Machine Learning Methodology for Management of Shipbuilding Master Data

Jeong, Ju Hyeon; Woo, Jong Hun; Park, Jung Goo

doi:10.1016/j.ijnaoe.2020.03.005

Cited by 25 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second, root-mean-square log error (RMSLE), applies more weight to outliers than the MAE, while also penalizing grab samples with concentrations below the composite value more than those above it (eq S2). , The results of the calculations used to compare the scales of flow are listed in Table (eqs S1–S4).…”

Section: Discussionmentioning

confidence: 99%

Impact of Sampling Type, Frequency, and Scale of the Collection System on SARS-CoV-2 Quantification Fidelity

George

Kaya

Layton³

et al. 2022

Environ. Sci. Technol. Lett.

View full text Add to dashboard Cite

With the rapid onset of the COVID-19 pandemic, wastewater-based epidemiology sampling methodologies for SARS-CoV-2 were often implemented quickly and may not have considered the unique drainage catchment characteristics. This study assessed the impact of grab versus composite sampling on the detection and quantification of SARS-CoV-2 in four different catchment scales with flow rates ranging from high flow (wastewater treatment plant influent) to medium flow (neighborhood scale) to low-flow (city block scale) to ultralow flow (building scale). At the high-flow site, grab samples were comparable to 24 h composite samples with SARS-CoV-2 detected in all samples and differed in concentration from the composite by <1 log 10 unit. However, as the size of the catchment decreased, the percentage of negative grab samples increased despite all respective composites being positive, and the SARS-CoV-2 concentrations of grab samples varied from those of the composites by up to almost 2 log 10 units. At the ultra-low-flow site, increased sampling frequencies generated composite samples with higher fidelity to the 5 min composite, which is the closest estimate of the true SARS-CoV-2 composite concentration that could be measured. Thus, composite sampling is more likely to compensate for temporal signal variability while grab samples do not, especially as the catchment basin size decreases.

show abstract

Section: Discussionmentioning

confidence: 99%

Impact of Sampling Type, Frequency, and Scale of the Collection System on SARS-CoV-2 Quantification Fidelity

George

Kaya

Layton³

et al. 2022

Environ. Sci. Technol. Lett.

View full text Add to dashboard Cite

show abstract

“…To evaluate the performance of the prediction model, the statistical parameters including score-variance (Var-score) [28], max error (MaxE) [29], mean absolute error (MAE) [30], mean squared error (MSE) [31], coefficient of determination (R 2 ) [32], median absolute error (MedAE) [33] and mean squared logarithmic error (MSLE) [34] were used. Consider that the expected outputs for a given variable are Y i , for i ranging in the number of samples, n, and consider that X i represents the corresponding estimated values.…”

Section: Evaluation Of the Performance Of The Methods For The Estimation Of Nitrogen In Cucumbermentioning

confidence: 99%

One-Dimensional Convolutional Neural Networks for Hyperspectral Analysis of Nitrogen in Plant Leaves

et al. 2021

View full text Add to dashboard Cite

Accurately determining the nutritional status of plants can prevent many diseases caused by fertilizer disorders. Leaf analysis is one of the most used methods for this purpose. However, in order to get a more accurate result, disorders must be identified before symptoms appear. Therefore, this study aims to identify leaves with excessive nitrogen using one-dimensional convolutional neural networks (1D-CNN) on a dataset of spectral data using the Keras library. Seeds of cucumber were planted in several pots and, after growing the plants, they were divided into different classes of control (without excess nitrogen), N30% (excess application of nitrogen fertilizer by 30%), N60% (60% overdose), and N90% (90% overdose). Hyperspectral data of the samples in the 400–1100 nm range were captured using a hyperspectral camera. The actual amount of nitrogen for each leaf was measured using the Kjeldahl method. Since there were statistically significant differences between the classes, an individual prediction model was designed for each class based on the 1D-CNN algorithm. The main innovation of the present research resides in the application of separate prediction models for each class, and the design of the proposed 1D-CNN regression model. The results showed that the coefficient of determination and the mean squared error for the classes N30%, N60% and N90% were 0.962, 0.0005; 0.968, 0.0003; and 0.967, 0.0007, respectively. Therefore, the proposed method can be effectively used to detect over-application of nitrogen fertilizers in plants.

show abstract

“…The first, mean absolute error (MAE), quantifies the average discrepancy between the SARS-CoV-2 concentrations observed in the grab samples versus the composite sample at each site (Equation 2, Supporting Information). The second, root mean square log error (RMSLE), applies more weight to outliers than the MAE, while also penalizing grab samples with concentrations below the composite value more than those above it (Equation 3, Supporting Information) 17,18 .…”

Section: Effect Of Sampling Type On Quantification Of Sars-cov-2mentioning

confidence: 99%

The Impact of Sampling Type, Frequency and Scale of Collection System on SARS-CoV-2 Quantification Fidelity

George

Kaya

Layton³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid onset of the COVID-19 pandemic, wastewater-based epidemiology (WBE) sampling methodologies for SARS-CoV-2 were often implemented quickly and may not have taken the unique drainage catchment characteristics into account. One question of debate is the relevance of grab versus composite samples when surveying for SARS-CoV-2 at various catchment scales. This study assessed the impact of grab versus composite sampling on the detection and quantification of SARS-CoV-2 in catchment basins with flow rates ranging from high-flow (wastewater treatment plant influent), to medium-flow (neighborhood-scale micro-sewershed), to low-flow (city block-scale micro-sewershed) and down to ultra-low flow (building scale). At the high-flow site, grab samples were reasonably comparable to 24-h composite samples with the same non-detect rate (0%) and SARS-CoV-2 concentrations that differed by 32% on the Log10 scale. However, as the flow rates decreased, the percentage of false-negative grab samples increased up to 44% and the SARS-CoV-2 concentrations of grab samples varied by up to 1-2 orders of magnitude compared to their respective composite sample concentrations. At the ultra-low-flow site, increased sampling frequencies down to every 5 min led to composite samples with higher fidelity to the SARS-CoV-2 load. Thus, composite sampling is superior to grab sampling, especially as flow decreases.SynopsisThe need for composite sampling to generate reliable SARS-CoV-2 wastewater based epidemiology results increases as the collection basin scale decreases.Table of Content Art

show abstract

Machine Learning Methodology for Management of Shipbuilding Master Data

Cited by 25 publications

References 6 publications

Impact of Sampling Type, Frequency, and Scale of the Collection System on SARS-CoV-2 Quantification Fidelity

Impact of Sampling Type, Frequency, and Scale of the Collection System on SARS-CoV-2 Quantification Fidelity

One-Dimensional Convolutional Neural Networks for Hyperspectral Analysis of Nitrogen in Plant Leaves

The Impact of Sampling Type, Frequency and Scale of Collection System on SARS-CoV-2 Quantification Fidelity

Contact Info

Product

Resources

About