Greetings from NeuroDimension!

The World Leader in Neural Network Software

 

This issue of the NeuroDimension newsletter highlights significant spring savings available now, along with tips and news for NeuroDimension products.

 

In this issue you’ll find:

 

What’s New and News?

   *   Neural Network Course Savings

 

Product Upgrade Announcement

   *   NeuroSolutions v4.20 Now Available

 

NeuroSolutions Tip Box

   *   Configuring a Breadboard for Image Recognition

 
Customer Spotlight

   *   Prediction of Pregnancy-induced hypertensive disorders (PIHD)

 

Note: You are receiving this newsletter because you requested to stay informed concerning new developments at NeuroDimension. If you would like to stop receiving these newsletters, please see the bottom of this newsletter for removal instructions.

 

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=

What’s New and News?

 

Neural Network Course Savings

The deadline is quickly approaching for a 10% early registration discount for our next series of neural network courses. The courses are scheduled for April 29 - May 3, 2002 at the Grosvenor Resort, located in the Walt Disney World Resort in Orlando, Florida. Register before March 25, 2002 to receive a 10% discount on any course!

 

Our course format allows both novice and advanced users to find a suitable course. Offered courses include: "Introduction to NeuroSolutions", "Fundamentals of Neural Networks and NeuroSolutions", and "Advanced NeuroSolutions". The courses include a copy of our interactive book, Neural and Adaptive Systems: Fundamentals Through Simulations.

 

For details on this new offering, or to sign-up from the Internet, see http://www.nd.com/course/may_2002.htm

For general ND course information, see http://www.nd.com/course 

 

For more information and samples of the interactive book, see http://www.nd.com/products/nsbook.htm

 

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=

Product Upgrade Announcement

NeuroSolutions v4.20 Now Available

 

NeuroSolutions v4.20 is now available from NeuroDimension. This release addresses a few minor bugs and includes several enhancements to support development for Microsoft Office XP and Visual Studio .NET. These enhancements include:

 

   *   Code Generation support for Visual C++ 7.0 (.NET)

   *   DLL support for Visual C++ 7.0 (.NET)

   *   Support for compiling Custom Solution Wizard DLLs with Visual C++ 7.0 (.NET)

   *   Addition of Custom Solution Wizard project shells for:

       *   Visual Basic 7.0 (.NET)

       *   Visual C++ 7.0 (.NET)

       *   Excel XP

       *   Access XP

 

A complete list of improvements can be found at <http://www.nd.com/support/nsimprove.htm>.

 

If you already have NeuroSolutions v4.0 or v4.1 installed on your computer you can upgrade to v4.2 by downloading and running the patch from http://www.nd.com/support/ns_patch.htm

 

The complete installation program is available for download at http://www.nd.com/download.htm

 

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=

NeuroSolutions Tip Box

This Issue: Configuring a Breadboard for Image Recognition

 

NeuroSolutions supports the reading of bitmap (*.bmp) image data, where each pixel is translated into one grayscale value or three RGB values (0 to 255). The NeuralWizard and the NeuralBuilder do not currently give you the option to select this type of input data. However, setting up a neural network to read image data is a fairly straightforward process.

 

Here are the steps for using bitmap image data:

 

1. Build your network using the NeuralExpert or NeuralBuilder using a dummy column-formatted ASCII file (e.g., SampleData\xor.asc).

2. Open the inspector for the File component at the input.

3. Click the Remove button to remove the dummy file.

4. Click the Add button.

5. Select the first bitmap file you want to use as input.

6. Select either the “Bitmap” or “Color Bitmap” translator within the Associate dialog box that corresponds to selected file.

7. Repeat the previous 3 steps for each image you want to use as input.

8. If you are reading the images as grayscale (translator = “Bitmap”) open the inspector for the input Axon and change the number of Rows and Columns to match the dimensions of each image. For color bitmaps, you will need to multiply the number of Rows and Columns by three since there are three values for each pixel.

9. To view grayscale images as they are being fed to the network, attach an ImageViewer probe to the Activity access point (the right side) of the input Axon.

10. Add an ASCII file to the File component at the desired output. This file should contain one row for each input image.

 

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=

Customer Spotlight

This Issue: Prediction of the development of pregnancy-induced hypertensive disorders in high-risk pregnant women by artificial neural networks.

 

Mello G, Parretti E, Ognibene A, Mecacci F, Cioni R, Scarselli G, Messeri G.
Istituto di Clinica Ostetrica e Ginecologica, Universita di Firenze, Italy.

 

Pregnancy-induced hypertensive disorders (PIHD) are common complications of pregnancy and are associated with increased maternal and fetal morbidity. In this study, artificial neural networks (aNN) and multivariate logistic regression (MLR) were applied to a set of clinical and laboratory data (urea, creatinine, uric acid, total proteins, hematocrit, iron and ferritin) collected at 16 and 20 weeks of gestation. The efficacy of the two approaches in predicting the development of PIHD in 303 consecutive normotensive pregnant women at high risk of pre-eclampsia and intrauterine fetal growth retardation was then compared.

 

The aNN were trained with a randomly selected set of 187 patient records and evaluated on the remainder (n=116). MLR analysis was done with the same 116 patients. The performance of each model was assessed using receiver operator characteristic (ROC) curves. Pregnancies had a normal physiological course in 227 cases, whereas 76 (25.1%) women developed PIHD during the third trimester.

 

The best aNN at 20 weeks yielded an area under the ROC curve of 0.952, the sensitivity of 86.2%, the specificity of 95.4%, the positive predictive value of 86.2% and the negative predictive value of 95.5% for PIHD. The corresponding values for the MLR at 20 weeks were 0.962, 79.3%, 97.7%, 92% and 93.4%, respectively. The computer-aided integrated use of these conventional tests seems to provide a useful means for and early prediction of PIHD development.

 

Want to have your solutions spotlighted? We strongly encourage our customers to send their 1-2 page application summaries to submissions@nd.com so that we may post them on our web site at: http://www.nd.com/applicationsum.htm. We frequently spotlight solutions in our newsletters and include a link for people to get more information.

 

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=

Comments or Suggestions?

 

We appreciate your feedback! Please send us your comments or suggestions concerning this newsletter, our web site, or part of the NeuroDimension product line. Write to us at: feedback@nd.com

 

Have questions about NeuroDimension products or training services? Send your questions to: info@nd.com

 

Some mail readers may display an attachment at the bottom of this newsletter. This is typically caused when the mail reader is set to display text only. The original, formatted version is sometimes included as an attachment.

 

This issue and previous issues of this newsletter are available on the NeuroDimension web site at: http://www.nd.com/mailinglist.htm

 

If you would prefer not to receive these newsletters or subsequent product updates from NeuroDimension, please reply to this letter with the subject heading changed to the word REMOVE.

 

Thank you again for your support of NeuroDimension products!