| Web site and design © 2008 by G6G Consulting Group. All Rights Reserved. Most product content has been taken directly from manufacturer's web sites; other product content is assembled by G6G Consulting Group. G6G welcomes any corrections and/or comments. |
Category Intelligent Software>Data Mining Systems/Tools Abstract DataEngine is an intelligent data analysis and data mining software system. By using neural networks, fuzzy logic and statistical methods, DataEngine provides you with the most advanced techniques for data analysis. DataEngine Components/Features include: Data Access - Product offers various options for data access through its flexible import and export interfaces - 1) import and export of Microsoft Excel files; 2) flexible import and export of American Standard Code for Information Interchange (ASCII) files; 3) database interface, including import and export of data via Object Linking and Embedding, Database (OLE DB)/Open Database Connectivity (ODBC), and its 'mapping' feature allows you to transform the values of categorical variables into numerical values; 4) generic 'data acquisition board' support including (analog input and output, trigger and pre-trigger support). Basic Functions - DataEngine supplies basic mathematical, statistical and signal processing functions. Data Analysis & Data Mining - Fuzzy logic and neural networks are the basis of DataEngine's data analysis and data mining power. Fuzzy and neural models developed with DataEngine can be exported using the DataEngine ADL (Application Development Library). Fuzzy Rule Base features are - 1) linguistic If-Then Rules; 2) examples of potential applications are: knowledge-based diagnosis, classification, control and modeling; 3) multi-step inference technique; 4) supports the representation of symbolic and/or linguistic information; 5) fuzzy operators are: minimum, maximum, algebraic product, algebraic sum, gamma operator; 6) defuzzyfying strategies are: mean of maxima, center of gravity and fuzzy output; 7) debugging. Multilayer Perceptron features are - 1) supervised learning neural network; 2) examples of potential applications are: classification, modeling and control; 3) learning rules are: backpropagation, quickpropagation, Super Self Adaptive Backpropagation (SAB), resilent propagation, each with momentum and decay; 4) learning rate decay to avoid overfitting; 5) pruning algorithm for adapting the structure of the neural network architecture; 6) shortcut connections are possible: direct connections of input with output parameters and skipping hidden layers; 7) the 'best' neural network that appears during the training process can be saved automatically and the creation criteria for the 'best' network can also be configured. Kohonen Feature Map features are - 1) unsupervised learning neural network; 2) examples of potential applications are: clustering and classification; 3) labeling by examples; 4) graphical representation of the feature map. Fuzzy C-Means features are - 1) fuzzy clustering algorithm; 2) examples of potential applications are: clustering and classification; 3) initialize algorithm with pre-defined data partitions; 4) labeling by examples; 5) the 'best' number of classes can be determined automatically and the criteria for the 'best' number of classes can also be configured. Fuzzy Kohonen Network features are - 1) unsupervised learning neural network; 2) examples of potential applications are: clustering, classification; 3) very fast fuzzy training algorithm; 4) labeling by examples; 5) graphical representation of the feature map. Model Analysis - An analysis component that supports the validation and the improvement of your models and consists of: 1) Adjustment of operating values - The feature values of objects can be varied and the model's changing outputs can then be displayed. A "slider" software device is provided that can be used to vary the feature values. 2) Transfer function - On the basis of the chosen operating point a transfer function can be computed by varying (automatically) one or two of the features within their value range(s). The resulting function can be visualized as a 2- or 3-dimensional diagram. 3) Sensitivity analysis - On the basis of the chosen operating point a sensitivity analysis can be carried out for the current model. To help assess the sensitivity of the model, three (3) measures are provided. Each one of the measures is computed by varying one of the feature values. These measures are: 1) the minimum and maximum values of an output variable can be (shown as a hi-lo-close-plot); 2) the graph of an output variable can be (shown as a set of curves); 3) the cumulative derivation of an output variable can be (shown as a bar diagram). Test error - In addition to the test evaluations that currently exist in the model editors several additional error measures can also be calculated. Matrix of confusion - For classification tasks a 'matrix of confusion' is computed to determine what types of misclassifications exist in the test data. Visualization - The 2D and 3D charting module facilitates the interpretation of data analysis results and delivers presentation-style graphics for your reports. This module is available throughout DataEngine. DataEngine PlugIns - DataEngine capabilities can be extended by the user via user-defined function blocks. A Dynamic Link Library (DLL) based PlugIn interface enables you to integrate your own analysis tools into DataEngine in a simple and effective way. Cards - DataEngine's Cards provide a graphical macro language that can be used for the automation of data analysis procedures.
B) complete integration with the Microsoft Windows operating system C) An OLE interface allows you to configure the models and to perform the training/labeling/testing from within other programs (e.g. for Windows-based data analysis applications).
Microsoft Windows 2000 Terminal Server Manufacturer Home office; see web site for international distributors.
Pascalstraße 69 52076 Aachen, Germany software@mitgmbh.de by fax +49 2408 94582 by phone +49 2408 94580
Price DataEngine Server License Server version for MS Windows 2000 Terminal Server incl. 3 Clients* Euro 35.000,- DataEngine Workstation License Euro 8.000.- DataEngine ADL for Win95/98 or NT Euro 1.500.- DataEngine V.i Euro 2.500.- G6G Product Number 20042 G6G Manufacturer Number 101714 |
| The G6G Directory of Omics and Intelligent Software |
|
|