[ad_1]
Image of a robot listening to the radio from the space. SETI used artificial intelligence inspired by the same algorithm used by Internet companies to sort out a huge amount of spatial data. In a recent study, the researcher analyzed a mysterious signal from far away. ( Percée Listen | University of California, Berkeley )
SETI supercharges the quest for extraterrestrial life using artificial intelligence to analyze dozens of data collected in a distant and distant galaxy.
A great mystery
The researchers at Breakthrough Listen, a project led by the University of California at Berkely, used a new neural network to discover 72 fast radio waves or FRBs from a mysteriously noisy galaxy located about three billion light-years away from the Earth.
"This work is exciting, not only because it helps us better understand the dynamic behavior of fast radio bursts, but also through machine learning that can detect signals missed by conventional algorithms," says Andrew Siemion. Berkeley SETI. Director of the research center.
The FRB's radio transmissions, which last about a millisecond, have remained a mystery to this day. Many theories try to explain their origin, including strong magnetic fields in a dense plasma. Some think that these FRB 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 stellar object that has attracted the attention of scientists. Unlike other FRBs, FRB 121102 is not a single event. It is emitted by its mysterious source several times billions of light years away.
To analyze the signals, the researchers recorded data over a five-hour period with the help of the Green Bank Telescope in West Virginia in August 2017. The session yielded 400 terabytes of transmission data. .
An initial analysis using the standard computer algorithm allowed identifying 21 radio bursts in the hour following the observation.
Use AI
Researchers wanted to reanalyze data using the same techniques used by Internet companies to optimize search engine results and rank images. Gerry Zhang, a graduate student at the University of California at Berkeley, has developed the "convolutional neural network system" to browse the mass of data and find radio bursts from FBR 121102.
The new algorithm found 72 additional bursts from the recorded transmission data, bringing to about 300 the total number of bursts recorded since FBR 121102 since its discovery in 2012.
The researchers found no evidence suggesting that the emission came from an artificial origin originating from a distant planet. They did not detect any pattern of bursts.
However, the new method developed by Zhang and his team is changing the way scientists gather rapid radio bursts that could help uncover the mystery of their origin in the future.
"We hope our success could inspire further serious efforts in the application of machine learning to radio astronomy," Zhang said.
See now: 30 gadgets and technical gifts for Father's Day 2018
8 2018 TECHTIMES.com All rights reserved. Do not reproduce without permission.
[ad_2]
Source link
