{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T22:17:25Z","timestamp":1790720245889,"version":"4.1.0"},"reference-count":43,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science and Technology, Taiwan","award":["109-2221-E-002-204-MY2"],"award-info":[{"award-number":["109-2221-E-002-204-MY2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents the results on developing an ensemble machine learning model to combine commercial gas sensors for accurate concentration detection. Commercial gas sensors have the low-cost advantage and become key components of IoT devices in atmospheric condition monitoring. However, their native coarse resolution and poor selectivity limit their performance. Thus, we adopted recurrent neural network (RNN) models to extract the time-series concentration data characteristics and improve the detection accuracy. Firstly, four types of RNN models, LSTM and GRU, Bi-LSTM, and Bi-GRU, were optimized to define the best-performance single weak models for CO, O3, and NO2 gases, respectively. Next, ensemble models which integrate multiple single weak models with a dynamic model were defined and trained. The testing results show that the ensemble models perform better than the single weak models. Further, a retraining procedure was proposed to make the ensemble model more flexible to adapt to environmental conditions. The significantly improved determination coefficients show that the retraining helps the ensemble models maintain long-term stable sensing performance in an atmospheric environment. The result can serve as an essential reference for the applications of IoT devices with commercial gas sensors in environment condition monitoring.<\/jats:p>","DOI":"10.3390\/s22124393","type":"journal-article","created":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T02:01:44Z","timestamp":1655085704000},"page":"4393","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Ensemble Machine Learning Model for Accurate Air Pollution Detection Using Commercial Gas Sensors"],"prefix":"10.3390","volume":"22","author":[{"given":"Wei-In","family":"Lai","sequence":"first","affiliation":[{"name":"Institute of Applied Mechanics, National Taiwan University, Taipei 106, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Materials Engineering, Tatung University, Taipei 104, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-9160","authenticated-orcid":false,"given":"Jia-Hong","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Chang Gung University, Taoyuan 333, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1016\/S0140-6736(02)11274-8","article-title":"Air pollution and health","volume":"360","author":"Brunekreef","year":"2002","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.envpol.2007.06.012","article-title":"Human health effects of air pollution","volume":"151","author":"Kampa","year":"2008","journal-title":"Environ. Pollut."},{"key":"ref_3","unstructured":"(2021, September 22). Greenpeace International. WHO Strengthens Air Quality Guidelines: Greenpeace Response. Available online: https:\/\/www.greenpeace.org\/international\/press-release\/49648\/who-strengthens-air-quality-guidelines-greenpeace-response\/."},{"key":"ref_4","unstructured":"European Environment Agency (2019). Air Quality in Europe\u20142018 Report."},{"key":"ref_5","unstructured":"European Parliament (2019). Sampling Points for Air Quality."},{"key":"ref_6","unstructured":"UNION (2008). Directive 2008\/50\/EC of the European Parliament and of the Council of 21 May 2008 on ambient air quality and cleaner air for Europe. Off. J. Eur. Union, 1\u201344."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Marinello, S., Andretta, M., Lucialli, P., Pollini, E., and Righi, S. (2021). A Methodology for Designing Short-Term Stationary Air Quality Campaigns with Mobile Laboratories Using Different Possible Allocation Criteria. Sustainability, 13.","DOI":"10.3390\/su13137481"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104620","DOI":"10.1016\/j.envsoft.2019.104620","article-title":"Re-framing the Gaussian dispersion model as a nonlinear regression scheme for retrospective air quality assessment at a high spatial and temporal resolution","volume":"125","author":"Chen","year":"2020","journal-title":"Environ. Model. Softw."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Karagulian, F., Barbiere, M., Kotsev, A., Spinelle, L., Gerboles, M., Lagler, F., Redon, N., Crunaire, S., and Borowiak, A. (2019). Review of the performance of low-cost sensors for air quality monitoring. Atmosphere, 10.","DOI":"10.3390\/atmos10090506"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"109438","DOI":"10.1016\/j.envres.2020.109438","article-title":"Low-cost sensors as an alternative for long-term air quality monitoring","volume":"185","author":"Liu","year":"2020","journal-title":"Environ. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.envint.2018.04.018","article-title":"Applications of low-cost sensing technologies for air quality monitoring and exposure assessment: How far have they gone?","volume":"116","author":"Morawska","year":"2018","journal-title":"Environ. Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.envint.2016.12.007","article-title":"Can commercial low-cost sensor platforms contribute to air quality monitoring and exposure estimates?","volume":"99","author":"Castell","year":"2017","journal-title":"Environ. Int."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.proche.2009.07.051","article-title":"Selective modified SnO2-based materials for gas sensors arrays","volume":"1","author":"Krivetsky","year":"2009","journal-title":"Procedia Chem."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/j.snb.2016.06.037","article-title":"Highly sensitive and selective ammonia gas sensors based on PbS quantum dots\/TiO2 nanotube arrays at room temperature","volume":"236","author":"Liu","year":"2016","journal-title":"Sens. Actuators B Chem."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.matchemphys.2012.12.002","article-title":"Gas sensing characteristics of MEMS gas sensor arrays in binary mixed-gas system","volume":"138","author":"Kim","year":"2013","journal-title":"Mater. Chem. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/j.talanta.2008.12.031","article-title":"Quartz crystal microbalance sensor array for the detection of volatile organic compounds","volume":"78","author":"Xu","year":"2009","journal-title":"Talanta"},{"key":"ref_17","first-page":"229","article-title":"Quantitative recognition of flammable and toxic gases with artificial neural network using metal oxide gas sensors in embedded platform","volume":"18","author":"Mondal","year":"2015","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.psep.2016.05.014","article-title":"SAW mono sensor for identification of harmful vapors using PCA and ANN","volume":"102","author":"Singh","year":"2016","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1016\/j.snb.2016.07.036","article-title":"Field calibration of a cluster of low-cost commercially available sensors for air quality monitoring. Part B: NO, CO and CO2","volume":"238","author":"Spinelle","year":"2017","journal-title":"Sens. Actuators B Chem."},{"key":"ref_20","first-page":"1","article-title":"Low cost sensor with IoT LoRaWAN connectivity and machine learning-based calibration for air pollution monitoring","volume":"70","author":"Ali","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","unstructured":"Zaremba, W., Sutskever, I., and Vinyals, O. (2014). Recurrent neural network regularization. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10772-018-09573-7","article-title":"Long short-term memory recurrent neural network architectures for Urdu acoustic modeling","volume":"22","author":"Zia","year":"2019","journal-title":"Int. J. Speech Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_24","unstructured":"Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Processing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.procs.2020.03.036","article-title":"Air quality forecasting using LSTM RNN and wireless sensor networks","volume":"170","author":"Belavadi","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, T., Song, S., Li, S., Ma, L., Pan, S., and Han, L. (2019). Research on gas concentration prediction models based on LSTM multidimensional time series. Energies, 12.","DOI":"10.3390\/en12010161"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xie, T., and Wang, S. (December, January 30). Research on Air Pollution Gases Recognition Method Based on LSTM Recurrent Neural Network and Gas Sensors Array. Proceedings of the 2018 Chinese Automation Congress (CAC), Xi\u2019an, China.","DOI":"10.1109\/CAC.2018.8623060"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.apr.2020.11.010","article-title":"Assessment of air quality sensor system performance after relocation","volume":"12","author":"Marchesi","year":"2021","journal-title":"Atmos. Pollut. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, C., and Ma, Y. (2012). Ensemble Machine Learning: Methods and Applications, Springer.","DOI":"10.1007\/978-1-4419-9326-7"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e1249","DOI":"10.1002\/widm.1249","article-title":"Ensemble learning: A survey","volume":"8","author":"Sagi","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"Opitz","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G. (2000, January 21\u201323). Ensemble Methods in Machine Learning. Proceedings of the International Workshop on Multiple Classifier Systems, Cagliari, Italy.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","article-title":"Ensemble based systems in decision making","volume":"6","author":"Polikar","year":"2006","journal-title":"IEEE Circuits Syst. Mag."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-009-9124-7","article-title":"Ensemble-based classifiers","volume":"33","author":"Rokach","year":"2010","journal-title":"Artif. Intell. Rev."},{"key":"ref_36","first-page":"97","article-title":"That \u2018internet of things\u2019 thing","volume":"22","author":"Ashton","year":"2009","journal-title":"RFID J."},{"key":"ref_37","unstructured":"(2021, September 22). SPEC Sensors. Available online: https:\/\/www.spec-sensors.com\/?msclkid=b1661434bd4311ecadb51848a563b139."},{"key":"ref_38","unstructured":"Environmental Protection Administration (Taiwan) (2021, September 22). Air Quality Annual Report of R.O.C (Taiwan) 2020, Available online: chrome-extension:\/\/efaidnbmnnnibpcajpcglclefindmkaj\/https:\/\/www.epa.gov.tw\/DisplayFile.aspx?FileID=6BB17C4B4AD72C76."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.-P., Ng, R.T., and Sander, J. (2000, January 16\u201318). LOF: Identifying Density-Based Local Outliers. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, Dallas, TX, USA.","DOI":"10.1145\/342009.335388"},{"key":"ref_40","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_41","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1214\/aos\/1176348768","article-title":"Variable kernel density estimation","volume":"20","author":"Terrell","year":"1992","journal-title":"Ann. Stat."},{"key":"ref_43","unstructured":"(2021, September 22). AQ-SPEC, Available online: http:\/\/www.aqmd.gov\/aq-spec\/evaluations\/summary-gas?fbclid=IwAR1Na0WAP5uF-eAND8zlbpqKnprzE-i3OEER0WdS5n0HhbsXOtLR0sLyoAs."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/12\/4393\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:27:33Z","timestamp":1760138853000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/12\/4393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":43,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["s22124393"],"URL":"https:\/\/doi.org\/10.3390\/s22124393","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,10]]}}}