Local Manifold Embedding Cross-Domain Subspace Learning for Drift Compensation of Electronic Nose Data

被引:28
|
作者
Tian, Yutong [1 ]
Yan, Jia [2 ,3 ]
Yi, Danhong [2 ,3 ]
Zhang, Yuelin [1 ]
Wang, Zehuan [1 ]
Yu, Tianhang [1 ]
Peng, Xiaoyan [2 ,3 ]
Duan, Shukai [2 ,3 ]
机构
[1] Southwest Univ, WESTA Coll, Chongqing 400715, Peoples R China
[2] Southwest Univ, Coll Artificial Intelligence, Chongqing 400715, Peoples R China
[3] Southwest Univ, Minist Educ, Key Lab Luminescence Anal & Mol Sensing, Chongqing 400715, Peoples R China
基金
中国国家自然科学基金;
关键词
Drift compensation; electronic nose (E-nose); manifold learning; subspace learning; GAS SENSOR; CALIBRATION TRANSFER; RECOGNITION; REDUCTION; ARRAYS; CLASSIFICATION; SYSTEMS;
D O I
10.1109/TIM.2021.3108529
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The gas sensor drift problem arises from the bias of data, which is known as a significant problem in the artificial olfactory community. Traditionally, hardware calibration methods are laborious and ineffective due to frequent recalibration actions involving different gases, and some calibration transfer and baseline calibration methods are not effective enough. In this work, a local manifold embedding cross-domain subspace learning (LME-CDSL) model is proposed based on domain distribution alignment. It is a unified subspace learning model combined with manifold learning and domain adaptation, which tends to explore a latent transform matrix that not only enforces the drifted target domain data to learn the manifold of nondrifted source domain data but also adopts the domain adaptation method to align the domain data distribution. In general, the LME-CDSL model has three features: 1) the unsupervised and adaptation distribution subspace projection can be easily computed through eigenvector decomposition; 2) the local linear manifold learns to achieve the compact representations of high-dimensional data and is capable of preserving the local features of nondrifted samples; and 3) the domain adaptation part utilizes the maximum mean discrepancy (MMD) and variance maximization to make the sample distributions of different domains more similar and preserve the intrinsic properties. For long-term and short-term drift compensation on a single E-nose system, the local manifold embedding cross- domain subspace learning (LME-CDSL) model obtains the average recognition accuracy of 70.95% and 74.09%, respectively, while 71.71% and 73.96%, respectively for multiple identical E-nose systems with both long-term and interplate drift, which are higher than several comparative methods and proves the its effectiveness and superiority on anti-drift and gas recognition.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Sparse and Low-Rank Subspace Data Clustering with Manifold Regularization Learned by Local Linear Embedding
    Yang, Ye
    Hu, Yongli
    Wu, Fei
    APPLIED SCIENCES-BASEL, 2018, 8 (11):
  • [42] Probability-Based Graph Embedding Cross-Domain and Class Discriminative Feature Learning for Domain Adaptation
    Wang, Wenxu
    Shen, Zhencai
    Li, Daoliang
    Zhong, Ping
    Chen, Yingyi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 72 - 87
  • [43] Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation
    Liu, Weiming
    Chen, Chaochao
    Liao, Xinting
    Hu, Mengling
    Tan, Yanchao
    Wang, Fan
    Zheng, Xiaolin
    Ong, Yew-Soon
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 8, 2024, : 8815 - 8823
  • [44] Unsupervised Joint Subspace and Dictionary Learning for Enhanced Cross-Domain Person Re-Identification
    Qi, Lei
    Huo, Jing
    Fan, Xiaocong
    Shi, Yinghuan
    Gao, Yang
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2018, 12 (06) : 1263 - 1275
  • [45] A cross-domain fault diagnosis method based on pseudo-label driving local subspace alignment
    Zhang M.
    Wang B.
    Xu H.
    Yang W.
    Wang C.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2023, 42 (20): : 105 - 113
  • [46] Learning Low-Shot Generative Networks for Cross-Domain Data
    Kao, Hsuan-Kai
    Lee, Cheng-Che
    Chiu, Wei-Chen
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 6818 - 6825
  • [47] Drift compensation on electronic nose data for non-invasive diagnosis of prostate cancer by urine analysis
    Bax, Carmen
    Prudenza, Stefano
    Gaspari, Giulia
    Capelli, Laura
    Grizzi, Fabio
    Taverna, Gianluigi
    ISCIENCE, 2022, 25 (01)
  • [48] Global-Local Dynamic Adversarial Learning for Cross-Domain Sentiment Analysis
    Lyu, Juntao
    Zhang, Zheyuan
    Chen, Shufeng
    Fan, Xiying
    MATHEMATICS, 2023, 11 (14)
  • [49] Improving the performance of drifted/shifted electronic nose systems by cross-domain transfer using common transfer samples
    Yi, Ruonan
    Yan, Jia
    Shi, Debo
    Tian, Yutong
    Chen, Feiyue
    Wang, Zijian
    Duan, Shukai
    SENSORS AND ACTUATORS B-CHEMICAL, 2021, 329
  • [50] Online Sensor Drift Compensation for E-Nose Systems Using Domain Adaptation and Extreme Learning Machine
    Ma, Zhiyuan
    Luo, Guangchun
    Qin, Ke
    Wang, Nan
    Niu, Weina
    SENSORS, 2018, 18 (03):