Robust Classification of Largely Corrupted Electronic Nose Data Using Deep Neural Networks

• Published in: IEEE sensors journal Vol. 21; no. 4; pp. 5052 - 5059
• Main Authors: Yoo, YoungJoon, Kim, Hyun-Il, Choi, Sang-Il
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.02.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classification; Coders; convolutional neural network; Corruption; data corruption; Data integrity; Data loss; data reconstruction; deep neural network; denoising auto-encoder; Electronic nose; Electronic noses; Feature extraction; Gas detectors; Image reconstruction; Neural networks; Noise reduction; Restoration; Sensor arrays; Sensor phenomena and characterization; Smell
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2020.3034145

Data loss for electronic noses may occur because of the sensor's installation environment or from electrical disturbances. As a result, electronic noses may experience difficulties when identifying gases. This paper proposes two deep neural network-based functions for identifying gases. First, a denoising auto-encoder based on the corruption reconstruction method is proposed for electronic nose data to solve this problem. Second, a convolutional neural network-based gas-classifying model is proposed. Although the electronic nose data are highly discriminative, they are sensitive to the corruption of information; hence, they require an efficient restoration method for practical use. From the experiments we demonstrate that the proposed denoising auto-encoder provides a strong restoration capability, and the convolutional neural network-based classifier successfully discriminates the gas data samples with a classification rate over 95% even when the data loss is 50%.