{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:01:08Z","timestamp":1783929668367,"version":"3.55.0"},"reference-count":31,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T00:00:00Z","timestamp":1567641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key Research","award":["2018YFC0807900"],"award-info":[{"award-number":["2018YFC0807900"]}]},{"name":"Development Program of China","award":["2018YFC0807903"],"award-info":[{"award-number":["2018YFC0807903"]}]},{"name":"National Nature Science Foundation under Grant","award":["61702020"],"award-info":[{"award-number":["61702020"]}]},{"name":"Beijing Nature Science Foundation Grant","award":["4172013"],"award-info":[{"award-number":["4172013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Drift is an important issue that impairs the reliability of sensors, especially in gas sensors. The conventional method usually adopts the reference gas to compensate for the drift. However, its classification accuracy is not high. We propose a supervised learning algorithm that is based on multi-classifier integration for drift compensation in this paper, which incorporates drift compensation into the classification process, motivated by the fact that the goal of drift compensation is to improve the classification performance. In our method, with the obtained characteristics of sensors and the advantage of Support Vector Machine (SVM) in few-shot classification, the improved Long Shot Term Memory (LSTM) is integrated to build the multi-class classifier model. We tested the proposed approach on the publicly available time series dataset that was collected over three years by the metal-oxide gas sensors. The results clearly indicate the superiority of multiple classifier approach, which achieves higher classification accuracy as compared with different approaches during testing period with an ensemble of classifiers in the presence of sensor drift over time.<\/jats:p>","DOI":"10.3390\/s19183844","type":"journal-article","created":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T02:59:22Z","timestamp":1567738762000},"page":"3844","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["Sensor Drift Compensation Based on the Improved LSTM and SVM Multi-Class Ensemble Learning Models"],"prefix":"10.3390","volume":"19","author":[{"given":"Xia","family":"Zhao","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaitai","family":"Xiao","sequence":"additional","affiliation":[{"name":"Shenyang Research Institute of China Coal Technology and Engineering Group, Fushun 113122, China"},{"name":"State Key Laboratory of Coal Mine Safety Technology, Shenyang Branch of China Coal Research Institute, Shenyang 110016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangning","family":"Meng","sequence":"additional","affiliation":[{"name":"Shenyang Research Institute of China Coal Technology and Engineering Group, Fushun 113122, China"},{"name":"State Key Laboratory of Coal Mine Safety Technology, Shenyang Branch of China Coal Research Institute, Shenyang 110016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongchong","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,9,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Liu, Q., Zhou, S., Cheng, X., Cheng, H., and Zhang, H. (2017, January 10\u201311). Gas Sensor Drift Compensation by an Optimal Linear Transformation. Proceedings of the 2017 3rd International Conference on Big Data Computing and Communications (BIGCOM) IEEE, Chengdu, China.","DOI":"10.1109\/BIGCOM.2017.64"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/S0925-4005(97)80272-9","article-title":"Qualitative and quantitative analysis of volatile organic compounds using transient and steady-state responses of a thick-film tin oxide gas sensor array","volume":"41","author":"Llobet","year":"1997","journal-title":"Sens. Actuators B Chem."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ma, Z., Luo, G., Qin, K., Wang, N., and Niu, W. (2018). Online Sensor Drift Compensation for E-Nose Systems Using Domain Adaptation and Extreme Learning Machine. Sensors, 18.","DOI":"10.3390\/s18030742"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"267","DOI":"10.3390\/s7030267","article-title":"Gas Sensors Based on Conducting Polymers","volume":"7","author":"Bai","year":"2007","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.snb.2009.04.026","article-title":"Gas sensors using hierarchical and hollow oxide nanostructures: Overview","volume":"140","author":"Lee","year":"2009","journal-title":"Sens. Actuators B Chem."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1109\/JSEN.2018.2881745","article-title":"Heuristic Random Forests (HRF) for Drift Compensation in Electronic Nose Applications","volume":"19","author":"Bermak","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.snb.2012.01.074","article-title":"Chemical gas sensor drift compensation using classifier ensembles","volume":"166\u2013167","author":"Vergara","year":"2012","journal-title":"Sens. Actuators B Chem."},{"key":"ref_8","unstructured":"Brahimbelhouari, S., Bermak, A., and Chan, P.C.H. (2004, January 17\u201321). Gas identification with microelectronic gas sensor in presence of drift using robust GMM. Proceedings of the IEEE International Conference on Acoustics IEEE, Montreal, QC, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, T., Li, D., Chen, J., Chen, Y., Yang, T., and Cao, J. (2018). Gas-Sensor Drift Counteraction with Adaptive Active Learning for an Electronic Nose. Sensors, 18.","DOI":"10.3390\/s18114028"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/S0925-4005(02)00247-2","article-title":"On the Study of Feature Extraction Methods for an Electronic Nose","volume":"87","author":"Distante","year":"2002","journal-title":"Sens. Actuators B Chem."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/S0925-4005(03)00247-8","article-title":"A feature extraction method for chemical sensors in electronic noses","volume":"69","author":"Carmela","year":"2003","journal-title":"Sens. Actuators B Chem."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1002\/1099-128X(200009\/12)14:5\/6<711::AID-CEM607>3.0.CO;2-4","article-title":"Drift correction for gas sensors using multivariate methods","volume":"14","author":"Artursson","year":"2000","journal-title":"J. Chemom."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.chemolab.2009.10.002","article-title":"Drift compensation of gas sensor array data by Orthogonal Signal Correction","volume":"100","author":"Padilla","year":"2010","journal-title":"Chem. Intell. Lab. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1002\/int.21731","article-title":"Gas Recognition under Sensor Drift by Using Deep Learning","volume":"30","author":"Liu","year":"2015","journal-title":"Int. J. Intell. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"David, E., and Netanyahu, N.S. (2015). DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification. Int. Jt. Conf. Neural Netw. (IJCNN), 1\u20138.","DOI":"10.1109\/IJCNN.2015.7280815"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/JSTARS.2014.2329330","article-title":"Deep Learning-Based Classification of Hyperspectral Data","volume":"7","author":"Chen","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","article-title":"Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks","volume":"13","author":"Marmanis","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Adhikari, S., and Saha, S. (2014, January 21\u201322). Multiple classifier combination technique for sensor drift compensation using ANN & KNN. Proceedings of the 2014 IEEE International Advance Computing Conference (IACC), Gurgaon, India.","DOI":"10.1109\/IAdCC.2014.6779495"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1790","DOI":"10.1109\/TIM.2014.2367775","article-title":"Domain Adaptation Extreme Learning Machines for Drift Compensation in E-Nose Systems","volume":"64","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/JSEN.2013.2285919","article-title":"Drift Compensation for Electronic Nose by Semi-Supervised Domain Adaption","volume":"14","author":"Liu","year":"2014","journal-title":"IEEE Sens. J."},{"key":"ref_21","first-page":"95","article-title":"Sensor drift compensation method based on cyclic neural network","volume":"27","author":"Wenwei","year":"2005","journal-title":"Comput. Eng. Sci."},{"key":"ref_22","first-page":"772","article-title":"Exploring LSTM based recurrent neural network for failure time series prediction","volume":"44","author":"Wang","year":"2018","journal-title":"J. Beijing Univ. Aeronaut. Astronaut."},{"key":"ref_23","first-page":"38","article-title":"An emotion analysis model combining deep learning and emsemble learning","volume":"50","author":"Zhigang","year":"2018","journal-title":"J. Harbin Inst. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1109\/19.744316","article-title":"Nonlinear inverse dynamic models of gas sensing systems based on chemical sensor arrays for quantitative measurements","volume":"47","author":"Pardo","year":"1998","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.snb.2008.10.065","article-title":"Acceleration of chemo-sensory information processing using transient features","volume":"137","author":"Muezzinoglu","year":"2009","journal-title":"Sens. Actuators B Chem."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4704","DOI":"10.1109\/JSEN.2018.2820170","article-title":"The Order Statistics Correlation Coefficient and PPMCC Fuse Non-Dimension in Fault Diagnosis of Rotating Petrochemical Unit","volume":"18","author":"Xiong","year":"2018","journal-title":"IEEE Sens. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1093\/jamia\/ocw112","article-title":"Using recurrent neural network models for early detection of heart failure onset","volume":"24","author":"Choi","year":"2016","journal-title":"J. Am. Med. Inform. Assoc. JAMIA"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/JSEN.2015.2497277","article-title":"A Regularized Ensemble of Classifiers for Sensor Drift Compensation","volume":"16","author":"Verma","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4919","DOI":"10.1109\/JSEN.2016.2551743","article-title":"A Novel Semi-Supervised Learning Approach in Artificial Olfaction for E-Nose Application","volume":"16","author":"Zhang","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MSP.2018.2826566","article-title":"Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery","volume":"35","author":"Namrata","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_31","unstructured":"Sch\u00f6lkopf, B., Chapelle, O., and Zien, A. (2013). Semi-Supervised Learning. Handbook on Neural Information Processing, Springer."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/18\/3844\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:17:18Z","timestamp":1760188638000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/18\/3844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,5]]},"references-count":31,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2019,9]]}},"alternative-id":["s19183844"],"URL":"https:\/\/doi.org\/10.3390\/s19183844","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,5]]}}}