{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T09:48:12Z","timestamp":1777974492777,"version":"3.51.4"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,4,16]],"date-time":"2020-04-16T00:00:00Z","timestamp":1586995200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,4,16]],"date-time":"2020-04-16T00:00:00Z","timestamp":1586995200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioMed Eng OnLine"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>Generally, brain\u2013computer interfaces (BCIs) require calibration before usage to ensure efficient performance. Therefore, each BCI user has to attend a certain number of calibration sessions to be able to use the system. However, such calibration requirements may be difficult to fulfill especially for patients with disabilities. In this paper, we introduce a probabilistic transfer learning approach to reduce the calibration requirements of our EEG\u2013fTCD hybrid BCI designed using motor imagery (MI) and flickering mental rotation (MR)\/word generation (WG) paradigms. The proposed approach identifies the top similar datasets from previous BCI users to a small training dataset collected from a current BCI user and uses these datasets to augment the training data of the current BCI user. To achieve such an aim, EEG and fTCD feature vectors of each trial were projected into scalar scores using support vector machines. EEG and fTCD class conditional distributions were learnt separately using the scores of each class. Bhattacharyya distance was used to identify similarities between class conditional distributions obtained using training trials of the current BCI user and those obtained using trials of previous users.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>Experimental results showed that the performance obtained using the proposed transfer learning approach outperforms the performance obtained without transfer learning for both MI and flickering MR\/WG paradigms. In particular, it was found that the calibration requirements can be reduced by at least 60.43% for the MI paradigm, while at most a reduction of 17.31% can be achieved for the MR\/WG paradigm.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Conclusions<\/jats:title>\n<jats:p>Data collected using the MI paradigm show better generalization across subjects.<\/jats:p>\n<\/jats:sec>","DOI":"10.1186\/s12938-020-00765-4","type":"journal-article","created":{"date-parts":[[2020,4,16]],"date-time":"2020-04-16T16:04:36Z","timestamp":1587053076000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A probabilistic approach for calibration time reduction in hybrid EEG\u2013fTCD brain\u2013computer interfaces"],"prefix":"10.1186","volume":"19","author":[{"given":"Aya","family":"Khalaf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murat","family":"Akcakaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,4,16]]},"reference":[{"issue":"6","key":"765_CR1","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/S1388-2457(02)00057-3","volume":"113","author":"JR Wolpaw","year":"2002","unstructured":"Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM. Brain\u2013computer interfaces for communication and control. Clin Neurophysiol. 2002;113(6):767\u201391.","journal-title":"Clin Neurophysiol"},{"issue":"6","key":"765_CR2","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1016\/0013-4694(88)90149-6","volume":"70","author":"LA Farwell","year":"1988","unstructured":"Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol. 1988;70(6):510\u201323.","journal-title":"Electroencephalogr Clin Neurophysiol"},{"key":"765_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2013\/187024","volume":"2013","author":"S Amiri","year":"2013","unstructured":"Amiri S, Fazel-Rezai R, Asadpour V. A review of hybrid brain\u2013computer interface systems. Adv Hum\u2013Comput Interact. 2013;2013:1\u20138.","journal-title":"Adv Hum\u2013Comput Interact"},{"issue":"11","key":"765_CR4","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1016\/j.tibtech.2010.08.002","volume":"28","author":"B-K Min","year":"2010","unstructured":"Min B-K, Marzelli MJ, Yoo S-S. Neuroimaging-based approaches in the brain\u2013computer interface. Trends Biotechnol. 2010;28(11):552\u201360.","journal-title":"Trends Biotechnol"},{"issue":"3","key":"765_CR5","doi-asserted-by":"publisher","first-page":"036014","DOI":"10.1088\/1741-2552\/ab0b7f","volume":"16","author":"A Khalaf","year":"2019","unstructured":"Khalaf A, Sejdic E, Akcakaya M. EEG-fTCD hybrid brain\u2013computer interface using template matching and wavelet decomposition. J Neural Eng. 2019;16(3):036014.","journal-title":"J Neural Eng"},{"key":"765_CR6","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.jneumeth.2019.03.018","volume":"320","author":"A Khalaf","year":"2019","unstructured":"Khalaf A, Sejdic E, Akcakaya M. Common spatial pattern and wavelet decomposition for motor imagery EEG\u2013fTCD brain\u2013computer interface. J Neurosci Methods. 2019;320:98\u2013106.","journal-title":"J Neurosci Methods"},{"issue":"1","key":"765_CR7","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MCI.2015.2501545","volume":"11","author":"V Jayaram","year":"2016","unstructured":"Jayaram V, Alamgir M, Altun Y, Scholkopf B, Grosse-Wentrup M. Transfer learning in brain\u2013computer interfaces Abstract \\uFFFD The performance of brain\u2013computer interfaces (BCIs) improves with the amount of avail. IEEE Comput Intell Mag. 2016;11(1):20\u201331.","journal-title":"IEEE Comput Intell Mag"},{"issue":"10","key":"765_CR8","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345\u201359.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"765_CR9","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/86.895946","volume":"8","author":"H Ramoser","year":"2000","unstructured":"Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabil Eng. 2000;8(4):441\u20136.","journal-title":"IEEE Trans Rehabil Eng"},{"key":"765_CR10","doi-asserted-by":"crossref","unstructured":"Sybeldon M, Schmit L, Sejdic E, Akcakaya M. Transfer learning for EEG based BCI using LEARN++. NSE and mutual information. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). 2017. pp. 2632\u20136.","DOI":"10.1109\/ICASSP.2017.7952633"},{"issue":"5","key":"765_CR11","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1109\/TBME.2017.2742541","volume":"65","author":"P Zanini","year":"2018","unstructured":"Zanini P, Congedo M, Jutten C, Said S, Berthoumieu Y. Transfer learning: a Riemannian geometry framework with applications to brain\u2013computer interfaces. IEEE Trans Biomed Eng. 2018;65(5):1107\u201316.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"2","key":"765_CR12","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1109\/TBME.2019.2913914","volume":"67","author":"H He","year":"2020","unstructured":"He H, Wu D. Transfer learning for brain\u2013computer interfaces: a Euclidean space data alignment approach. IEEE Trans Biomed Eng. 2020;67(2):399\u2013410.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"7","key":"765_CR13","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1109\/TNSRE.2019.2923315","volume":"27","author":"AM Azab","year":"2019","unstructured":"Azab AM, Mihaylova L, Ang KK, Arvaneh M. Weighted transfer learning for improving motor imagery-based brain\u2013computer interface. IEEE Trans Neural Syst Rehabil Eng. 2019;27(7):1352\u20139.","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"2","key":"765_CR14","doi-asserted-by":"publisher","first-page":"026007","DOI":"10.1088\/1741-2552\/aaf3f6","volume":"16","author":"F Fahimi","year":"2019","unstructured":"Fahimi F, Zhang Z, Goh WB, Lee T-S, Ang KK, Guan C. Inter-subject transfer learning with an end-to-end deep convolutional neural network for EEG-based BCI. J Neural Eng. 2019;16(2):026007.","journal-title":"J Neural Eng"},{"key":"765_CR15","unstructured":"Ozdenizci O, Wang Y, Koike-Akino T, Erdogmus D. Transfer learning in brain\u2013computer interfaces with adversarial variational autoencoders. In: International IEEE\/EMBS Conference on Neural Engineering, NER. 2019, vol. 2019-March, pp. 207\u201310."},{"issue":"2","key":"765_CR16","doi-asserted-by":"publisher","first-page":"172988141984086","DOI":"10.1177\/1729881419840860","volume":"16","author":"C Tan","year":"2019","unstructured":"Tan C, Sun F, Fang B, Kong T, Zhang W. Autoencoder-based transfer learning in brain\u2013computer interface for rehabilitation robot. Int J Adv Robot Syst. 2019;16(2):172988141984086.","journal-title":"Int J Adv Robot Syst"},{"issue":"1","key":"765_CR17","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/j.1552-6569.2006.00088.x","volume":"17","author":"AV Alexandrov","year":"2007","unstructured":"Alexandrov AV, Sloan MA, Wong LKS, Douville C, Razumovsky AY, Koroshetz WJ, Kaps M, Tegeler CH. Practice standards for transcranial doppler ultrasound: part I\u2014test performance. J Neuroimaging. 2007;17(1):11\u20138.","journal-title":"J Neuroimaging"},{"issue":"4","key":"765_CR18","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1023\/A:1026412811036","volume":"10","author":"N Stroobant","year":"2000","unstructured":"Stroobant N, Vingerhoets G. Transcranial Doppler ultrasonography monitoring of cerebral hemodynamics during performance of cognitive tasks: a review. Neuropsychol Rev. 2000;10(4):213\u201331.","journal-title":"Neuropsychol Rev"},{"issue":"6","key":"765_CR19","doi-asserted-by":"publisher","first-page":"972","DOI":"10.3171\/jns.1995.82.6.0972","volume":"82","author":"LH Monsein","year":"1995","unstructured":"Monsein LH, Razumovsky AY, Ackerman SJ, Nauta HJW, Hanley DF. Validation of transcranial Doppler ultrasound with a stereotactic neurosurgical technique. J Neurosurg. 1995;82(6):972\u20135.","journal-title":"J Neurosurg"},{"key":"765_CR20","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.jneumeth.2018.11.017","volume":"313","author":"A Khalaf","year":"2019","unstructured":"Khalaf A, Sejdic E, Akcakaya M. A novel motor imagery hybrid brain computer interface using EEG and functional transcranial Doppler ultrasound. J Neurosci Methods. 2019;313:44\u201353.","journal-title":"J Neurosci Methods"},{"issue":"5","key":"765_CR21","doi-asserted-by":"publisher","first-page":"056019","DOI":"10.1088\/1741-2552\/aad46f","volume":"15","author":"A Khalaf","year":"2018","unstructured":"Khalaf A, Sejdic E, Akcakaya M. Towards optimal visual presentation design for hybrid EEG\u2013fTCD brain\u2013computer interfaces. J Neural Eng. 2018;15(5):056019.","journal-title":"J Neural Eng"},{"key":"765_CR22","doi-asserted-by":"publisher","first-page":"217987","DOI":"10.1155\/2011\/217987","volume":"2011","author":"D Devlaminck","year":"2011","unstructured":"Devlaminck D, Wyns B, Grosse-Wentrup M, Otte G, Santens P. Multisubject learning for common spatial patterns in motor-imagery BCI. Comput Intell Neurosci. 2011;2011:217987.","journal-title":"Comput Intell Neurosci"},{"key":"765_CR23","doi-asserted-by":"crossref","unstructured":"Wang Y, Gao S, Gao X. Common spatial pattern method for channel selection in motor imagery based brain\u2013computer interface. In: 2005 IEEE engineering in medicine and biology 27th annual conference. 2005. pp. 5392\u20135.","DOI":"10.1109\/IEMBS.2005.1615701"},{"issue":"1","key":"765_CR24","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MSP.2008.4408441","volume":"25","author":"B Blankertz","year":"2008","unstructured":"Blankertz B, Tomioka R, Lemm S, Kawanabe M, Muller K. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag. 2008;25(1):41\u201356.","journal-title":"IEEE Signal Process Mag"},{"key":"765_CR25","unstructured":"Valencia D. Discrete wavelet transform filter bank implementation. 2010. https:\/\/www.dsprelated.com\/showarticle\/115.php."},{"issue":"1","key":"765_CR26","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1111\/1467-9884.00122","volume":"47","author":"DN Joanes","year":"1998","unstructured":"Joanes DN, Gill CA. Comparing measures of sample skewness and kurtosis. J R Stat Soc Ser D (The Stat). 1998;47(1):183\u20139.","journal-title":"J R Stat Soc Ser D (The Stat)"},{"issue":"3","key":"765_CR27","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1080\/00031305.2014.917055","volume":"68","author":"PH Westfall","year":"2014","unstructured":"Westfall PH. Kurtosis as peakedness, 1905\u20132014. R.I.P. Am Stat. 2014;68(3):191\u20135.","journal-title":"Am Stat"},{"issue":"4","key":"765_CR28","first-page":"309","volume":"5","author":"RC Blair","year":"1980","unstructured":"Blair RC, Higgins JJ. A comparison of the power of Wilcoxon\u2019s rank-sum statistic to that of student\u2019s t statistic under various nonnormal distributions. J Educ Stat. 1980;5(4):309.","journal-title":"J Educ Stat"},{"key":"765_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3324-9","volume-title":"Density estimation for statistics and data analysis","author":"BW Silverman","year":"1986","unstructured":"Silverman BW. Density estimation for statistics and data analysis. London: Chapman and Hall; 1986."},{"issue":"4","key":"765_CR30","first-page":"1","volume":"1","author":"Sung-Hyuk Cha","year":"2007","unstructured":"Cha Sung-Hyuk. Comprehensive survey on distance\/similarity measures between probability density functions. Int J Math Model Methods Appl Sci. 2007;1(4):1\u20138.","journal-title":"Int J Math Model Methods Appl Sci"},{"issue":"4","key":"765_CR31","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MSP.2004.1311138","volume":"21","author":"P Stoica","year":"2004","unstructured":"Stoica P, Selen Y. Model-order selection. IEEE Signal Process Mag. 2004;21(4):36\u201347.","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"765_CR32","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/7333.948456","volume":"9","author":"B Obermaier","year":"2001","unstructured":"Obermaier B, Neuper C, Guger C, Pfurtscheller G. Information transfer rate in a five-classes brain\u2013computer interface. IEEE Trans Neural Syst Rehabil Eng. 2001;9(3):283\u20138.","journal-title":"IEEE Trans Neural Syst Rehabil Eng"}],"container-title":["BioMedical Engineering OnLine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-020-00765-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12938-020-00765-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-020-00765-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T01:35:55Z","timestamp":1618536955000},"score":1,"resource":{"primary":{"URL":"https:\/\/biomedical-engineering-online.biomedcentral.com\/articles\/10.1186\/s12938-020-00765-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,16]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["765"],"URL":"https:\/\/doi.org\/10.1186\/s12938-020-00765-4","relation":{},"ISSN":["1475-925X"],"issn-type":[{"value":"1475-925X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,16]]},"assertion":[{"value":"10 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All research procedures employed in this study were approved by University of Pittsburgh IRB (IRB number: PRO16080475).","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"23"}}