From a Cracker Jack box to The Da Vinci Code, everyone loves deciphering secret messages. But biomedical engineers at Duke University have taken the decoder ring to a place it’s never been before: the patterns created by bacterial colonies.
Depending on the initial conditions used, such as nutrient levels and space constraints, bacteria tend to grow in specific ways. The researchers created a virtual bacterial colony, then controlled growth conditions and the number and size of simulated bacterial dots to create a complete alphabet based on the appearance of the colonies after filling a virtual petri dish. They call this coding scheme emorfi.
The encoding is not unique, because the final simulated pattern corresponding to each letter is not exactly the same each time. However, the researchers found that a machine learning program could learn to tell them apart to recognize the correct letter.
“A friend may see many images of me over time, but none of them will be exactly the same,” said Lingchong You, a professor of biomedical engineering at Duke. “But if the pictures all consistently reinforce what I generally look like, the friend will be able to recognize me even if he sees a picture of me he’s never seen before.”
To encrypt the real messages, the encoder ends up creating a film of a series of patterns, each corresponding to a different letter. Although they may look like to the untrained eye, the computer algorithm can tell them apart. As long as the receiver knows the set of initial conditions that led to their creation, an intruder should not be able to crack the code without their own powerful AI.
Try encryption yourself. You can type in anything from your name to the Gettysburg address, or even the Christmas classic, “Make sure you drink your Ovaltine.”
Fractal patterns in growing bacterial colonies
Jia Lu et al, Coding and Decoding Distributed Information Using Self-Organizing Spatial Models, Grounds (2022). DOI: 10.1016/j.patter.2022.100590
Provided by Duke University
Quote: An AI message decoder based on bacterial growth models (2022, September 23) Retrieved September 23, 2022 from https://phys.org/news/2022-09-ai-message-decoder-based-bacterial.html
This document is subject to copyright. Except for fair use for purposes of private study or research, no part may be reproduced without written permission. The content is provided for information only.