{Home} {Publications and Codes} {Research} {Projects} {Professional Activities} {People}

Machine Olfaction, Signal Processing and Pattern Recognition

[Abnormal Odor Detection]

Paper:

Lei Zhang* and Pingling Deng, Abnormal Odor Detection in Electronic Nose via Self-Expression Inspired Extreme Learning Machine, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017, doi: 10.1109/TSMC.2017.2691909. [paper]

Abstract:

The electronic nose (E-nose), as a metal oxide semiconductor gas sensor system coupled with pattern recognition algorithms, is developed for approximating artificial olfaction functions. Ideal gas sensors should be with selectivity, reliability, and cross-sensitivity to different odors. However, a new problem is that abnormal odors (e.g., perfume, alcohol, etc.) would show strong sensor response, such that they deteriorate the usual usage of E-nose for target odor analysis. An intuitive idea is to recognize abnormal odors and remove them online. A known truth is that the kinds of abnormal odors are countless in real-world scenarios. Therefore, general pattern classification algorithms lose effect because it is expensive and unrealistic to obtain all kinds of abnormal odors data. In this paper, we propose two simple yet effective methods for abnormal odor (outlier) detection: 1) a self-expression model (SEM) with l1/l2-norm regularizer is proposed, which is trained on target odor data for coding and then a very few abnormal odor data is used as prior knowledge for threshold learning and 2) inspired by self-expression mechanism, an extreme learning machine (ELM) based self-expression (SE2LM) is proposed, which inherits the advantages of ELM in solving a single hidden layer feed-forward neural network. Experiments on several datasets by an E-nose system fabricated in our laboratory prove that the proposed SEM and SE2LM methods are significantly effective for real-time abnormal odor detection.

The proposed SEM and SE2LM Framework:

Network structure of SE2LM. The difference between this structure and ELM lies in that the number of input nodes is associated with the dimensionality. In SE2LM, it serves for representing each sample by using hidden layer output and the analytically determined output weights α. It implies that the ELM space represents the dictionary space. Note that an interesting aspect is that in ELM, the number of input nodes and output nodes can be the dimension D, which would become a transformation problem. If N is set, it is expression problem focused in this paper. Also, in the proposed structure, each node is composed of D subnodes (i.e., shadow nodes).

Experimental Results

References:

[1] L. Zhang and D. Zhang, “Efficient solutions for discreteness, drift, and disturbance (3D) in electronic olfaction,” IEEE Trans. Syst., Man, Cybern., Syst., to be published, doi: 10.1109/TSMC.2016.2597800

[2] L. Zhang and D. Zhang, “Robust visual knowledge transfer via extreme learning machine-based domain adaptation,” IEEE Trans. Image Process., vol. 25, no. 10, pp. 4959–4973, Oct. 2016, doi: 10.1109/TIP.2016.2598679

[3] L. Zhang et al., “A novel background interferences elimination method in electronic nose using pattern recognition,” Sensors Actuators A Phys., vol. 201, pp. 254–263, Oct. 2013.

[4] F. Tian, Z. Liang, L. Zhang, Y. Liu, and Z. Zhao, “A novel pattern mismatch based interference elimination technique in E-nose,” Sensors Actuators B Chem., vol. 234, pp. 703–712, Oct. 2016.