The synergistic effect of QR decomposition with t-SNE DOI Open Access
Mohsin Ali, Jitendra Choudhary

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 34(2), P. 1159 - 1159

Published: March 23, 2024

The study utilized non-parametric tests, specifically, the Mann-Whitney U test, to evaluate performance of a proposed model called QRPCA-t-SNE, along with two other models, MDS and UMAP. compared these three models datasets on metrics such as accuracy, training testing mean square error, AUC scores, precision, recall, F1 scores. Once model's was conducted, Anderson-Darling test check for data normality before applying hypothesis proof. analysis revealed that Model 1 (QRPCA-t-SNE) significantly outperformed 2 (UMAP) 3 (MDS) in terms p-values 0.0027 0.0003, respectively. This finding suggests is suitable high-accuracy reliability applications, providing valuable insights into predictive analytics 95% confidence interval (confidence level α= 0.05).

Language: Английский

A framework for optimizing environmental covariates to support model interpretability in digital soil mapping DOI Creative Commons
Babak Kasraei, Margaret G. Schmidt, Jin Zhang

et al.

Geoderma, Journal Year: 2024, Volume and Issue: 445, P. 116873 - 116873

Published: April 4, 2024

A common practice in digital soil mapping (DSM) is to incorporate many environmental covariates into a machine-learning algorithm predict the spatial patterns of attributes. Variance inflation factor (VIF), principal component analysis (PCA), and recursive feature elimination (RFE) are three statistical methods that can be used reduce number covariates. This study aims 1) compare VIF PCA approaches; 2) identify an approach determine minimum DSM ensure model parsimony using RFE after VIF; 3) examine interpret impact on variability predicted properties. The area was province British Columbia (BC), Canada. legacy data for four properties make maps: organic carbon (SOC%), pH, clay%, coarse fragment (CF%). Seven models were made each property influence validation results by different produced various results. showed could reduced from 70 4 12 with only little or no difference concordance correlation coefficient (CCC) CCC pH 7 both 0.74, other properties, this negligible. obtained performance reducing not as effective when VIF. Moreover, related precipitation most important modeling SOC%, clay%. Topographic influential CF%. emphasizes potential benefits combining reduction achieve optimal outcomes generate parsimonious interpretable models.

Language: Английский

Citations

15
Improving model performance in mapping black-soil resource with machine learning methods and multispectral features DOI Creative Commons
Jianfang Hu,

Yulei Tang,

Jiapan Yan

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 7, 2025

Abstract Accurate information on the distribution of regional black-soil resource is one important elements for sustainable management soils. And its results can provide decision makers with robust data that be translated into better making. This study utilized all Sentinel-2 images covering area from April to July in 2022. After masking clouds, were synthesized monthly. Based revised random forest classification algorithm, model performance using different feature combination programs evaluated search an efficient, high-precision method mapping resource. The impact adding temperature, precipitation and slope geographic covariates was analyzed. robustness verified Landsat-8 lower spatial resolution. showed (1) based multi-temporal ensemble features shows best performance, OA 94.6%; (2) temperature covariate effectively improve accuracy mapping; (3) compared sentinel data, reduced but still plausible, verifying model. provides a rapid

Language: Английский

Citations

0
Using long-term bare earth composite image and machine learning in lithological mapping of Adrar Souttouf mafic complex (Oulad Dlim massif, Southern Morocco) DOI

El Houcine El Haous,

Abdelkrim Bouasria, Abdelilah Fekkak

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 101516 - 101516

Published: March 1, 2025

Language: Английский

Citations

0
The synergistic effect of QR decomposition with t-SNE DOI Open Access
Mohsin Ali, Jitendra Choudhary

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 34(2), P. 1159 - 1159

Published: March 23, 2024

The study utilized non-parametric tests, specifically, the Mann-Whitney U test, to evaluate performance of a proposed model called QRPCA-t-SNE, along with two other models, MDS and UMAP. compared these three models datasets on metrics such as accuracy, training testing mean square error, AUC scores, precision, recall, F1 scores. Once model's was conducted, Anderson-Darling test check for data normality before applying hypothesis proof. analysis revealed that Model 1 (QRPCA-t-SNE) significantly outperformed 2 (UMAP) 3 (MDS) in terms p-values 0.0027 0.0003, respectively. This finding suggests is suitable high-accuracy reliability applications, providing valuable insights into predictive analytics 95% confidence interval (confidence level α= 0.05).

Language: Английский

Citations

0