–| KnowledgeMiner E-News | December, 2001 |—————————–
IN THIS ISSUE
– Script Software Announces the Release of KnowledgeMiner 4.0
– About KnowledgeMiner: Personal Data Mining Made Easy.
– Why is KnowledgeMiner needed?
– History
– Book about Personal Data Mining and KnowledgeMiner
– What KnowledgeMiner Users are Saying
– Distributing KnowledgeMiner
————————————————————————
Script Software Announces the Release of KnowledgeMiner 4.0
————————————————————————
Cutting Edge Data Mining Technology Now Runs on the Mac and Windows.
KnowledgeMiner can be downloaded from:
http://www.knowledgeminer.net and http://www.scriptsoftware.com
Version 4.0 features
– extended AppleScript support (Mac)
– first version that runs on Windows 98, 2000, and NT using Ardi’s
Executor Mac OS runtime environment (Windows)
– workflow processing – importing data from databases or spreadsheets,
data preprocessing, data mining, prediction/classification of new
data, and returning processed data – by running a single script
– creating and predicting from within a script
– creating documents of a certain table dimension via AppleScript
– calculation of the ROC integral as a measure of classification
power of a model
– an actual vs. predicted view added
– fixed bug when calculating the AEV criterion on an out-of-sample
data subset (examination set) during modeling
Included datasets and examples range from; stock market trends, medical
diagnosis, global temperature predictions, failure of materials (like the
Challenger Space Shuttle O-Ring), wine recognition, national economy, to
party affiliation in the US congress. The many examples included with KM
show its power to work on human issues.
————————————————————————
About KnowledgeMiner: Personal Data Mining Made Easy
————————————————————————
KnowledgeMiner is a software application being used by NASA, Boeing, MIT,
Columbia, Notre Dame, University of Hamburg, Mobil Oil, Pfizer Inc., Dean &
Company and many other corporations, universities, research institutions and
individuals around the world. Because it is a data mining technology, it can
be used in any field of human inquiry to reveal new and previously unknown
relationships in data.
KnowledgeMiner is the first choice in data mining because it provides the
most objective, easiest, fastest and least expensive data mining
technologies in the world. Also, as it learns about a new dataset, it
generates equations on the fly that model that data. It is knowledge
extraction in its most advanced form.
KnowledgeMiner is a powerful modeling and prediction tool which
was designed to support the automation of knowledge extraction from data. It
works using three advanced self-organizing modeling technologies: Group
Method of Data Handling (GMDH), Analog Complexing and Fuzzy Rule Induction.
This is the first time that all of these algorithms have been available in
one place on any computer platform.
Built on the cybernetic principles of self-organization, KnowledgeMiner
brings high-end classification, clustering, modeling and prediction
capabilities to your desktop without the need for an expert.
With the extended AppleScript support now available in KnowledgeMiner 4.0,
it is possible to control and automate the knowledge discovery process via a
single script. In this way, KnowledgeMiner users can embed advanced data
mining technology into personal solutions, automate repetitive tasks in
simulations, create their own intelligent agents and display real time data
mining on the internet.
KnowledgeMiner empowers businesses and private users with its combination of
ease of use, advanced self-organizing data mining technologies and the
personalization and workflow capabilities of AppleScript. KnowledgeMiner is
the first Personal Data Mining software.
————————————————————————
Why is KnowledgeMiner needed?
————————————————————————
There are two main reasons. First, because of the explosive growth of many
business, government, scientific and personal databases. The flood of
information has far outpaced our ability to interpret and digest this data.
Second, there is a strong demand for a new generation of tools and
techniques for automated and intelligent database analysis both on large
and small datasets, coupled with a growing desire by non-specialists for
easy to use tools that don’t require a lifetime of experience and knowledge
to operate.
Databases are growing more and more massive everyday:
– The human genome project
– Mobil oil exploration info (100 terabytes)
– NASA Earth Observing System (50 gigs/hour)
– Everyone with a computer is experiencing this on a personal level with
contacts, stock market info, files and email deluging us in a growing
torrent.
Data mining, knowledge discovery, and decision support are becoming
increasingly important for all areas of human activity. As an example look
at El Ni=F1o. El Ni=F1o is now described as a minute temperature change in t=
he
ocean off of South America which strongly influences global weather. A
couple years ago we were all very impressed by the power of El Ni=F1o but
until recently that data was lost in an ocean of other climatic data.
How many other powerful influences on weather, politics, sociology, economy,
energy, health, history, crime, etc. are hidden in the vast mountains of
data we already have?
Specific questions like how national economies are interconnected and
affected by local crises, how water quality and temperature is influenced by
the environment and vice versa, how the population of a country or the world
will change, how cancer can be detected or how credit card fraud can be
tracked are only a few of the applications that a tool like KnowledgeMiner
can be used for.
————————————————————————
History
————————————————————————
KnowledgeMiner has a distinguished history. Built on research activities and
results of different sciences like cybernetics, systems theory, computer
science, and mathematics over the past 30 years. Different approaches to
Inductive Learning from scientists in the Ukraine, Germany, USA, Japan, and
China have come together to provide the most powerful, unique, and
easy-to-use piece of data mining software on the market. Our goal is to
integrate these state-of-the-art data mining technologies into software
tools that can help solve real world problems in economy, ecology, medicine,
or sociology. Our international team of researchers and developers is
constantly working to improve our products. More details are on our site.
————————————————————————
Book about Personal Data Mining and KnowledgeMiner
————————————————————————
Many people have wanted to learn more about self-organizing modeling and the
basic ideas behind KM’s modeling methods. Frank Lemke and Prof. Mueller, two
recognized leaders in this field, have just finished a book called
“Self-Organising Data Mining. An Intelligent Approach To Extracting
Knowledge From Data.”
This book provides a comprehensive view of all major issues related to
self-organizing data mining and its application to solving real-world
problems, and it answers the following questions.
– What makes self-organizing data mining different from other data
mining methods?
– What problems can be solved by self-organizing data mining in general
and by using KnowledgeMiner specifically?
– How to prepare a problem for solution as demonstrated using several
examples from economy, ecology, and sociology.
The book is available now on our website as a Adobe Acrobat PDF. It is
also included in every regular copy of KnowledgeMiner.
————————————————————————
What KnowledgeMiner Users are Saying
————————————————————————
“KnowledgeMiner is the only product that I have found that makes it easy to
try non-standard equation formats on a data set. Many standard regression
tools are as easy, but they limit you to a small set of potential
relationships. KnowledgeMiner combines spreadsheet-like set up with an
algorithm that doesn’t “over fit” the model. Also, the output is in a
readily usable format (e.g. not C++ code).”
– Ware Adams, Dean & Company, a strategy consulting firm in the U.S.
“The Alpine skiing and Athletic French Federation have contacted my
laboratory to build a profile of their elite athletes. In this case,
KnowledgeMiner helped me save a lot of time and gave me models on the most
important variables, and pointed out the less relevant.”
– Fabrice Viale, Doctoral thesis student
Laboratoire de Physiologie, Faculte de Medecine, France
“I like KnowledgeMiner because its algorithm does not make any assumtions on
the underlying data; well, at least not during the initial model-building
phase. I also like the fact that it generates sets of equations that the
user can review with detailed understanding of the interactions and
dependencies of each variable. Also, the algorithm(s) behave surprising well
under extreme conditions for certain complex dynamical systems.
Congratulations for your excellent work.”
– Alexis Pobedonostzeff, Pfizer Inc.
Director, Health Care Issues Analysis & Management
For more information on KnowledgeMiner go to our web site:
http://www.knowledgeminer.net
or email info@knowledgeminer.net