Application of artificial neural networks to an electronic olfactory system

TLDR

The human sense of smell underpins industry monitoring of beverages, food, and perfumes, and prior work has developed electronic noses—a computer‑controlled multi‑sensor array that responds differentially to various vapours and odours—to emulate this capability. The study aims to apply artificial neural networks to process data from an electronic nose sensor array. The authors use artificial neural networks to analyze the sensor array outputs, enabling adaptive, fault‑tolerant classification of odor signals. The ANN approach demonstrates adaptability, fault tolerance, and hardware‑implementation potential, and successfully classifies alcohol spectra, indicating strong promise for sensor‑array processing.

Abstract

The human sense of smell is the faculty upon which many industries rely to monitor items such as beverages, food and perfumes. Previous work has been carried out to construct an instrument that mimics the remarkable capabilities of the human olfactory system. The instrument or electronic nose consists of a computer-controlled multi-sensor array which exhibits a differential response to a range of vapours and odours. The authors report on a novel application of artificial neural networks (ANNS) to the processing of data gathered from the integrated sensor array or electronic nose. This technique offers several advantages, such as adaptability, fault tolerance, and potential for hardware implementation over conventional data processing techniques. Results of the classification of the signal spectra measured from several alcohols are reported and they show considerable promise for the future application of ANNS within the field of sensor array processing.