Kohonen and counterpropagation artificial neural networks in analytical chemistry

Zupan, Jure; Novič, Marjana; Ruisánchez, Itziar

doi:10.1016/s0169-7439(97)00030-0

Cited by 258 publications

(164 citation statements)

References 14 publications

Supporting

Mentioning

160

Contrasting

Unclassified

Order By: Relevance

“…Two different splitting methods were applied. The first method involved automated random selection, while the second involved a Kohonen map artificial neural network (ANN) or self-organizing maps (SOM) [13,14]. Due to their clustering capabilities, Kohonen maps ensure that both sets are homogeneously distributed within the entire area of descriptor space.…”

Section: Dataset For Analysismentioning

confidence: 99%

Receptor-guided 3D-QSAR approach for the discovery of c-kit tyrosine kinase inhibitors

2011

View full text Add to dashboard Cite

Studies of the the three-dimensional quantitative structure-activity relationships for ninety-five c-kit tyrosine kinase inhibitors were performed. Based on a cocrystallized compound (1 T46), known inhibitors were aligned with c-kit by induced-fit docking, and multiple training/test set splitting was performed to validate the selected pharmacophore model. The best pharmacophore model consisted of five features: one hydrogen-bond donor and four aromatic rings. Reliable statistics were obtained (R 2 =0.95, R pred 2 =0.75), and the model was validated by using it to select c-kit inhibitors from a database; 82.1% of the hits it retrieved were active. Accordingly, our model can be reliably used to identify new c-kit inhibitors, and can provide useful information when designing new inhibitors.

show abstract

Section: Dataset For Analysismentioning

confidence: 99%

Receptor-guided 3D-QSAR approach for the discovery of c-kit tyrosine kinase inhibitors

2011

View full text Add to dashboard Cite

show abstract

“…Se trata de un sistema de interconexión de neuronas en una red que colabora para producir un estímulo de salida, consistente de dos capas, una capa llamada Kohonen, la cual puede ser usada para el análisis estructural de los datos y una capa de salida. Esta técnica está basada en la búsqueda de similaridades en las muestras y permite proyectarlas en un espacio topológico donde las muestras similares están cerca las unas de las otras y las disímiles aparte (Ver Figura 3) [5], [7], [8].…”

Section: Métodos De Aprendizaje Y Optimizaciónunclassified

“…Esto ocurre cuando las muestras son asignadas a neuronas donde los pesos de la capa de salida son similares, es decir, la neurona no puede ser asignada a una clase específica. Las variables originales son usualmente pretratadas escalándolas en un rango entre 0 y 1 para hacerlas comparables con el peso de las redes [7]. Por otra parte, los algoritmos genéticos (GA) son descritos ampliamente por Leardi y cols.…”

Section: Métodos De Aprendizaje Y Optimizaciónunclassified

See 1 more Smart Citation

Análisis estadistico multivariado como herramienta Estratégica para el Control de procesos de calidad en la industria agroalimentaria

Domínguez

2011

Publ. investig.

View full text Add to dashboard Cite

El uso de técnicas de estadística multivariada para el control de procesos y calidad en la industria agroalimentaria ha venido en crecimiento significativo desde la mitad de los años setenta, como una consecuencia de la revolución informática que facilitó el análisis de matrices de datos de gran tamaño. A diferencia de los métodos univariados de exploración de datos, la estadística multivariada utiliza como gran pilar el análisis de información descrita por tres o más variables que pueden ser estudiadas simultá-neamente y comprendidas de una manera rápida, eficiente y sencilla. Debido al extraordinario avance en las máquinas informáticas, hoy es posible aplicar estas metodologías para resolver problemas extremadamente complejos. Este artículo presenta las técnicas de estadística multivariada más reconocidas, así como la compilación de algunos trabajos que sirven como demostración de su aplicabilidad en el campo de los alimentos. Palabras clave: clasificación, exploración, modelamiento, optimización, regresión AbstractThe use of multivariate statistical techniques for quality and process control in the food industry has been growing significantly since the mid-seventies, as a result of the informatics revolution which facilitated the analysis of large data sets. Unlike univariate methods of data exploration, multivariate statistics uses as a major pillar the analysis of information described by three or more variables that can be simultaneously studied and understood in a fast, efficient and easy way. Thanks to the extraordinary advance in computing machines, it is now possible to apply these methodologies to solve extremely complex problems. This article presents the most recognized multivariate statistical techniques, as well as the compilation of some papers that serve as a demonstration of its applicability in the field of foods.

show abstract

“…Many techniques using Artificial Intelligence have been used in Monitoring and Fault Diagnosis with the purpose to help the nuclear power plants operators, including the Fuzzy Logic [13], Artificial Neural Networks (ANNs) [5] [1], the Group Method of Data Handling (GMDH) [3], Genetic Algorithms (AGs) [11] [5]. The uses of these techniques are justified because it is possible to model the process without using algebraic equations [8], by using only a database which contains the plant information.…”

Section: Introductionmentioning

confidence: 99%

Monitoring and fault detection: a comparative study using computational intelligence techniques

Pereira¹,

Bueno²

2016

Anais Do 11. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Abstract-In this work, two different computational intelligence techniques -Neural Networks and Neuro-fuzzywere used in the development of a Monitoring and Fault Detection system applied to the IEA-R1 experimental nuclear reactor. The monitoring is made by comparing an estimative of the variable generated by the computational intelligence techniques with the actual value. Both techniques have been successfully applied to the Monitoring System and were effective in estimate a monitored variable. The Neuro-Fuzzy technique showed strongly better performance compared with Neural Network.

show abstract

Kohonen and counterpropagation artificial neural networks in analytical chemistry

Cited by 258 publications

References 14 publications

Receptor-guided 3D-QSAR approach for the discovery of c-kit tyrosine kinase inhibitors

Receptor-guided 3D-QSAR approach for the discovery of c-kit tyrosine kinase inhibitors

Análisis estadistico multivariado como herramienta Estratégica para el Control de procesos de calidad en la industria agroalimentaria

Monitoring and fault detection: a comparative study using computational intelligence techniques

Contact Info

Product

Resources

About