JNS
Researchers used a machine learning algorithm to create a ‘library’ of odors, detectable at a level of sensitivity 10,000 times higher than that of commonly used electronic devices.
Tel Aviv University researchers have developed a biological sensor that sends electrical signals in response to odors, allowing robots to “smell.”
The researchers first devised the mechanism, and then used a machine learning algorithm to identify odors at a level of sensitivity 10,000 times higher than that of commonly used electronic devices.
“We connected the biological sensor and let it smell different odors while we measured the electrical activity that each odor induced. The system allowed us to detect each odor at the level of an insect’s primary sensory organ. Then, in the second step, we used machine learning to create a ‘library’ of smells. We were able to characterize eight odors, such as geranium, lemon and marzipan, in a way that allowed us to know when the smell of lemon or marzipan was presented,” said professor Yossi Yovel of TAU’s School of Zoology and Sagol School of Neuroscience.
The study was led by doctoral student Neta Shvil of TAU’s Sagol School of Neuroscience, and also included Dr. Ben Maoz of the Fleischman Faculty of Engineering and the Sagol School of Neuroscience and professor Amir Ayali of the School of Zoology and Sagol School of Neuroscience.
The results of the study were published in the journal Biosensor and Bioelectronics.
The researchers believe that the technology can be applied in the future to identify explosives, drugs, diseases and more.
“Man-made technologies still can’t compete with millions of years of evolution,” said Maoz and Ayali. “One area in which we particularly lag behind the animal world is that of odor perception. An example of this can be found at the airport, where we go through a magnetometer that costs millions of dollars and can detect if we are carrying any metal devices. But when they want to check if a passenger is smuggling drugs, they bring in a dog,” they continued.
In the animal world, the researchers said, insects excel at receiving and processing chemical signals. “A mosquito, for example, can detect a 0.01 percent difference in the level of carbon dioxide in the air. Today, we are far from producing sensors whose capabilities come close to those of insects,” they said.
“Nature is much more advanced than we are, so we should use it. The principle we have demonstrated can be used and applied to other senses, such as sight and touch. For example, some animals have amazing abilities to detect explosives or drugs; the creation of a robot with a biological nose could help us preserve human life and identify criminals in a way that is not possible today. Some animals know how to detect diseases. Others can sense earthquakes. The sky is the limit,” said Maoz.
