scholarly journals Determination of composition of mixed biological samples using laser-induced fluorescence and combined classification/regression models

2021 ◽  
Vol 136 (11) ◽  
Author(s):  
Lea Fellner ◽  
Marian Kraus ◽  
Arne Walter ◽  
Frank Duschek ◽  
Thomas Bocklitz ◽  
...  
Keyword(s):  
Neural Networks ◽  
Experimental Design ◽  
Regression Models ◽  
Laser Induced Fluorescence ◽  
Classification Algorithms ◽  
Excellent Performance ◽  
Classification And Regression ◽  
Mixed Samples

AbstractLaser-induced fluorescence (LIF) provides the ability to distinguish organic materials by a fast and distant in situ analysis. When detecting the substances directly in the environment, e.g., in an aerosol cloud or on surfaces, additional fluorescence signals of other fluorophores occurring in the surrounding are expected to mix with the desired signal. We approached this problem with a simplified experimental design for an evaluation of classification algorithms. An upcoming question for enhanced identification capabilities is the case of mixed samples providing different signals from different fluorophores. For this work, mixtures of up to four common fluorophores (NADH, FAD, tryptophan and tyrosine) were measured by a dual-wavelength setup and spectrally analyzed. Classification and regression are conducted with neural networks and show an excellent performance in predicting the ratios of the selected ingredients.

scholarly journals Neural networks and principle component analysis approaches to predict pile capacity in sand

2018 ◽  
Vol 149 ◽  
pp. 02025 ◽  
Author(s):  
A Benali ◽  
A Nechnech ◽  
B Boukhatem ◽  
M N Hussein ◽  
M Karry
Keyword(s):  
Neural Networks ◽  
Bearing Capacity ◽  
Driven Piles ◽  
In Situ Tests ◽  
Pile Capacity ◽  
Significant Development ◽  
Pca Method ◽  
Main Component

Determination of pile bearing capacity from the in-situ tests has developed considerably due to the significant development of their technology. The project presented in this paper is a combination of two approaches, artificial neural networks and main component analyses that allow the development of a neural network model that provides a more accurate prediction of axial load bearing capacity based on the SPT test data. The retropropagation multi-layer perceptron with Bayesian regularization (RB) was used in this model. This was established by the incorporation of about 260 data, obtained from the published literature, of experimental programs for large displacement driven piles. The PCA method is proposed for compression and suppression of the correlation between these data. This will improve the performance of generalization of the model.

Data mining in manufacturing: Significance analysis of process parameters

2008 ◽  
Vol 222 (11) ◽  
pp. 1503-1516 ◽  
Author(s):  
M Perzyk ◽  
R Biernacki ◽  
J Kozlowski
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Process Parameters ◽  
Regression Models ◽  
Simulated Data ◽  
Real Data ◽  
Support Vector ◽  
Data Sets ◽  
Interaction Factors

Determination of the most significant manufacturing process parameters using collected past data can be very helpful in solving important industrial problems, such as the detection of root causes of deteriorating product quality, the selection of the most efficient parameters to control the process, and the prediction of breakdowns of machines, equipment, etc. A methodology of determination of relative significances of process variables and possible interactions between them, based on interrogations of generalized regression models, is proposed and tested. The performance of several types of data mining tool, such as artificial neural networks, support vector machines, regression trees, classification trees, and a naïve Bayesian classifier, is compared. Also, some simple non-parametric statistical methods, based on an analysis of variance (ANOVA) and contingency tables, are evaluated for comparison purposes. The tests were performed using simulated data sets, with assumed hidden relationships, as well as on real data collected in the foundry industry. It was found that the performance of significance and interaction factors obtained from regression models, and, in particular, neural networks, is satisfactory, while the other methods appeared to be less accurate and/or less reliable.

scholarly journals Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training

2021 ◽  
Author(s):  
Anna-Kathrin Kopetzki ◽  
Stephan Günnemann
Keyword(s):  
Neural Networks ◽  
Regression Models ◽  
State Of The Art ◽  
Robustness Analysis ◽  
Reachable Set ◽  
Reachable Sets ◽  
Feature Ranking ◽  
Training Procedure ◽  
Classification And Regression ◽  
Norm Bound

AbstractNeural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and reliability of predictions. We answer these questions by computing reachable sets of neural networks, i.e. sets of outputs resulting from continuous sets of inputs. We provide two efficient approaches that lead to over- and under-approximations of the reachable set. This principle is highly versatile, as we show. First, we use it to analyze and enhance the robustness properties of both classifiers and regression models. This is in contrast to existing works, which are mainly focused on classification. Specifically, we verify (non-)robustness, propose a robust training procedure, and show that our approach outperforms adversarial attacks as well as state-of-the-art methods of verifying classifiers for non-norm bound perturbations. Second, we provide techniques to distinguish between reliable and non-reliable predictions for unlabeled inputs, to quantify the influence of each feature on a prediction, and compute a feature ranking.

scholarly journals DINÂMICA DO BULBO MOHADO NO SOLO POR MEIO DA IRRIGAÇÃO POR GOTEJAMENTO EM PERIMETROS IRRIGADOS DO SUBMÉDIO DO VALE DO SÃO FRANCISCO

Irriga ◽  
2015 ◽  
Vol 1 (2) ◽  
pp. 95-102
Author(s):  
ARMANDO BAGAGI BEZERRA ◽  
Luis Fernando S. M. Campeche
Keyword(s):  
Experimental Design ◽  
San Francisco ◽  
Flow Rate ◽  
Regression Models ◽  
Irrigation Management ◽  
Equation Model ◽  
Maximum Diameter ◽  
Application Range ◽  
Surface Diameter

DINÂMICA DO BULBO MOHADO NO SOLO POR MEIO DA IRRIGAÇÃO POR GOTEJAMENTO EM PERIMETROS IRRIGADOS DO SUBMÉDIO DO VALE DO SÃO FRANCISCO  ARMANDO BAGAGI BEZERRA1 E LUIS FERNANDO S. M. CAMPECHE2 1 Engenheiro Agrônomo, Mestrando em engenharia da água e solo, Universidade Federal do Vale do São Francisco-UNIVASF, [email protected] Engenheiro Agrônomo, Professor titular Irrigação e Drenagem, Instituto Federal do Sertão Pernambucano – IF SERTÃO, [email protected]  1 RESUMO Foi realizado a determinação em campo das dimensões do bulbo molhado do solo por meio da irrigação por gotejamento, sendo analisadas as variáveis, diâmetro superficial, diâmetro máximo, profundidade do diâmetro máximo e profundidade máxima do bulbo molhado em seis tipos de solos no sub médio do vale do são Francisco, entre eles, Argissolo Vermelho Amarelo textura franco-siltoso (PVA), Argissolo Vermelho Amarelo textura franco-arenoso (PVAe), associação de Argissolo Vermelho Amarelo e Latossolo textura franco-arenoso (PVA/Aed), associação de Cambissolo e Neossolo textura franco-arenoso (CYn), associação de Argissolo Amarelo e Argissolo Vermelho Amarelo textura franco-arenoso (PAed) e Vertissolo textura franco-argiloso (VGn). Os tratamentos tiveram cinco gotejadores entre as vazões de 1 L h-1, 1,5 L h-1, 2,0 L h-1, 3,0 L h-1 e 4,0 L h-1, em intervalo de aplicação entre 1 h e 10 h. O delineamento experimental ocorreu em blocos casualisados em três repetições, em faixa. As determinações em campo possibilitaram a determinação de modelos de regressão do tipo potencial, em função do tempo e do volume para todas as variáveis, além da determinação do espaçamento entre emissores em função do diâmetro máximo do bulbo molhado do solo. O coeficiente ´´a`` da equação do modelo potencial aumentou com o aumento da vazão do gotejador no mesmo tempo de aplicação, ou seja, o bulbo molhado aumenta com o incremento da vazão aplicada e os maiores espaçamentos entre emissores ocorreram nos solos com maiores teores de argila. Palavras – chave: Semiárido, manejo da irrigação, espaçamento entre gotejadores. BEZERRA, A. B.; CAMPECHE, L. F. S. M.DYNAMICS BUBLO MOHADO GROUND THROUGH IRRIGATION DRIPPING IN IRRIGATED SUB SÃO FRANCISCO VALLEY MIDDLE   2 ABSTRACT This was the determination to field the size of the wet soil bulb through drip irrigation , and analyzed the variables , surface diameter , maximum diameter , depth of maximum diameter and maximum depth of the wet bulb in six soils in the medium sub of the San Francisco valley. The treatments had five emitters of 1,0 L h-1 , 1.5 L h-1 , 2.0 L h-1 , 3.0 L h-1  and 4.0 L h-1, application range from 1 h to 10 h. The experimental design was randomized blocks in three replications, and the vent to plot and time the sub plot The measurements enabled the field type determining potential regression models , depending on the time and volume for all variables in addition to the determination of the emitter spacing as a function of maximum wet soil bulb diameter. The ''a`` coefficient equation model of the potential increased with the emitter of the application flow at the same time , that is , wet bulb increases with increasing flow rate and applied greater spacing between emitters occurred in soils with a higher content of clay  KEYWORDS: Semiarid, irrigation management, spacing between drippers. 

Sign in / Sign up

Export Citation Format

Share Document