Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Humidity compensation by neural network for bad-smell sensing system using gas detector tube and built-in camera

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Nakamoto, T. ; Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan ; Ikeda, T. ; Hirano, H. ; Arimoto, T.

Cheap and rapid sensing system is required for detecting bad smell or VOC. Although a gas detector tube is known as simple gas detection method, its measurement process has not been automated. We studied an automated measurement system for gas detector tube using a built-in camera. Although the measurement was automated using our system, other problem was disclosed. Since a digital camera is sensitive to color change, the slight change due to humidity, which is not the problem for manual inspection, cannot be ignored in our system. Thus, the humidity sensor was added to the system. However, the simple compensation method such as linear regression etc did not work because the humidity influenced the data in a complicated manner. Then, MLP (multilayer perceptron) neural network was used for the humidity compensation. Both discoloration area and the humidity data were input to the neural network. As a result, the accurate concentration estimation was successfully performed.

Published in:

Sensors, 2009 IEEE

Date of Conference:

25-28 Oct. 2009