[name]

Machine Olfaction, Signal Processing and Pattern Recognition

[Anti-drift: Subspace Projection for Heterogeneous Olfaction]

Paper:

Lei Zhang*, Yan Liu, Zhenwei He, Ji Liu, Pingling Deng and Xichuan Zhou, Anti-drift in E-nose: A Subspace Projection Approach with Drift Reduction, Sensors and Actuators B: Chemical, vol. 253, pp. 407-417, 2017. [paper]

Abstract:

Anti-drift is an emergent and challenging issue in sensor-related subjects. In this paper, we propose toaddress the time-varying drift (e.g. electronic nose drift), which is sometimes an ill-posed problem dueto its uncertainty and unpredictability. Considering that drift is with different probability distributionfrom the regular data, a machine learning based subspace projection approach is proposed. The mainidea behind is that given two data clusters with different probability distribution, we tend to find alatent projection P (i.e. a group of basis), such that the newly projected subspace of the two clusters iswith similar distribution. In other words, drift is automatically removed or reduced by projecting thedata onto a new common subspace. The merits are threefold: 1) the proposed subspace projection isunsupervised; without using any data label information; 2) a simple but effective domain distance isproposed to represent the mean distribution discrepancy metric; 3) the proposed anti-drift method canbe easily solved by Eigen decomposition; and anti-drift is manifested with a well solved projection matrixin real application. Experiments on synthetic data and real datasets demonstrate the effectiveness andefficiency of the proposed anti-drift method in comparison to state-of-the-art methods.

Schematic diagram of the proposed DRCA method; after a subspace projection P, the source domain and target domain of different space distribution lie in a latent subspace with good distribution consistency (the centers of both domains become very close and drift is removed); in this latent subspace, the classification of two classes is successfully achieved.

[name]

E-nose system architecture

[name]

The proposed DRCA Approach:

[name]

Experimental Results

[name] [name] [name] [name]

References:

[1] L. Zhang, F. Tian, S. Liu, L. Dang, X. Peng, X. Yin, Chaotic time series predictionof e-nose sensor drift in embedded phase space, Sens. Actuators, B 182 (2013)71–79.

[2] F. Hossein-Babaei, V. Ghafarinia, Compensation for the drift-like terms causedby environmental fluctuations in the response of chemoresistive gas sensors,Sens. Actuators, B 143 (2010) 641–648.

[3] S. Yan, D. Xu, B. Zhang, H. Zhang, Q. Yang, S. Lin, Graph embedding andextensions: a general framework for dimensionality reduction, IEEE Trans.Pattern Anal. Mach. Intell. 29 (1) (2007) 40–51.

[4] A. Vergara, S. Vembu, T. Ayhan, M.A. Ryan, M.L. Homer, R. Huerta, Chemicalgas sensor drift compensation using classifier ensembles, Sens. Actuators, B:Chem. 167 (2012) 320–329.