{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:26:20Z","timestamp":1773516380820,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T00:00:00Z","timestamp":1675987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001824","name":"Czech Science Foundation","doi-asserted-by":"publisher","award":["21-00579S"],"award-info":[{"award-number":["21-00579S"]}],"id":[{"id":"10.13039\/501100001824","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Czech Technical University in Prague","award":["21-00579S"],"award-info":[{"award-number":["21-00579S"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The aim of this work was to test microwave brain stroke detection and classification using support vector machines (SVMs). We tested how the nature and variability of training data and system parameters impact the achieved classification accuracy. Using experimentally verified numerical models, a large database of synthetic training and test data was created. The models consist of an antenna array surrounding reconfigurable geometrically and dielectrically realistic human head phantoms with virtually inserted strokes of arbitrary size, and different dielectric parameters in different positions. The generated synthetic data sets were used to test four different hypotheses, regarding the appropriate parameters of the training dataset, the appropriate frequency range and the number of frequency points, as well as the level of subject variability to reach the highest SVM classification accuracy. The results indicate that the SVM algorithm is able to detect the presence of the stroke and classify it (i.e., ischemic or hemorrhagic) even when trained with single-frequency data. Moreover, it is shown that data of subjects with smaller strokes appear to be the most suitable for training accurate SVM predictors with high generalization capabilities. Finally, the datasets created for this study are made available to the community for testing and developing their own algorithms.<\/jats:p>","DOI":"10.3390\/s23042031","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T02:14:11Z","timestamp":1676254451000},"page":"2031","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["On the Role of Training Data for SVM-Based Microwave Brain Stroke Detection and Classification"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7628-6031","authenticated-orcid":false,"given":"Tomas","family":"Pokorny","sequence":"first","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6528-0187","authenticated-orcid":false,"given":"Jan","family":"Vrba","sequence":"additional","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8259-0611","authenticated-orcid":false,"given":"Ondrej","family":"Fiser","sequence":"additional","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8631-4283","authenticated-orcid":false,"given":"David","family":"Vrba","sequence":"additional","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9061-8231","authenticated-orcid":false,"given":"Tomas","family":"Drizdal","sequence":"additional","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9255-2651","authenticated-orcid":false,"given":"Marek","family":"Novak","sequence":"additional","affiliation":[{"name":"Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, 166 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2089-2483","authenticated-orcid":false,"given":"Luca","family":"Tosi","sequence":"additional","affiliation":[{"name":"ELEDIA Research Center (ELEDIA@UniTN\u2014University of Trento), DICAM\u2014Department of Civil, Environmental, and Mechanical Engineering, Via Mesiano 77, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Polo","sequence":"additional","affiliation":[{"name":"ELEDIA Research Center (ELEDIA@UniTN\u2014University of Trento), DICAM\u2014Department of Civil, Environmental, and Mechanical Engineering, Via Mesiano 77, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6948-8636","authenticated-orcid":false,"given":"Marco","family":"Salucci","sequence":"additional","affiliation":[{"name":"ELEDIA Research Center (ELEDIA@UniTN\u2014University of Trento), DICAM\u2014Department of Civil, Environmental, and Mechanical Engineering, Via Mesiano 77, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"252093","DOI":"10.1155\/2012\/252093","article-title":"Microwave Imaging and Emerging Applications","volume":"2012","author":"Meaney","year":"2012","journal-title":"Int. J. Biomed. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1002\/bem.22024","article-title":"Dielectric properties of brain tissue at 1\u2009GHz in acute ischemic stroke: Experimental study on swine","volume":"38","author":"Semenov","year":"2017","journal-title":"Bioelectromagnetics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"6349","DOI":"10.1109\/TAP.2022.3177556","article-title":"Artificial Intelligence: New Frontiers in Real-Time Inverse Scattering and Electromagnetic Imaging","volume":"70","author":"Salucci","year":"2022","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1080\/09205071.2017.1402713","article-title":"Learning-by-examples techniques as applied to electromagnetics","volume":"32","author":"Massa","year":"2018","journal-title":"J. Electromagn. Waves Appl."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Oliveri, G., Rocca, P., and Massa, A. (2012, January 8\u201314). SVM for Electromagnetics: State-of-art, potentialities, and trends. Proceedings of the 2012 IEEE International Symposium on Antennas and Propagation, Chicago, IL, USA.","DOI":"10.1109\/APS.2012.6348759"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2806","DOI":"10.1109\/TBME.2014.2330554","article-title":"Microwave-Based Stroke Diagnosis Making Global Prehospital Thrombolytic Treatment Possible","volume":"61","author":"Persson","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/JERM.2020.2995329","article-title":"Stroke Classification in Simulated Electromagnetic Imaging Using Graph Approaches","volume":"5","author":"Zhu","year":"2021","journal-title":"IEEE J. Electromagn. RF Microw. Med. Biol."},{"key":"ref_8","unstructured":"Li, J., Zhu, G., and Xi, M. (November, January 31). Automating Stroke Subtype Classification from Electromagnetic Signals Using Principal Component Methods. Proceedings of the The 7th International Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII2021), Beijing, China."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Fhager, A., Candefjord, S., Elam, M., and Persson, M. (2019). 3D Simulations of Intracerebral Hemorrhage Detection Using Broadband Microwave Technology. Sensors, 19.","DOI":"10.3390\/s19163482"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1007\/s11517-016-1578-6","article-title":"Microwave technology for detecting traumatic intracranial bleedings: Tests on phantom of subdural hematoma and numerical simulations","volume":"55","author":"Candefjord","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Merunka, I., Massa, A., Vrba, D., Fiser, O., Salucci, M., and Vrba, J. (2019, April 08). Microwave Tomography System for Methodical Testing of Human Brain Stroke Detection Approaches. Available online: https:\/\/www.hindawi.com\/journals\/ijap\/2019\/4074862\/abs\/.","DOI":"10.1155\/2019\/4074862"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2796","DOI":"10.1002\/mop.30821","article-title":"Real-time brain stroke detection through a learning-by-examples technique\u2014An experimental assessment","volume":"59","author":"Salucci","year":"2017","journal-title":"Microw. Opt. Technol. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1002\/mop.31639","article-title":"Instantaneous brain stroke classification and localization from real scattering data","volume":"61","author":"Salucci","year":"2019","journal-title":"Microw. Opt. Technol. Lett."},{"key":"ref_14","unstructured":"Pokorny, T., and Tesarik, J. (2019, January 13\u201315). Microwave Stroke Detection and Classification Using Different Methods from MATLAB\u2019s Classification Learner Toolbox. Proceedings of the 2019 European Microwave Conference in Central Europe (EuMCE), Prague, Czech Republic."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Salucci, M., Polo, A., and Vrba, J. (2021). Multi-Step Learning-by-Examples Strategy for Real-Time Brain Stroke Microwave Scattering Data Inversion. Electronics, 10.","DOI":"10.3390\/electronics10010095"},{"key":"ref_16","unstructured":"(2022). COMSOL Multiphysics\u00ae, COMSOL AB. Available online: www.comsol.com."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1017\/S1759078720000835","article-title":"Dielectric sensitivity of different antennas types for microwave-based head imaging: Numerical study and experimental verification","volume":"12","author":"Tesarik","year":"2020","journal-title":"Int. J. Microw. Wirel. Technol."},{"key":"ref_18","unstructured":"Erik, G., and Lee, R.L.H. (2016). Population Head Model Repository V1.0, IT\u2019IS Foundation."},{"key":"ref_19","unstructured":"(2023, January 09). Materialize 3-Matic; Leuven, Belgium. Available online: www.materialise.com."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Said, T., and Varadan, V.V. (2009, January 7\u201312). Variation of Cole-Cole model parameters with the complex permittivity of biological tissues. Proceedings of the 2009 IEEE MTT-S International Microwave Symposium Digest, Boston, MA, USA.","DOI":"10.1109\/MWSYM.2009.5165979"},{"key":"ref_21","unstructured":"Hasgall, P.A., Di Gennnaro, F., Baumgartner, C., Neufeld, E., Lloyd, B., Gosselin, M.C., Payne, D., Klingenb\u00f6ck, A., and Kuster, N. (2018). IT\u2019IS Database for Thermal and Electromagnetic Parameters of Biological Tissues, version 4.0, IT\u2019IS Foundation."},{"key":"ref_22","unstructured":"(2013). IEEE Recommended Practice for Determining the Peak Spatial-Average Specific Absorption Rate (SAR) in the Human Head from Wireless Communications Devices: Measurement Techniques (Standard No. IEEE Std 1528-2013 Revis. IEEE Std 1528-2003)."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1136\/practneurol-2020-002763","article-title":"Acute intracerebral haemorrhage: Diagnosis and management","volume":"21","author":"McGurgan","year":"2021","journal-title":"Pract. Neurol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mariano, V., Tobon Vasquez, J.A., Casu, M.R., and Vipiana, F. (2023). Brain Stroke Classification via Machine Learning Algorithms Trained with a Linearized Scattering Operator. Diagnostics, 13.","DOI":"10.3390\/diagnostics13010023"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lhotska, L., Sukupova, L., Lackovi\u0107, I., and Ibbott, G.S. (2018, January 3\u20138). Prototype of Simplified Microwave Imaging System for Brain Stroke Follow Up. Proceedings of the World Congress on Medical Physics and Biomedical Engineering 2018, Prague, Czech Republic.","DOI":"10.1007\/978-981-10-9038-7"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Pokorny, T., Vrba, D., Tesarik, J., Rodrigues, D.B., and Vrba, J. (2019, November 25). Anatomically and Dielectrically Realistic 2.5D 5-Layer Reconfigurable Head Phantom for Testing Microwave Stroke Detection and Classification. Available online: https:\/\/www.hindawi.com\/journals\/ijap\/2019\/5459391\/.","DOI":"10.1155\/2019\/5459391"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2031\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:31:04Z","timestamp":1760121064000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2031"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,10]]},"references-count":26,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23042031"],"URL":"https:\/\/doi.org\/10.3390\/s23042031","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,10]]}}}