CyberWarfare / ExoWarfare

Automated Threat Recognition Algorithm With Machine Learning Capability

Neutral Explosives Detection Algorithm in Development

In order to upgrade and improve airport security systems, the U.S. government and airport security experts are working to develop vendor-neutral software for explosives detection in baggage-screening systems at airports and other ports of entry.

The idea is to develop explosives detection algorithms able to run on a variety of baggage-screening systems.

These software applications enable the U.S. Department of Homeland Security’s Transportation Security Administration (TSA) to complete airport security technology widely through industry, and ensure passenger security systems have the latest technologies.

In fact, the TSA announced plans to award an estimated $3 million one-year contract to Stratovan, for the development of this software.

Stratovan has developed an automated threat recognition algorithm with machine learning capability that uses computed tomography (CT) imaging technology developed originally for medical applications for explosives detection in a specific model baggage-screening system.

The idea now is to determine if a third party could develop a vendor-neutral algorithm.

This contract would continue an effort with Stratovan, and expand development of the vendor-neutral automated threat recognition software, on which the company already has started development.

This contract asks Stratovan engineers to enable the algorithm to detect home-made explosives and integrate it into an explosives-detection machine. If this works, TSA officials will be able to select automated threat recognition technologies independently of systems vendors.

In this way TSA can avoid being locked-in to explosives-detection technologies that are specific to baggage-screening system suppliers, according to militaryaerospace.com.

According to the TSA the most effective way to enhance explosives-detection algorithms while mitigating the risk of a false alarm is through machine learning technology.

 

This post is also available in: heעברית (Hebrew)

from: https://i-hls.com/archives/86213

 

 

 

By continuing to use this site, you agree to the use of cookies. Please consult the Privacy Policy page for details on data use. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close