Download file (2.4 MB)
Download as zip (2.18 MB)

Collection

Citation

Description:

The creation of new odors by blending existing ones is usually done manually based on the human sense. To enable robots to perform this automatically, we developed an automated odor-blending system. In this system, an olfactory sensor system composed of an array of Membrane-type Surface stress Sensors (MSSs) performs odor measurement of a blended liquid, and Bayesian optimization controls the blending concentration. The actual blending of the liquid samples is performed by automated syringe pumps. Our system performs odor-blending by injecting liquid samples into a pot or by draining some of the liquid from the pot. The one-pot strategy has the advantage of reducing the amount of liquid samples used in the entire optimization task and reduces the problem of pot replacement. To implement this one-pot strategy effectively, a Drainable One-Pot Bayesian Optimization (DOPBO) algorithm was developed and applied to our system. The system was tested using a ternary liquid mixture.

Rights:

• Creative Commons BY Attribution 4.0 International
  

Keyword: Machine learning, MSS, Bayesian optimization, Olfactory sensor

Date published: 2024-04-16

Publisher: Royal Society of Chemistry (RSC)

Journal:

• Digital Discovery (ISSN: 2635098X) vol. 3 issue. 5 p. 969-976

Funding:

• Japan Society for the Promotion of Science 21H01008
• Japan Society for the Promotion of Science 21H01971
• Japan Society for the Promotion of Science 21K18859
• Japan Society for the Promotion of Science 22K05324
• Japan Society for the Promotion of Science JP19KK0141

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1039/d3dd00215b

Related item:

Other identifier(s):

Contact agent:

Updated at: 2024-06-10 12:30:19 +0900

Published on MDR: 2024-06-10 12:30:19 +0900