Research on the classification of small civilian UAV operation competency level based on EEG and BCAM-LSTM network

Research on the classification of small civilian UAV operation competency level based on EEG and BCAM-LSTM network | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Research on the classification of small civilian UAV operation competency level based on EEG and BCAM-LSTM network Xiang Sheng, Wenxin Duan, Ziyan Nie, Anni Zheng, Jiahui Li, Dapeng Ye, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6139237/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract As the civilian drone market continues rapidly growing, the civilian drone operator training system standard is under developing. However, traditional training evaluation methods based on processes and behaviors are no longer sufficient to dynamically and cognitively classify the training competency levels. In this research, an experiment was designed and conducted to explore the possibility of classifying the civilian drone operator competency level based on EEG signals and deep learning models. Moreover, a deep learning model was proposed and called the Bidirectional Custom Attention Mechanism Long and Short Term Memory (BCAM-LSTM). Furthermore, two different feature extraction methods were compared and discussed, including time domain features (Shannon entropy, Autoregressive coefficients, and Differencing) and frequency domain features (power spectrum density features). The drone simulation task was designed for 24 recruited drone trainees with no operation experience. Three proficiency levels were defined based on performance scores. EEG signal preprocessing included baseline and artifact removals, band-pass filtering, and ICA detection. This research adopted the five-fold cross-validation strategy and incorporated five classifier performance evaluation metrics including Accuracy, Sensitivity, Precision, F2 score, and Specificity. To demonstrate the proposed model BCAM-LSTM performance, four common models were compared and discussed including Bi-LSTM, Am-LSTM, ANN, and LDA. The research results gave evidence of accurately classifying trainee competency levels employing cognitive EEG signals as the proposed model BCAM-LSTM showed very high values of accuracy (0.97), specificity (0.97), and F2-score (0.97) with the frequency domain features. Simultaneously, Bi-LSTM and Am-LSTM also exhibited satisfactory accuracy of 0.89 and 0.88 respectively. Moreover, the results also indicated that frequency domain features excelled greatly than time domain features with whatever models were applied. The proposed model BCAM-LSTM displayed the largest feature characteristics accuracy difference of 31%, followed by Bi-LSTM (24%). This research showed the potential for future intelligent proficiency level judgment systems of drone operator training based on EEG frequency domain features by using the proposed BCAM-LSTM model. Physical sciences/Engineering/Electrical and electronic engineering Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Learning algorithms Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Network models Biological sciences/Neuroscience/Cognitive neuroscience Biological sciences/Physiology/Neurophysiology EEG Competency level Drone Operator training BCAM-LSTM Cognitive Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6139237","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":458630822,"identity":"30f56347-b8ee-4694-bd87-673e14236ebc","order_by":0,"name":"Xiang Sheng","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Xiang","middleName":"","lastName":"Sheng","suffix":""},{"id":458630823,"identity":"bc877b5d-a3a7-4474-8cd0-d2f0a53b07dd","order_by":1,"name":"Wenxin Duan","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Wenxin","middleName":"","lastName":"Duan","suffix":""},{"id":458630824,"identity":"a5fb440c-8d59-47a0-9e4e-9225920bbd12","order_by":2,"name":"Ziyan Nie","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Ziyan","middleName":"","lastName":"Nie","suffix":""},{"id":458630825,"identity":"78f75606-cacd-4c78-a265-e1f86727b160","order_by":3,"name":"Anni Zheng","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Anni","middleName":"","lastName":"Zheng","suffix":""},{"id":458630826,"identity":"1a0428e8-b49b-4398-8376-c7b9eeb72daf","order_by":4,"name":"Jiahui Li","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Jiahui","middleName":"","lastName":"Li","suffix":""},{"id":458630827,"identity":"7321d328-3825-4594-baad-e91b2863df7c","order_by":5,"name":"Dapeng Ye","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Dapeng","middleName":"","lastName":"Ye","suffix":""},{"id":458630828,"identity":"bc3b9206-625b-46de-9305-e85f3af2e719","order_by":6,"name":"Meibin Xie","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Meibin","middleName":"","lastName":"Xie","suffix":""},{"id":458630829,"identity":"2a3a08df-8ede-4d4c-b3ce-ed86349ee96b","order_by":7,"name":"Lin Zhong","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Zhong","suffix":""},{"id":458630830,"identity":"3d971175-14ba-46d3-9ece-72affc7bd619","order_by":8,"name":"Xiaolei Deng","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Xiaolei","middleName":"","lastName":"Deng","suffix":""},{"id":458630831,"identity":"a6ef6af2-dc8a-4300-8649-e9b023a09eee","order_by":9,"name":"Shuhe Zheng","email":"","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Shuhe","middleName":"","lastName":"Zheng","suffix":""},{"id":458630832,"identity":"75ef659e-5893-4d68-9a38-71b199a30885","order_by":10,"name":"Xin Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYDACZjApAeF8sAGRjI0HiNbCOCMNTDXg14KinScNwsCrRb6d9/ALxjaLPIPjZw+/tkmwSVzbfhhoS41NNC4tBof50iwYzkgUG5zJS7POSUgzNjuTCNRyLC23AZcWZh4zA4YKicRtB3LMjHN/HJYzOwDUwthwGKcW+WaQFgOglvNvzIwtEg7zmJ1/iF8Lw2Ee4wdgW27kGD9mSADacoOALQZAYxmAfkncf+ONGWMPyC83gLYk4PGLfP8Z4w+MbXWJM/tzjD/8AIbYtvPpDx98qLHB7TAGBjbpP1CGBFwsAbdyEGD+gM4YBaNgFIyCUYACAKoCXtfK0Is/AAAAAElFTkSuQmCC","orcid":"","institution":"Fujian Agriculture and Forestry University","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-03-02 12:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6139237/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6139237/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91379689,"identity":"30eea1a2-0853-41b2-bb9a-29dec3bab30c","added_by":"auto","created_at":"2025-09-15 23:01:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1420956,"visible":true,"origin":"","legend":"","description":"","filename":"Revised20250402ResearchontheclassificationofsmallcivilianUAVoperationcompetencylevelbasedonEEGandBCAMLSTMnetwork.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6139237/v1_covered_4b5a5aae-df5e-45df-8530-45d7f8429213.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on the classification of small civilian UAV operation competency level based on EEG and BCAM-LSTM network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"EEG, Competency level, Drone, Operator training, BCAM-LSTM, Cognitive","lastPublishedDoi":"10.21203/rs.3.rs-6139237/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6139237/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAs the civilian drone market continues rapidly growing, the civilian drone operator training system standard is under developing. However, traditional training evaluation methods based on processes and behaviors are no longer sufficient to dynamically and cognitively classify the training competency levels. In this research, an experiment was designed and conducted to explore the possibility of classifying the civilian drone operator competency level based on EEG signals and deep learning models. Moreover, a deep learning model was proposed and called the Bidirectional Custom Attention Mechanism Long and Short Term Memory (BCAM-LSTM). Furthermore, two different feature extraction methods were compared and discussed, including time domain features (Shannon entropy, Autoregressive coefficients, and Differencing) and frequency domain features (power spectrum density features). The drone simulation task was designed for 24 recruited drone trainees with no operation experience. Three proficiency levels were defined based on performance scores. EEG signal preprocessing included baseline and artifact removals, band-pass filtering, and ICA detection. This research adopted the five-fold cross-validation strategy and incorporated five classifier performance evaluation metrics including Accuracy, Sensitivity, Precision, F2 score, and Specificity. To demonstrate the proposed model BCAM-LSTM performance, four common models were compared and discussed including Bi-LSTM, Am-LSTM, ANN, and LDA. The research results gave evidence of accurately classifying trainee competency levels employing cognitive EEG signals as the proposed model BCAM-LSTM showed very high values of accuracy (0.97), specificity (0.97), and F2-score (0.97) with the frequency domain features. Simultaneously, Bi-LSTM and Am-LSTM also exhibited satisfactory accuracy of 0.89 and 0.88 respectively. Moreover, the results also indicated that frequency domain features excelled greatly than time domain features with whatever models were applied. The proposed model BCAM-LSTM displayed the largest feature characteristics accuracy difference of 31%, followed by Bi-LSTM (24%). This research showed the potential for future intelligent proficiency level judgment systems of drone operator training based on EEG frequency domain features by using the proposed BCAM-LSTM model.\u003c/p\u003e","manuscriptTitle":"Research on the classification of small civilian UAV operation competency level based on EEG and BCAM-LSTM network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-20 14:26:30","doi":"10.21203/rs.3.rs-6139237/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"31417eff-af15-4b29-a48d-618dc28f7a08","owner":[],"postedDate":"May 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48720304,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":48720305,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":48720306,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Learning algorithms"},{"id":48720307,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Network models"},{"id":48720308,"name":"Biological sciences/Neuroscience/Cognitive neuroscience"},{"id":48720309,"name":"Biological sciences/Physiology/Neurophysiology"}],"tags":[],"updatedAt":"2025-09-15T22:53:20+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-20 14:26:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6139237","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6139237","identity":"rs-6139237","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}