Abstract

Practical applications of machine olfaction have been eagerly awaited. A free-hand measurement, in which a measurement device is manually exposed to sample odors, is expected to be a key technology to realize practical machine olfaction. To implement odor identification systems based on the free-hand measurement, the comprehensive development of a measurement system including hardware, measurement protocols, and data analysis is necessary. In this study, we developed palm-size wireless odor measurement devices equipped with Membrane-type Surface stress Sensors (MSS) and investigated the effect of measurement protocols and feature selection on odor identification. By using the device, we measured vapors of liquids as odor samples through the free-hand measurement in different protocols. From the measurement data obtained with these protocols, datasets of transfer function ratios (TFRs) were created and analyzed by clustering and machine learning classification. It has been revealed that TFRs in the low-frequency range below 1 Hz notably contributed to vapor identification because the frequency components in that range reflect the dynamics of the detection mechanism of MSS. We also showed the optimal measurement protocol for accurate classification. This study has shown a guideline of the free-hand measurement and will contribute to the practical implementation of machine olfaction in society.

Highlights

  • Among the five human senses (i.e., sight, hearing, touch, taste, and smell), machine olfaction and gustation applications have not been widely implemented in society

  • We have developed palm-size wireless odor measurement devices equipped with Membrane-type Surface stress Sensors (MSS)

  • The free-hand measurement is independent of the input pattern in principle, roughly fixed measurement protocols are favored from a viewpoint of practical use

Read more

Summary

Introduction

Among the five human senses (i.e., sight (vision), hearing (audition), touch (somatosensation), taste (gustation), and smell (olfaction)), machine olfaction and gustation applications have not been widely implemented in society. It is more challenging to realize machine olfaction because there are no “basic smells” for olfaction whereas taste can be sensed by detecting the five basic tastes (i.e., sweet, sour, salty, umami, and bitter) [1,2]. In 1982 [3], machine olfaction—gas sensor systems for identifying odors—has been extensively studied by many researchers [4,5]. Owing to the advancement in sensing technologies including the development of sensor elements, fabrication techniques, and signal analysis methods, some products have already been available in the market. For practical application, there are still many technical issues in sensitivity, selectivity, usability, commercial availability, and so on. Considering the Sensors 2020, 20, 6190; doi:10.3390/s20216190 www.mdpi.com/journal/sensors

Objectives
Methods
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call