Automated Data Acquisition for In-Situ Material-Processing Modeling

Award Information
Agency:
Department of Defense
Amount:
$99,706.00
Program:
SBIR
Contract:
N/A
Solitcitation Year:
N/A
Solicitation Number:
N/A
Branch:
Air Force
Award Year:
1996
Phase:
Phase I
Agency Tracking Number:
32309
Solicitation Topic Code:
N/A
Small Business Information
Advanced Refractory
699 Hertel Ave., Buffalo, NY, 14207
Hubzone Owned:
N
Woman Owned:
N
Socially and Economically Disadvantaged:
N
Duns:
N/A
Principal Investigator
 Arvind Goel
 (716) 875-4091
Business Contact
Phone: () -
Research Institution
N/A
Abstract
Exploiting the many analogies between biological neurons and the cells within a spreadsheet application, we have succeeded in constructing independtly functioning, self-trained neural network cascades that are capable of (1) forming models of their spreadsheet environment, (2) manipulating data, (3) identifying anomalous information or noise, (4) locomotion, and (5) control over external instruments or devices. If information gathered by process sensors is fed through a spreadsheet application by dynamic data exchange, such neurological cascades or "databots" may be used to patrol the resulting databases, automatically identifying systematic and random noise, forming both neural and semantic models, organizing data, and coordinating external sensors and actuators. These accomplishments are made possible through two pioneering efforts. The first is the so-called "Creativity Machine Paradigm," allow autonomous discovery and planning using a tandem arrangement of chaotic and supervising networks. The second achievement involves the implementation of this paradigm without the use of any algorithmic code, instead using the inherent parallel processing capacity built into spreadsheet applications via cell referencing and resident spreadsheet functions. Autonomy of this spreadsheet "organism" is guaranteed by the encapsulation of both data and function, reminiscent of object-oriented programming, but now implemented in a virtual, analog network.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government