'AI electronic nose' used to digitally detect scents
A research team from the Daegu Gyeongbuk Institute of Science and Technology (DGIST) has developed a so-called ‘next-generation AI electronic nose’ that is capable of distinguishing scents like the human olfactory system does and then analysing them using artificial intelligence.
The technology, which converts scent molecules into electrical signals and trains AI models on their unique patterns, holds great promise for applications in personalised health care, the cosmetics industry, and environmental monitoring. It has been described in the journal ACS Nano.
While conventional electronic noses (e-noses) have already been deployed in areas such as food safety and gas detection in industrial settings, they struggle to distinguish subtle differences between similar smells or analyse complex scent compositions. For instance, distinguishing among floral perfumes with similar notes or detecting the faint odour of fruit approaching spoilage remains challenging for current systems. This gap has driven demand for next-generation e-nose technologies with greater precision, sensitivity and adaptability.
The research team was inspired by the biological mechanism known as combinatorial coding, in which a single odorant molecule activates multiple olfactory receptors to create a unique pattern of neural signals. By mimicking this principle, the team engineered sensors that respond to scent molecules by generating distinct combinations of electrical signals. The AI system learns these complex signal patterns to accurately recognise and classify a wide variety of scents, resulting in a high-performance artificial olfaction platform that is said to surpass existing technologies.
The e-nose uses a laser to process a thin carbon-based material (graphene) and incorporates a cerium oxide nano catalyst to create a sensitive sensor array. This single-step laser fabrication method eliminates the need for complex manufacturing equipment and enables high-efficiency production of integrated sensor arrays.
In performance tests, the device successfully identified nine fragrances commonly used in perfumes and cosmetics, with over 95% accuracy. It could also estimate the concentration of each scent, making it suitable for fine-grained olfactory analysis.
The device is ultrathin, flexible and highly durable, making it ideal for wearable devices or bright patches attached to the skin or clothing. It can be bent more than 30,000 times around a 2.5 mm radius without any performance degradation.
“The core innovation of our research is the ability to integrate multiple scent-sensitive sensors with diverse properties, similar to those of the human nose, into a single unit through a one-step selective laser fabrication process,” said team leader Professor Hyuk-jun Kwon. “We are actively expanding development and commercialisation efforts to apply this technology to personal health care, environmental pollution detection and the fragrance industry.”
Scientists create low-cost liquid lenses
Researchers have discovered a simple, affordable way to make dynamically adjustable water-based...
Water filter designed to remove PFAS molecules
Monash University researchers have developed a water filtration membrane that effectively removes...
'Pain-on-a-chip' device identifies different chronic pain types
The pain-on-a-chip concept has the potential to provide a biosensor platform for a minimally...