A new library to combine artificial neural networks and support vector machines with statistics and a database engine for application in environmental modeling

Authors:
Ralf Wieland;Wilfried Mirschel;Bernd Zbell;Karin Groth;Alison Pechenick;Kyoko Fukuda
Affiliations:
Leibniz-Center for Agricultural Landscape Research, Institute of Landscape Systems Analysis, Eberswalder Street 84, 15374 Muencheberg, Germany;Leibniz-Center for Agricultural Landscape Research, Institute of Landscape Systems Analysis, Eberswalder Street 84, 15374 Muencheberg, Germany;Leibniz-Center for Agricultural Landscape Research, Institute of Landscape Systems Analysis, Eberswalder Street 84, 15374 Muencheberg, Germany;Leibniz-Center for Agricultural Landscape Research, Institute of Landscape Systems Analysis, Eberswalder Street 84, 15374 Muencheberg, Germany;College of Engineering and Mathematical Sciences, University of Vermont 351 Votey Hall, Burlington, VT 05405, USA;Department of Mathematics and Statistics, Department of Computer Science and Software Engineering, University of Canterbury, Private Bag 4800, Christchurch, New Zealand
Venue:
Environmental Modelling & Software
Year:
2010

Citing 11
Cited 2

Inference for the Generalization Error

Machine Learning
Early Stop Criterion from the Bootstrap Ensemble

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4 - Volume 4
Information Theory, Inference & Learning Algorithms

Information Theory, Inference & Learning Algorithms
Exploring the ecological status of human altered streams through Generative Topographic Mapping

Environmental Modelling & Software
Adaptive fuzzy modeling versus artificial neural networks

Environmental Modelling & Software
Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application

Environmental Modelling & Software
Prediction of urban stormwater quality using artificial neural networks

Environmental Modelling & Software
Modeling with Data: Tools and Techniques for Scientific Computing

Modeling with Data: Tools and Techniques for Scientific Computing
GNU Scientific Library Reference Manual - Third Edition

GNU Scientific Library Reference Manual - Third Edition
The relative utility of regression and artificial neural networks models for rapidly predicting the capacity of water supply reservoirs

Environmental Modelling & Software
A Primer of Ecology with R

A Primer of Ecology with R

Modeling net ecosystem metabolism with an artificial neural network and Bayesian belief network

Environmental Modelling & Software
A new method for semi-automatic fuzzy training and its application in environmental modeling

Environmental Modelling & Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

SADATO (SAMT DAta TOol) is an open source software library presenting new possibilities in modeling based on artificial neural networks and support vector machines. The main advantage of SADATO is its central data management based on Sqlite3 or MySQL and the statistical functions inherited from the APOPHENIA software. SADATO can be used for modeling as well as in large simulations. Modeling is demonstrated with two examples of artificial neural networks and support vector machines. The use of SADATO in simulation is supported by its very high computation speed. The highly aggregated functions in SADATO keep the software simple and easy to maintain. This allows the scientist experienced in software development easy access to all methods provided by SADATO. Additionally, an easy-to-use graphical user interface was developed to support scientists in developing models without any special knowledge in computer science.