{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T09:05:26Z","timestamp":1776935126465,"version":"3.51.2"},"reference-count":48,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T00:00:00Z","timestamp":1665446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council (NSERC) of Canada"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Alternative fuel sources, such as hydrogen-enriched natural gas (HENG), are highly sought after by governments globally for lowering carbon emissions. Consequently, the recognition of hydrogen as a valuable zero-emission energy carrier has increased, resulting in many countries attempting to enrich natural gas with hydrogen; however, there are rising concerns over the safe use, storage, and transport of H2 due to its characteristics such as flammability, combustion, and explosivity at low concentrations (4 vol%), requiring highly sensitive and selective sensors for safety monitoring. Microfluidic-based metal\u2013oxide\u2013semiconducting (MOS) gas sensors are strong tools for detecting lower levels of natural gas elements; however, their working mechanism results in a lack of real-time analysis techniques to identify the exact concentration of the present gases. Current advanced machine learning models, such as deep learning, require large datasets for training. Moreover, such models perform poorly in data distribution shifts such as instrumental variation. To address this problem, we proposed a Sparse Autoencoder-based Transfer Learning (SAE-TL) framework for estimating the hydrogen gas concentration in HENG mixtures using limited datasets from a 3D printed microfluidic detector coupled with two commercial MOS sensors. Our framework detects concentrations of simulated HENG based on time-series data collected from a cost-effective microfluidic-based detector. This modular gas detector houses metal\u2013oxide\u2013semiconducting (MOS) gas sensors in a microchannel with coated walls, which provides selectivity based on the diffusion pace of different gases. We achieve a dominant performance with the SAE-TL framework compared to typical ML models (94% R-squared). The framework is implementable in real-world applications for fast adaptation of the predictive models to new types of MOS sensor responses.<\/jats:p>","DOI":"10.3390\/s22207696","type":"journal-article","created":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T06:13:27Z","timestamp":1665468807000},"page":"7696","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Investigation of a Sparse Autoencoder-Based Feature Transfer Learning Framework for Hydrogen Monitoring Using Microfluidic Olfaction Detectors"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6276-7483","authenticated-orcid":false,"given":"Hamed","family":"Mirzaei","sequence":"first","affiliation":[{"name":"School of Engineering, University of British Columbia Okanagan Campus, Kelowna, BC V1V 1V7, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milad","family":"Ramezankhani","sequence":"additional","affiliation":[{"name":"School of Engineering, University of British Columbia Okanagan Campus, Kelowna, BC V1V 1V7, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Earl","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of Victoria, Victoria, BC V8P 5C2, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishat","family":"Tasnim","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of Victoria, Victoria, BC V8P 5C2, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-9989","authenticated-orcid":false,"given":"Abbas S.","family":"Milani","sequence":"additional","affiliation":[{"name":"School of Engineering, University of British Columbia Okanagan Campus, Kelowna, BC V1V 1V7, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2665-7532","authenticated-orcid":false,"given":"Mina","family":"Hoorfar","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of Victoria, Victoria, BC V8P 5C2, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sagar, S.M.V., and Agarwal, A.K. (2018). Hydrogen-Enriched Compressed Natural Gas: An Alternate Fuel for IC Engines. Advances in Internal Combustion Engine Research, Springer.","DOI":"10.1007\/978-981-10-7575-9_6"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Melaina, M.W., Antonia, O., and Penev, M. (2013). Blending Hydrogen into Natural Gas Pipeline Networks: A Review of Key Issues.","DOI":"10.2172\/1219920"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sparkman, O.D., Penton, Z., and Kitson, F.G. (2011). Gas Chromatography and Mass Spectrometry: A Practical Guide, Elsevier Inc.","DOI":"10.1016\/B978-0-12-373628-4.00002-2"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1038\/s41377-018-0114-x","article-title":"Pd films on soft substrates: A visual, high-contrast and low-cost optical hydrogen sensor","volume":"8","author":"She","year":"2019","journal-title":"Light Sci. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4773","DOI":"10.1364\/OL.44.004773","article-title":"Plasmonic fiber optic hydrogen sensor using oxygen defects in nanostructured molybdenum trioxide film","volume":"44","author":"Aray","year":"2019","journal-title":"Opt. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.snb.2016.03.017","article-title":"Combined amperometric and potentiometric hydrogen sensors based on BaCe0.7Zr0.1Y0.2O3-\u03b4 proton-conducting ceramic","volume":"231","author":"Kalyakin","year":"2016","journal-title":"Sens. Actuators B Chem."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/j.snb.2015.09.110","article-title":"Potentiometric hydrogen sensors based on yttria-stabilized zirconia electrolyte (YSZ) and CdWO4 interface","volume":"223","author":"Li","year":"2016","journal-title":"Sens. Actuators B Chem."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/j.snb.2010.11.004","article-title":"Micromachined catalytic combustible hydrogen gas sensor","volume":"153","author":"Lee","year":"2011","journal-title":"Sens. Actuators B Chem."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2834","DOI":"10.1016\/j.ijhydene.2009.01.027","article-title":"Robust hydrogen detection system with a thermoelectric hydrogen sensor for hydrogen station application","volume":"34","author":"Nishibori","year":"2009","journal-title":"Int. J. Hydrog. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1016\/j.snb.2017.05.028","article-title":"MoS2 gas sensor functionalized by Pd for the detection of hydrogen","volume":"250","author":"Baek","year":"2017","journal-title":"Sens. Actuators B Chem."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1109\/LED.2003.813354","article-title":"A new Pd-oxide-Al0.3Ga0.7As MOS hydrogen sensor","volume":"24","author":"Lu","year":"2003","journal-title":"IEEE Electron. Device Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.snb.2004.12.115","article-title":"Micro-bead of nano-crystalline F-doped SnO2 as a sensitive hydrogen gas sensor","volume":"109","author":"Han","year":"2005","journal-title":"Sens. Actuators B Chem."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.snb.2004.11.092","article-title":"Hydrogen sensing characteristics of WO3 thin film conductometric sensors activated by Pt and Au catalysts","volume":"108","author":"Ippolito","year":"2005","journal-title":"Sens. Actuators B Chem."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.mseb.2017.12.036","article-title":"Semiconductor metal oxide gas sensors: A review","volume":"229","author":"Dey","year":"2018","journal-title":"Mater. Sci. Eng. B Solid-State Mater. Adv. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.snb.2016.10.048","article-title":"Characterization of channel coating and dimensions of microfluidic-based gas detectors","volume":"241","author":"Paknahad","year":"2017","journal-title":"Sens. Actuators B Chem."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"27804","DOI":"10.3390\/s151127804","article-title":"Electronic nose feature extraction methods: A review","volume":"15","author":"Yan","year":"2015","journal-title":"Sensors"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: Data mining, inference and prediction","volume":"27","author":"Hastie","year":"2005","journal-title":"Math. Intell."},{"key":"ref_18","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/S0925-2312(03)00433-8","article-title":"A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine","volume":"55","author":"Cao","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.snb.2007.01.008","article-title":"Classification of Chinese drinks by a gas sensors array and combination of the PCA with Wilks distribution","volume":"124","author":"Yin","year":"2007","journal-title":"Sens. Actuators B Chem."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bengio, Y. (2009). Learning Deep Architectures for AI, Now Publishers Inc.","DOI":"10.1561\/9781601982957"},{"key":"ref_22","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","volume":"27","author":"Baldi","year":"2012","journal-title":"Proc. ICML Workshop Unsupervised Transf. Learn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2855","DOI":"10.3390\/s17122855","article-title":"Stacked sparse auto-encoders (SSAE) based electronic nose for Chinese liquors classification","volume":"17","author":"Zhao","year":"2017","journal-title":"Sensors"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"129349","DOI":"10.1016\/j.snb.2020.129349","article-title":"Gas recognition method based on the deep learning model of sensor array response map","volume":"330","author":"Ma","year":"2021","journal-title":"Sens. Actuators B Chem."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.snb.2015.11.058","article-title":"Calibration transfer and drift compensation of e-noses via coupled task learning","volume":"225","author":"Yan","year":"2016","journal-title":"Sens. Actuators B Chem."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"129162","DOI":"10.1016\/j.snb.2020.129162","article-title":"Improving the performance of drifted\/shifted electronic nose systems by cross-domain transfer using common transfer samples","volume":"329","author":"Yi","year":"2021","journal-title":"Sens. Actuators B Chem."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"129012","DOI":"10.1016\/j.snb.2020.129012","article-title":"Classification and Regression of Binary Hydrocarbon Mixtures using Single Metal Oxide Semiconductor Sensor With Application to Natural Gas Detection","volume":"326","author":"Barriault","year":"2021","journal-title":"Sens. Actuators B Chem."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"128921","DOI":"10.1016\/j.snb.2020.128921","article-title":"Validation of the rapid detection approach for enhancing the electronic nose systems performance, using different deep learning models and support vector machines","volume":"327","author":"Gamboa","year":"2021","journal-title":"Sens. Actuators B Chem."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.jmsy.2021.02.015","article-title":"Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing","volume":"59","author":"Ramezankhani","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_31","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia. Available online: http:\/\/arxiv.org\/abs\/1703.03400."},{"key":"ref_32","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume":"4","author":"Yosinski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","unstructured":"Neyshabur, B., Sedghi, H., and Zhang, C. (2020). What is being transferred in transfer learning?. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ramezankhani, M., Narayan, A., Seethaler, R., and Milani, A.S. (2021, January 10\u201312). An Active Transfer Learning (ATL) Framework for Smart Manufacturing with Limited Data: Case Study on Material Transfer in Composites Processing. Proceedings of the 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), Victoria, BC, Canada.","DOI":"10.1109\/ICPS49255.2021.9468145"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"12555","DOI":"10.1016\/j.ijhydene.2020.08.200","article-title":"Gas detection of hydrogen\/natural gas blends in the gas industry","volume":"46","author":"Hall","year":"2020","journal-title":"Int. J. Hydrog. Energy"},{"key":"ref_36","unstructured":"Montazeri, M.M., De Vries, N., Afantchao, A., Mehrabi, P., Kim, E., O\u2019Brien, A., Najjaran, H., Hoorfar, M., and Kadota, P. (November, January 29). A sensor for nuisance sewer gas monitoring. Proceedings of the IEEE Sensors, Glasgow, UK."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ahmadou, D., Laref, R., Losson, E., and Siadat, M. (2017, January 22\u201325). Reduction of drift impact in gas sensor response to improve quantitative odor analysis. Proceedings of the IEEE International Conference on Industrial Technology (ICIT), Toronto, ON, Canada.","DOI":"10.1109\/ICIT.2017.7915484"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4322","DOI":"10.1109\/JSEN.2017.2707525","article-title":"On-Chip Electronic Nose For Wine Tasting: A Digital Microfluidic Approach","volume":"17","author":"Paknahad","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_39","first-page":"361","article-title":"Hydrogen and methane gas sensors synthesis of multi-walled carbon nanotubes","volume":"47","author":"Samarasekara","year":"2009","journal-title":"Chin. J. Phys."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"8350","DOI":"10.3390\/s140508350","article-title":"Calorimetric thermoelectric gas sensor for the detection of hydrogen, methane and mixed gases","volume":"14","author":"Park","year":"2014","journal-title":"Sensors"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.1109\/JSEN.2005.858926","article-title":"Fast and robust gas identification system using an integrated gas sensor technology and Gaussian mixture models","volume":"5","author":"Bermak","year":"2005","journal-title":"IEEE Sens. J."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.snb.2014.03.048","article-title":"Fiber optic hydrogen sensor for a continuously monitoring of the partial hydrogen pressure in the natural gas grid","volume":"199","author":"Westerwaal","year":"2014","journal-title":"Sens. Actuators B Chem."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"32318","DOI":"10.1016\/j.ijhydene.2021.06.221","article-title":"Detecting hydrogen concentrations during admixing hydrogen in natural gas grids","volume":"46","author":"Blokland","year":"2021","journal-title":"Int. J. Hydrog. Energy"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1901608","DOI":"10.1002\/adhm.201901608","article-title":"Evolving magnetically levitated plasma proteins detects opioid use disorder as a model disease","volume":"9","author":"Ashkarran","year":"2020","journal-title":"Adv. Healthc. Mater."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1109\/JSEN.2017.2657653","article-title":"Application of random forest classifier by means of a QCM-based e-nose in the identification of Chinese liquor flavors","volume":"17","author":"Li","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_46","first-page":"3146","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1007\/s42114-019-00107-6","article-title":"A multi-objective Gaussian process approach for optimization and prediction of carbonization process in carbon fiber production under uncertainty","volume":"2","author":"Ramezankhani","year":"2019","journal-title":"Adv. Compos. Hybrid Mater."},{"key":"ref_48","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7696\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:49:40Z","timestamp":1760143780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,11]]},"references-count":48,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22207696"],"URL":"https:\/\/doi.org\/10.3390\/s22207696","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,11]]}}}