Home / Science / SETI uses AI to help seek out foreign life

SETI uses AI to help seek out foreign life

Image of a robot listening to radio outbreak from outer space. SETI used artificial intelligence inspired by the same algorithm used by internet companies to sort through a massive spacecraft space. In a new study, the researcher analyzed a mysterious signal that came from far. Breakthrough Listen | University of California, Berkeley )

SETI overloads search for alien life using artificial intelligence to analyze dozens of data collected from a galaxy far away.

A Great Mystery

The Breakthrough Listen researchers, a project led by the University of California Berkely, used a new neural network to detect 72 straight radio outbreaks or FRB from a mysterious noisy galaxy about three billion light years from Earth. [1

9659005] "This work is exciting not only because it helps us understand the dynamic behavior of fast radio outages in detail, but also because of the promise it shows to use machine learning to detect signals missing from classic algorithms "says Andrew Siemion, Berkeley SETI Research Center Director.

FRB is pulses of radio emissions, lasting about one millisecond, has remained a mystery for this day. Lots of theories try to explain their origin, including strong magnetic fields in a dense plasma. Some believe that these FRBs could come from a technology developed by an advanced extraterrestrial civilization.

FRB 121102, the subject of the study published in The astrophysical journal is a spelled object that has drawn the attention of researchers. Unlike other FRB, FRB 121102 is not a one-off event. It is played by its mysterious source repeatedly from billions of light years away.

To analyze the signals, researchers recorded data over a five-hour period using the Green Bank Telescope in West Virginia in August 2017. The session gave 400 terabytes of transmission data.

An initial analysis with the default computer algorithm was able to identify 21 line breaks within one hour of observation.

Using AI

Researchers wanted to reassess data using the same techniques that Internet companies use to optimize search results and classify images. Gerry Zhang, a doctoral student at UC Berkeley, developed the "Fasting Neural Network System" to shed the huge amount of data and find radio blasts from FBR 121102.

The new algorithm could find another 72 deficiencies from the recorded transmission data, resulting in it Total number of explosives recorded from FBR 121102 to about 300 since its discovery in 2012.

The researchers did not find evidence that the emissions were from an artificial origin from a planet far away. They discovered no pattern from the shortcomings.

Yet, the new method developed by Zhang and his team changes how researchers gather fast radio outbreaks that can help reveal the mystery's origins in the future.

"We hope our success can inspire other serious efforts in applying machine learning to radio astronomy," says Zhang.

See Now: 30 Gadgets and Technical Gifts for Father's Day 2018 That Dad Will Think Is Row

20120 TECHTIMES.com All rights reserved.

Source link