Low-Cost Sensor Outlier Detection Framework For on-Line Monitoring of Particle Pollutants in Multiple Scenarios

Low-Cost Sensor Outlier Detection Framework For on-Line Monitoring of Particle Pollutants in Multiple Scenarios | 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 Research Article Low-Cost Sensor Outlier Detection Framework For on-Line Monitoring of Particle Pollutants in Multiple Scenarios Yinyue Xu, Zhengwei Long, Wuxuan Pan, Yukun Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-218927/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 6 You are reading this latest preprint version Abstract Monitoring the concentration of particle pollutants is very important for industrial production control and workers' health protection. Low-cost sensors are widely used to reduce deployment costs. The outliers in the observed data of pollutant concentration can be eliminated by outlier detection algorithms. However, it is difficult to meet the actual needs of changing working conditions or scene migration in factories by building a single algorithm for specific scenarios. It is a feasible scheme to identify the changing characteristics of data and adaptively adjust the outlier detection algorithm. From the point of view of data characteristics, we creatively match typical data types with high performance algorithms. The framework proposed in this paper provides a general process including five basic tasks, and uses a modular structure to complete the outlier detection target. The actual pollutant data of the workshops are used to evaluate the performance of our framework. At last, we compare eight different strategies under this framework, and analyze the contribution of each step to outlier detection from the perspective of algorithm principle. The results show that low-cost sensors following the framework can meet the outlier detection requirements in the field of pollutant monitoring, thus greatly reducing the cost of algorithm selection and data adaptation. Environmental Policy Low-cost sensor Multiple scenarios Pollutant concentration Outlier detection Sensor performance Time-series Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Full Text Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Major Revision 28 Mar, 2021 Reviews received at journal 24 Feb, 2021 Reviewers invited by journal 22 Feb, 2021 Editor invited by journal 21 Feb, 2021 Editor assigned by journal 10 Feb, 2021 First submitted to journal 06 Feb, 2021 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-218927","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":13275549,"identity":"3701fb9e-6072-46f2-ad11-0c711d498063","order_by":0,"name":"Yinyue Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIie3RsUrEMBjA8YRCuoTe+pVCfYUvHIiC4Av4EAmC0w03udoaqIvimoIPoW/QQ7hbTueMLb5AoYPLgbbdbkk7CuY/hu83fPkI8fn+YIuA5nWLjC9CXREYnqoJEj9oLcw6SuPHrcpmEdzvioS36RLtlcjIHEKsKoDjqSoN/67PC5JGVtJu7RDUKH0GeKOek6e3LC7IMrYySIyDBKByi7hV5cvHSNSrlSzgDsKgX1riTz+5agZyN0k439xDhaxff0UHInGKQJhrkSEbPlkY+ARR7huduMjle9h8HQ7jKesObi9Oot31pnORowIY70+zuaCfbefP+nw+3z/qF9okUhsEEVb0AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-7661-0145","institution":"Tianjin University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Yinyue","middleName":"","lastName":"Xu","suffix":""},{"id":13275550,"identity":"a58cc828-ae33-44dd-9f9f-2d5960e711bd","order_by":1,"name":"Zhengwei Long","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zhengwei","middleName":"","lastName":"Long","suffix":""},{"id":13275551,"identity":"65ff9525-8ff6-43c0-9351-b46372a5d540","order_by":2,"name":"Wuxuan Pan","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wuxuan","middleName":"","lastName":"Pan","suffix":""},{"id":13275552,"identity":"36a5dedb-e1b0-4811-b1c5-3b34fde07ce9","order_by":3,"name":"Yukun Wang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yukun","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2021-02-07 09:55:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-218927/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-218927/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":6371946,"identity":"b41d3dc0-0468-491a-b2c7-cd9cc00dc0b3","added_by":"auto","created_at":"2021-02-25 22:34:26","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":75911,"visible":true,"origin":"","legend":"The framework of the type recognition step shows the input, output and structural settings of the neural network model.","description":"","filename":"Fig01.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/fcf9f1ea986af3e5aebb51b6.png"},{"id":6371577,"identity":"4772de6b-38fd-4b1e-8c18-b56edc7b6aac","added_by":"auto","created_at":"2021-02-25 22:31:26","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":66679,"visible":true,"origin":"","legend":"Multi-scene outlier detection framework suitable for three typical data types includes five core steps to automatically improve data quality.","description":"","filename":"Fig02.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/f1608fddddf1cb09e8af1f8f.png"},{"id":6371945,"identity":"c5603f70-9154-488c-a8b7-e5bb2380fe2d","added_by":"auto","created_at":"2021-02-25 22:34:26","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":118423,"visible":true,"origin":"","legend":"Three types of original sequence operational trend extraction: a oil fume, b oil mist, c PM2.5.","description":"","filename":"Fig03.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/1ac0574a9d1b242790db9301.png"},{"id":6371581,"identity":"94925d7d-ec0a-40f8-ab2c-07427397afc1","added_by":"auto","created_at":"2021-02-25 22:31:26","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":80880,"visible":true,"origin":"","legend":"The feature sequence diagrams of three types of original data sets are used to demonstrate the effect of wavelet transform and normalization processing.","description":"","filename":"Fig04.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/75a489826921be390f8c1f2d.png"},{"id":6371583,"identity":"3f227d49-77ca-422e-8787-f5fdc151b72e","added_by":"auto","created_at":"2021-02-25 22:31:26","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":102929,"visible":true,"origin":"","legend":"Outlier detection results for three types of original data sets: a oil fume, b oil mist, c PM2.5.","description":"","filename":"Fig05.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/dbaa631d510996f390482223.png"},{"id":6371586,"identity":"a5e50ab4-cf62-44db-8a0c-08c355035960","added_by":"auto","created_at":"2021-02-25 22:31:26","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":129146,"visible":true,"origin":"","legend":"Gap-filling results for three types of original data sets: a oil fume, b oil mist, c PM2.5. ","description":"","filename":"Fig06.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/c0927d6e0df394194266cb35.png"},{"id":6372353,"identity":"c1cc7319-3cfa-4ac8-84e4-42b464f6ec01","added_by":"auto","created_at":"2021-02-25 22:37:27","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":122663,"visible":true,"origin":"","legend":"Outlier detection results for three types of labeled data sets: a oil fume, b oil mist, c PM2.5.","description":"","filename":"Fig07.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/97a79c475fcaca8e7ddad6ca.png"},{"id":6371941,"identity":"bacc6420-18e4-4512-8e95-56786e66ec63","added_by":"auto","created_at":"2021-02-25 22:34:26","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":62785,"visible":true,"origin":"","legend":"The 5th group of outliers of Type 3 data is shown here as an example of the variation in outlier detection accuracy rate with z under different k values in the grid-search process.","description":"","filename":"Fig08.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/67bd9f74b36b901820cb42ac.png"},{"id":6372347,"identity":"182995eb-4aca-450e-8322-bc2937cc9ea2","added_by":"auto","created_at":"2021-02-25 22:37:26","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":101986,"visible":true,"origin":"","legend":"The 5th group of outliers of Type 3 data is shown here as an example of the variation in the FP and FN rates for outlier detection with k under different z values in the grid-search process.","description":"","filename":"Fig09.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/0010dae4d0acb1578f808cbc.png"},{"id":6371580,"identity":"60b1bbff-1c3f-478e-97b8-7c3a4fa8e6c4","added_by":"auto","created_at":"2021-02-25 22:31:26","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":138158,"visible":true,"origin":"","legend":"Comparison of outlier detection accuracy rates of 8 strategies in three typical data types","description":"","filename":"Fig10.png","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1/db1d7c98480a313dae78c32b.png"},{"id":13595698,"identity":"7301c65c-71f3-4596-a139-1b4c588160bb","added_by":"auto","created_at":"2021-09-17 05:25:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1241724,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1_covered.pdf"},{"id":6372672,"identity":"2d65a641-263e-4b01-9280-430e7e0fdc16","added_by":"auto","created_at":"2021-02-25 22:40:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1011804,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-218927/v1_stamped.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eLow-Cost Sensor Outlier Detection Framework For on-Line Monitoring of Particle\u0026nbsp;Pollutants in Multiple Scenarios\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-218927/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Low-cost sensor, Multiple scenarios, Pollutant concentration, Outlier detection, Sensor performance, Time-series","lastPublishedDoi":"10.21203/rs.3.rs-218927/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-218927/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMonitoring the concentration of particle pollutants is very important for industrial production control and workers' health protection. Low-cost sensors are widely used to reduce deployment costs. The outliers in the observed data of pollutant concentration can be eliminated by outlier detection algorithms. However, it is difficult to meet the actual needs of changing working conditions or scene migration in factories by building a single algorithm for specific scenarios. It is a feasible scheme to identify the changing characteristics of data and adaptively adjust the outlier detection algorithm. From the point of view of data characteristics, we creatively match typical data types with high performance algorithms. The framework proposed in this paper provides a general process including five basic tasks, and uses a modular structure to complete the outlier detection target. The actual pollutant data of the workshops are used to evaluate the performance of our framework. At last, we compare eight different strategies under this framework, and analyze the contribution of each step to outlier detection from the perspective of algorithm principle. The results show that low-cost sensors following the framework can meet the outlier detection requirements in the field of pollutant monitoring, thus greatly reducing the cost of algorithm selection and data adaptation.\u003c/p\u003e","manuscriptTitle":"Low-Cost Sensor Outlier Detection Framework For on-Line Monitoring of Particle\u0026nbsp;Pollutants in Multiple Scenarios","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-02-25 22:31:23","doi":"10.21203/rs.3.rs-218927/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major Revision","date":"2021-03-28T12:25:17+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-02-25T00:00:00+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-02-23T00:00:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Environmental Science and Pollution Research","date":"2021-02-22T00:00:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-02-11T00:00:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Environmental Science and Pollution Research","date":"2021-02-07T04:54:57+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"caf2bece-9898-42de-8a2b-e15859fd7ab4","owner":[],"postedDate":"February 25th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":2619366,"name":"Environmental Policy"}],"tags":[],"updatedAt":"2021-05-09T23:40:44+00:00","versionOfRecord":[],"versionCreatedAt":"2021-02-25 22:31:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-218927","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-218927","identity":"rs-218927","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}