Are there machines that can smell

Materials provided by Manchester University. Note: Content may be edited for style and length. Science News. Story Source: Materials provided by Manchester University. Capacitance-modulated transistor detects odorant binding protein chiral interactions.

Nature Communications , ; 6: DOI: ScienceDaily, 16 January Manchester University. Sensors could give machines more accurate sense of smell than that of humans. Retrieved November 10, from www. However, ordinary light only weakly senses molecular However, during Once a number of compounds were identified manually by the chemists, fast computers were given the data to train deep learning networks.

The computation was accelerated by special devices, called GPUs, that can process multiple different pieces of information at the same time. The deep learning networks learned more and more from each breath sample until they could recognise specific patterns that revealed specific compounds in the breath. In this first study, the focus was on recognising a group of chemicals, called aldehydes , that are often associated with fragrances but also human stress conditions and illnesses.

Computers equipped with this technology only take minutes to autonomously analyse a breath sample that previously took hours by a human expert.

Effectively, AI is making the whole process cheaper — but above all it is making it more reliable. Even more interestingly, this intelligent software acquires knowledge and improves over time as it analyses more samples. As a result, the method is not restricted to any particular substance. Using this technique, deep learning systems can be trained to detect small amounts of volatile compounds with potentially wide applications in medicine, forensics, environmental analysis and others.

If an AI system can detect markers of disease, then it becomes possible to also diagnose whether we are ill or not. This has a great potential, but it could also prove controversial.

We simply suggest that AI could be used as a tool to detect substances in the air. The final conclusions and decisions are left to us. In the process, it can help producers determine which are acceptable substitutions when usual supply lines are interrupted. Traditional quality-control measures for vanilla have included the use of UV spectrophotometry and gas chromatography. But Aryballe says those methods involve equipment that is expensive, bulky, and inadequately sensitive.

Odor detection at the retail shelf is equally important. The technology is good enough, however, to meet the needs of many supply chains for which odor, both good and bad, is a critical concern. Jordan says Aryballe is still in startup mode, with plans to install its first wide-scale, cloud-based deployment in January.

She sees future opportunities in healthcare, with the ability to diagnose disease based on a sample of human breath. A Machine Can Tell.