Improving the Robustness of Prediction Model by Transfer Learning for Interference Suppression of Electronic Nose
Improving the Robustness of Prediction Model by Transfer Learning for Interference Suppression of Electronic Nose
复制标题
通过迁移学习提高电子鼻干扰抑制预测模型的鲁棒性
DOI：
10.1109/jsen.2017.2778012
复制
发表时间：
2018-02
影响因子：
4.3
通讯作者：
Tao Liu
中科院分区：
文献类型：
--
作者：
Zhifang Liang;Fengchun Tian;Ci Zhang;Hao Sun;An Song;Tao Liu
针对电子鼻不稳定行为的不确定性和不可预测性，提出了一种解决电子鼻干扰问题的方法。传统的干扰抑制方法是分量校正框架，其费力或效率低。在干扰（特别是背景干扰和传感器漂移）的影响下，实际应用中得到的测试数据的分布与以前训练数据的分布不同。从机器学习的角度出发，提出了一种新型的具有转移能力的域校正和自适应极端学习机（DC-AELM）框架，以解决电子鼻中严重的干扰问题。该框架由两部分组成：1）DC，使两个域的分布接近; 2）AELM，实现决策层的知识转移，提高预测模型的鲁棒性。该方法借鉴了迁移学习的思想，特别是从领域修正和决策的角度出发，实现了干扰抑制的知识迁移。通过电子鼻获得的背景干扰数据集和公共基准传感器漂移数据集验证了DC-AELM方法的有效性。
This paper gives a solution to solve the interference problem of electronic nose (e-nose), which is ill-posed due to the uncertainty and unpredictability of its instable behavior. Traditional methods for interference suppression are component correction frameworks, which are laborious or little efficient. With interference (especially background interference and sensor drift), the distribution of test data obtained in practical application is different from that of the previous training data. From the viewpoint of machine learning, a novel domain correction and adaptive extreme learning machines (DC-AELM) framework with transferring capability is proposed to solve the serious interference problem in e-nose. The framework consists of two parts: 1) DC, which makes the distributions of two domains close and 2) AELM, which realizes the knowledge transfer at the decision level and makes the robustness of the prediction model improved. This method is motivated by the idea of transfer learning, especially from the perspective of domain correction and decision-making, to realize the knowledge transfer for interference suppression. A background interference data set obtained by our designed e-nose and a public benchmark sensor drift data set are used to verify the effectiveness of the proposed DC-AELM method.
登录
查看更多内容
DOI：
10.1016/j.chemolab.2009.10.002
发表时间：
2010-01-15
影响因子：
3.9
作者：
Padilla, M.;Perera, A.;Marco, S.
通讯作者：
Marco, S.
影响因子：
8.4
作者：
Green, Geoffrey C.;Chan, Adrian D. C.;Lin, Min
通讯作者：
Lin, Min
影响因子：
6
作者：
Huang, Guang-Bin;Zhu, Qin-Yu;Siew, Chee-Kheong
通讯作者：
Siew, Chee-Kheong
影响因子：
8.4
作者：
M. Zuppa;C. Distante;P. Siciliano;K. Persaud
通讯作者：
M. Zuppa;C. Distante;P. Siciliano;K. Persaud
DOI：
10.1109/tim.2009.2016874
发表时间：
2009-05
影响因子：
5.6
作者：
B. Tudu;A. Metla;Barun Das;N. Bhattacharyya;A. Jana;D. Ghosh;R. Bandyopadhyay
通讯作者：
B. Tudu;A. Metla;Barun Das;N. Bhattacharyya;A. Jana;D. Ghosh;R. Bandyopadhyay