KnowledgeMiner® Classic

Category Intelligent Software>Data Mining Systems/Tools, Intelligent Software>Fuzzy Logic Systems/Tools and Intelligent Software>Neural Network Systems/Tools

Abstract KnowledgeMiner Classic is a data mining tool that enables anyone to use its unique form of modeling to quickly visualize new possibilities. It is an artificial intelligence tool designed to easily extract hidden knowledge from data.

It was built on the cybernetic principles of self-organization: Learning a completely unknown relationship between output and input of any given system in an evolutionary way from a very simple organization to an optimally complex one. Products features/capabilities include:

The main advantages of the inductive KnowledgeMiner approach are:

1) Only minimal, uncertain a priori information about the system is required. That means, even if you have No experience in modeling, data analysis or designing a neural network (NN) you will be able to model, analyze and predict complex relationships of nearly any kind of system.

2) A very fast and effective learning process for a personal computer. That means you can solve problems on your desktop in a reasonable time which you may have never thought possible.

3) Modeling short and noisy data samples. That means, you can deal with a problem as is and don't have to construct artificial conditions for your modeling method to get it work.

4) Output of an optimally complex model. Generally you can be sure to get a model at the end of the automated modeling process which can be expected Not to be over-fitted. Over-fitted models are Not able to predict inherent relationships between variables.

5) Output of an analytical model as a transparent explanation component. That means, you can evaluate the analytical model to explain the obtained results immediately after modeling.

KnowledgeMiner Classic works via three (3) advanced inductive learning modeling algorithms:

1) Self-organizing Networks of Active Neurons (SONAN; also known as GMDH Networks - see below...) --

This method creates parametric time series models, static or dynamic input-output models and predictable systems of equations. Up to 500 input variables could be considered for model creation, whereby at least 6 data samples are needed for each variable. The network structure is Not predefined.

GMDH -- Group Method of Data Handling. It is an inductive, statistical learning network technology using the cybernetical approach of self-organization including systems, information and control theory and computer science. GMDH is Not a traditional statistical modeling method. It is an interdisciplinary approach to overcome some of the main disadvantages of statistics and Neural Networks (NNs).

2) Self-Organizing Fuzzy Rule Induction (FRI) --

Working much like Self-organizing Networks of Active Neurons, this method generates fuzzy rules from fuzzy or Boolean data. Using fuzzy variables like negative, positive or medium, the generated rules are composed of several AND, OR, NOT operators, and they show natural language-like descriptive power.

3) Analog Complexing (AC) --

Analog Complexing is a multi-dimensional pattern search method that can be used for clustering, classifying, and predicting most fuzzy objects. For prediction, for example, it self-selects several similar patterns relative to a given reference pattern and then uses their known continuations to form a prediction for the reference pattern.

Model Base --

KnowledgeMiner Classic has a built-in model base to store and access all generated models of a document. Every model can be activated easily by the ‘Models’ menu to show graphs, report, analytical model description, and to use it for prediction on new data within the program.

The power and the advantages of KnowledgeMiner, compared with statistics as well as with traditional neural networks, make it easy to use and rapidly applicable to a wide range of real-world problems, and characterize it as the most effective modeling and prediction tool available.

Application areas --

KnowledgeMiner's algorithms can be used for different data mining tasks:

Data Mining Function and Algorithm(s) used --

1) Classification -- SONAN, FRI, and AC.

2) Modeling -- SONAN and FRI.

3) Time Series Forecasting -- AC, SONAN and FRI.

4) Sequential Patterns -- AC.

5) Clustering -- AC.

Examples that come with KnowledgeMiner --

Included datasets and examples range from prediction of global temperature, stock market trends, medical diagnosis, failure of materials (like the Challenger Space Shuttle O-Ring), recognition of handwritten digits, Wine Recognition, national economy, to party affiliation in the US congress.

The many examples included with KnowledgeMiner show its power to work on human issues.

KnowledgeMiner Classic Features/capabilities --

1) Spreadsheet like handling of data including simple formulas and cell references.

2) Several built-in mathematical functions for extending the data basis.

3) Opens ASCII text files.

4) Creates automatically --

5) Enables background modeling.

6) Receiver Operator Characteristic (ROC) for evaluation of the classification power of generated models.

7) Stores all created models in a model base dynamically.

8) All models can be used for status-quo or what-if predictions, classification or diagnosis problems within KnowledgeMiner.

9) Copy (PDF file) of the book by Mueller/Lemke “Self-Organising Data Mining”.

10) AppleScript support for program-to-program communication, task automation, and knowledge discovery workflow across the system or a network (Not available on Windows systems). Read the book AppleScript for Absolute Starters by Bert Altenburg. It is free (PDF, 896k).

11) Creates nonparametric prediction models for fuzzy objects by Analog Complexing, an advanced pattern recognition technology for evolutionary processes. A synthesis of different prediction models (SONAN-based and Analog Complexing-based) is now possible as a powerful way to increase prediction accuracy.

12) Provides Fuzzy Rule Induction as a third self-organizing data mining method for modeling, classification and prediction tasks.

13) For the first time, integrated noise filtering characteristics for a second level, on-the-fly model validation; supports evaluation if a model reflects a causal relationship or if it just models noise.

14) Two (2) new data mining algorithms: Analog Complexing based clustering and classification (n classes).

16) Explicit definition of exogenous and endogenous variables for creation of systems of equations and their what-if type prediction.

17) TransformModel (utility) for implementing models in Microsoft Excel.

System Requirements

Contact manufacturer.


Manufacturer Web Site KnowledgeMiner Classic

Price Contact manufacturer.

G6G Abstract Number 20142R

G6G Manufacturer Number 102350