopy level, RF was the classifier with an optimal balance of Sensitivity (0.75) and PPV (0.75). The most relevant vegetation indices were linked to the biochemical parameters chlorophyll, water, nitrogen, and cellulose as well as vegetation cover, which is in line with biochemical and ecophysiological properties reported for A. longifolia. Our results highlight the potential to use remote sensing as a tool for an early detection of A. longifolia in Mediterranean coastal ecosystems.

show abstract

Section: Classificationmentioning

confidence: 99%

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Class membership of each variable is then assigned by reference cell coding the response matrix (Y) with dummy variables. 35 Y is assumed to be one of the classes (G þ 1) indicated by 0;1; : : : ; G. The recoded response matrix is then defined as an n × ðG þ 1Þ matrix with:…”

Section: Sparse Partial Least Squares Discriminant Analysismentioning

confidence: 99%

“…After constructing latent components, the final step required in SPLS-DA is to fit a classifier since the number of latent components (K) is generally smaller than n. For this purpose, linear classifiers such as linear discriminant analysis (LDA) are commonly utilized. 35 …”

Section: Sparse Partial Least Squares Discriminant Analysismentioning

confidence: 99%

“…20 In the case of SPLS-DA, there are only two key tuning parameters that require optimization for ideal model performance. 35,46 These include the number of latent components "k" and a sparsity thresholding parameter "eta" that can be optimized using CV. While "k" largely depends on the number of variables and sample size it has been recommended to search for components between 1 and 10 with a thresholding parameter ranging between 0 and 1.…”

Section: Optimizing Pls-da and Spls-damentioning

confidence: 99%

“…Nonetheless, certain studies have extended the PLS approach to impose sparseness within the technique for the combined purpose of variable selection and dimension reduction. 35 Designed explicitly for optimal group discrimination in highdimensional settings, SPLS-DA effectively overcomes the problem of being affected by a large number of predictors. 35 This ability makes SPLS-DA well suited for analyzing highdimensional data and for selecting important variables when classifying features of interest.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Does simultaneous variable selection and dimension reduction improve the classification ofPinusforest species?

Peerbhay

Mutanga

Ismail

2014

J. Appl. Remote Sens

View full text Add to dashboard Cite

Abstract. Tree species information is important for forest inventory management and supports decisions related to the composition and distribution of forest resources. However, traditional methods of obtaining such information involve time consuming and cost intensive ground-based methods. Hyperspectral data offer an alternative source for obtaining information related to forest inventory. Utilizing Airborne Imaging Spectrometer for Applications Eagle hyperspectral data (393 to 994 nm), this study compares the utility of two partial least squares (PLS)-based methods for the classification of three commercial Pinus tree species. Results indicate that the sparse partial least squares discriminant analysis (SPLS-DA) method performed variable selection and dimension reduction successfully to produce an overall accuracy of 80.21%. In comparison, the PLS-DA method and variable importance in the projection (VIP) selected bands produced an overall accuracy of 71.88%. The most effective bands selected by PLS-DA and VIP coincided within the visible region of the spectrum (393 to 700 nm). However, SPLS-DA selected fewer wavebands within the blue (415 to 483 nm), green (515 to 565 nm), and red regions (674 to 694 nm) to confirm the importance of the visible in discriminating tree species. Overall, this study shows the potential of SPLS-DA to perform simultaneous variable selection and dimension reduction of hyperspectral remotely sensed data resulting in improved classification accuracies. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Neurocognitive Analysis of Low-level Arsenic Exposure and Executive Function Mediated by Brain Anomalies Among Children, Adolescents, and Young Adults in India

Vaidya,

Holla,

Heron

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceArsenic, a contaminant of groundwater and irrigated crops, is a global public health hazard. Exposure to low levels of arsenic through food extends well beyond the areas with high arsenic content in water.ObjectiveTo identify cognitive impairments following commonly prevalent low-level arsenic exposure and characterize their underlying brain mechanisms.Design, Setting, and ParticipantsThis multicenter population-based cohort study analyzed cross-sectional data of the Indian Consortium on Vulnerability to Externalizing Disorders and Addictions (cVEDA) cohort, recruited between November 4, 2016, and May 4, 2019. Participants aged 6 to 23 years were characterized using deep phenotyping measures of behavior, neuropsychology, psychopathology, brain neuroimaging, and exposure to developmental adversities and environmental neurotoxins. All analyses were performed between June 1, 2020, and December 31, 2021.ExposureArsenic levels were measured in urine as an index of exposure.Main Outcomes and MeasuresExecutive function measured using the cVEDA neuropsychological battery, gray matter volume (GMV) from T1-weighted magnetic resonance imaging, and functional network connectivity measures from resting state functional magnetic resonance imaging.ResultsA total of 1014 participants aged 6 to 23 years (589 male [58.1%]; mean [SD] age, 14.86 [4.79] years) were included from 5 geographic locations. Sparse-partial least squares analysis was used to describe a negative association of arsenic exposure with executive function (r = −0.12 [P = 5.4 × 10−4]), brain structure (r = −0.20 [P = 1.8 × 10−8]), and functional connectivity (within network, r = −0.12 [P = 7.5 × 10−4]; between network, r = −0.23 [P = 1.8 × 10−10]). Alterations in executive function were partially mediated by GMV (b = −0.004 [95% CI, −0.007 to −0.002]) and within-network functional connectivity (b = −0.004 [95% CI, −0.008 to −0.002]). Socioeconomic status and body mass index moderated the association between arsenic and GMV, such that the association was strongest in participants with lower socioeconomic status and body mass index.Conclusions and RelevanceThe findings of this cross-sectional study suggest that low-level arsenic exposure was associated with alterations in executive functioning and underlying brain correlates. These results indicate potential detrimental consequences of arsenic exposure that are below the currently recommended guidelines and may extend beyond endemic risk areas. Precision medicine approaches to study global mental health vulnerabilities highlight widespread but potentially modifiable risk factors and a mechanistic understanding of the impact of low-level arsenic exposure on brain development.

show abstract

Sparse Partial Least Squares Classification for High Dimensional Data

Cited by 162 publications

References 24 publications

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

Does simultaneous variable selection and dimension reduction improve the classification ofPinusforest species?

Neurocognitive Analysis of Low-level Arsenic Exposure and Executive Function Mediated by Brain Anomalies Among Children, Adolescents, and Young Adults in India

Contact Info

Product

Resources

About