Malodour classification with low-cost flexible electronics

• Published in: Nature communications Vol. 14; no. 1; p. 777
• Main Authors: Ozer, Emre, Kufel, Jedrzej, Biggs, John, Rana, Anjit, Rodriguez, Francisco J., Lee-Clark, Thomas, Sou, Antony, Ramsdale, Catherine, White, Scott, Garlapati, Suresh Kumar, Valliappan, Palaniappan, Rahmanudin, Aiman, Komanduri, Venuskrishnan, Saez, Glenn Sunley, Gollu, Sankara, Brown, Gavin, Dudek, Piotr, Persaud, Krishna C., Turner, Michael L., Murray, Stephanie, Bates, Susan, Treloar, Robert, Newby, Brian, Ford, Jane
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 11.02.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/898; 639/166/987; Classification; Consumer products; Electronic noses; Electronics; Flexible components; Hardware; Humanities and Social Sciences; Learning algorithms; Low cost; Machine learning; Measurement methods; multidisciplinary; Organic compounds; Science; Science (multidisciplinary); Sensor arrays; Substrates; VOCs; Volatile organic compounds
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-36104-z

Understanding body malodour in a measurable manner is essential for developing personal care products. Body malodour is the result of bodily secretion of a highly complex mixture of volatile organic compounds. Current body malodour measurement methods are manual, time consuming and costly, requiring an expert panel of assessors to assign a malodour score to each human test subject. This article proposes a technology-based solution to automate this task by developing a custom-designed malodour score classification system comprising an electronic nose sensor array, a sensor readout interface and a machine learning hardware fabricated on low-cost flexible substrates. The proposed flexible integrated smart system is to augment the expert panel by acting like a panel assessor but could ultimately replace the panel to reduce the test and measurement costs. We demonstrate that it can classify malodour scores as good as or even better than half of the assessors on the expert panel. Designing machine learning hardware on flexible substrates is promising for several applications. Here, the authors propose an integrated smart system built with low-cost flexible electronics components for classifying human malodour, and demonstrates that the proposed system scores malodour as good as expert human assessors.