Award Data

A quality simulation which allows a user to simulate the acoustic emissions in a multi-source environment and then study the effects these conditions have on a set of acoustic sensors would be of great value. As acoustic sensors technology continues to advance with robust algorithms for detection, tracking and identification as well as high performance hardware providing real-time operation, thes ...

N/A

N/A

This project applies a combination of Artificial Neural Networks (ANN), Genetic Algorithms (GA), and CAD software to the problem of optimum armor design. Previous work for TACOM has established the efficacy of ANN/GA as applied to the problem of 1-D armor design. This new work will extend the concept to full 3-D vehicle geometries (CAD models). The CAD part of the code will handle the 3D data d ...

N/A

This effort will integrate an advanced technology speech recognition system (SRS) with a computer-assisted contingency planning training model. The SRS makes use of algorithms developed in the Speech Technology and Research Labratory of SRI International. Its state-of-the-art approach provides significant improvements in accuracy and robustness over other approaches. It provides for speaker ind ...

UTS will investigate technologies that can be applied to an 'after-action-review' capability in support of weapon system development and testing. The capability can be used to provide standard "Debrief Module" products during and after a DIS experiment. The Debrief Module will support "what if" analysis during and within hours after a DIS experiment, including an assessment of the impact of alte ...

DACCO SCI, INC. proposes a Phase I SBIR program to develop an affordable sensor system to monitor the health or condition of infrastructure. Although the selection of sensors will depend on the particular infrastructure being monitored, it is anticipated that in-situ corrosion sensors will be coupled with fiber optic and/or acoustic sensors. The corrosion sensor is capable of monitoring corrosio ...

This SBIR Phase I project will create an event representation framework and generate a catalogue of reasoning mechanisms for transforming domain specific events into a convenient representational framework. The choice of the representation scheme used to model a domain for analysis by the neural network of fuzzy logic system can make an enormous difference in the ease and efficiency of the proble ...

Enterprises today rely heavily upon a wide variety of modeling methods and modeling technologies for the development of requirements for complex, software intensive systems. In general, however, (i) the different modeling methods provide very different perspectives on system information, (ii) models created with these methods are expressed in very different modeling languages, and (iii) models ar ...