AI nose: Study explores future of scent detection

Korean scientists have developed a next-generation artificial intelligence (AI) electronic nose that can smell and distinguish scents like a human nose. The device showed 95% accuracy when identifying nine fragrances commonly used in cosmetics and perfumes. It was also able to detect the types of smells and concentrations of each scent.  

The study highlights that the e-nose is still in its developing stage, but the researchers argue that it is a promising tool for future sensor technologies.  

“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,” says Hyuk-jun Kwon, professor at the department of electrical engineering and computer science at Daegu Gyeongbuk Institute of Science and Technology, South Korea.

Distinguishing perfumes

The researchers used combinational coding, in which a single odorant molecule — tiny air particles triggering a sense of smell when in contact with the human nose — activates multiple olfactory receptors, creating a pattern of neural signals. 

The study, published in ACS Nano, mimicked the pattern and then engineered it so that the sensors respond to scent molecules, producing a combination of electronic signals through the sensors.

The results showed that the e-nose effectively classified nine distinct odorant molecules.The nose uses a single-step laser fabrication method and an integrated sensor analysis while eliminating the need for complex manufacturing equipment.

“The laser parameters could be adjusted to fine-tune the properties of the active channels without the need for complex deposition processes, offering a convenient method for creating sensor arrays that mimic the human olfactory system,” reads the study.

The results showed that the e-nose effectively classified nine distinct odorant molecules used in the cosmetics and perfume industry.

“We are actively expanding development and commercialization efforts to apply this technology to the fragrance industry, personal healthcare, and environmental pollution detection,” says Kwon.

Electric sense of smell

The researchers stress that artificial olfactory systems — electronic noses — are a challenging frontier. Digitalization of other human senses, such as image sensors, speakers, and microphones for hearing, and pressure sensors for touch, has seen an increase in applications and capabilities, even beyond the human senses.

Digital noses are a slower innovation due to their high link to human memory and being one of the most primal senses. However, the authors argue that their potential for the cosmetic industry and fragrances is vast.

“Odorant receptors do not bind to odorant molecules in a one-to-one manner. Instead, they use a ‘combinatorial coding’ process, where odorant molecules bind to multiple odorant receptors to convey information about the scent,” reads the study.

The researchers say perfumes are multi-component odors in real-world environments. Therefore, next-generation e-noses are the gap needed in the market for greater precision and sensitivity in the fragrance industry to distinguish between scents, as perfumes often have a mixture of notes, such as floral and fruity.

It also has the potential to detect environmental hazards such as chemical gases through electric signals. The authors say that, apart from detecting odorant molecules in perfumes, the innovation can potentially discover reactive inorganic gases and toxins in the air.

AI progresses in beautyThe AI nose also has the potential to detect environmental hazards through electric signals.

AI is transforming product formulations and ingredients in the personal care industry.

Haut.AI recently launched an AI technology that provides consumers personalized skin care recommendations. The data is collected, converting frequent recommendations into insights for brands. Anastasia Georgievskaya, the company’s CEO and co-founder, previously told Personal Care Insights that personalization will no longer be static.

“It will become a living, adaptive process [that is] much closer to how human experts would approach long-term skin health,” she told us.

Unilever also recently announced accelerating AI, machine learning, big data, and robotics across its R&D processes. The company has over 500 AI-based capabilities globally, and plans to launch science-led products such as whole-body deodorants and premium body wash.