Thermal Comfort Prediction Using Machine Learning: A Comparative Study of Algorithms and Features

Thermal Comfort Prediction Using Machine Learning: A Comparative Study of Algorithms and Features | 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 Thermal Comfort Prediction Using Machine Learning: A Comparative Study of Algorithms and Features Josephine Theresa S, Geethamani D, Bhuvaneshwari A, Sagayapriya A This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7852982/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 Predicting thermal comfort with precision is vital for enhancing indoor environments and promoting occupant well-being. As the focus on energy-efficient and occupant-focused buildings intensifies, the demand for accurate comfort modeling has grown. However, many existing models struggle to accommodate diverse environmental conditions and individual preferences. This study deploys predictive models using deep learning (DL) algorithms to solve challenges. For this purpose, the research utilizes a Multi-Input LSTM-Attention Based Deep Neural Network (MI-LSTM-ATTN) DL algorithm. The method begins by collecting global thermal comfort data. It performs preprocessing to remove missing or duplicate elements and compresses the dataset from 70 columns to 12 columns. Following this, wavelet scattering-based feature extraction is applied to enrich the dataset by capturing vital temporal and frequency-based attributes of thermal comfort parameters. Two feature selection methods are then used to determine the optimal feature sets, enhancing the accuracy of thermal preference predictions. The MI-LSTM-ATTN model is ultimately employed for classification, capitalizing on its ability to handle sequential data and highlight significant time-dependent patterns through the attention mechanism. D.The algorithm's performance is evaluated using statistical error measures such as the Root Mean Square error (RMSE), the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the constant error (R²). According to the research results, the proposed method has excellent performance, with a maximum R² score of 0.982, MAE of 0.986, MSE of 0.048, and RMSE of 0.154. We achieved a maximum error of 1.398 using competitive error metrics. Artificial Intelligence and Machine Learning Thermal comfort prediction indoor environment architecture deep learning (DL) heating ventilation and air conditioning (HVAC) systems Full Text Additional Declarations The authors declare no competing interests. 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-7852982","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":529137752,"identity":"a167fa69-03a2-4653-b55b-2375403e8633","order_by":0,"name":"Josephine Theresa S","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYHACNoYHQAxmJDAwyDEw8BChJQFJizGxWqAMIEhsIKTFvP/wsweJe/jk5Nt7jz14uMMmfcPxswcffGCwk9NtwK5F5kaauUHCMzZjgzPn0g0Sz6TlbjiTl2w4gyHZ2OwAdi0SEjxsEgkH2BI3SOSYSSS2Hc7dcCDHTJqH4UDiNlxa+M9AtMyf/wak5X+6wfk3BLQw5EC0NNzgAWk5kGBwg5AtEmlmIC1Av+SlAbUkG8688cbYcIYBHr/wH34m8eHAMWCInT0m+bPNTp7vfI7hgw8VdnK4tEDBMQZ4DCqAVRrgVQ4CNQgt8g0EVY+CUTAKRsEIAwBSCVwB+lYhlgAAAABJRU5ErkJggg==","orcid":"","institution":"St.joseph's College(A), Tiruchirappalli, India","correspondingAuthor":true,"prefix":"","firstName":"Josephine","middleName":"Theresa","lastName":"S","suffix":""},{"id":529137753,"identity":"ab86200e-1a29-499f-90b6-3da69d79a675","order_by":1,"name":"Geethamani D","email":"","orcid":"","institution":"Dr N.G.P. Arts and Science College(A), Coimbatore , India","correspondingAuthor":false,"prefix":"","firstName":"Geethamani","middleName":"","lastName":"D","suffix":""},{"id":529137754,"identity":"3de740a9-47fc-408e-aff1-62d0478823c2","order_by":2,"name":"Bhuvaneshwari A","email":"","orcid":"","institution":"SRM Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Bhuvaneshwari","middleName":"","lastName":"A","suffix":""},{"id":529137755,"identity":"dd47a120-de0a-4174-a157-880eed6821f0","order_by":3,"name":"Sagayapriya A","email":"","orcid":"","institution":"Bishop Heber College(A)","correspondingAuthor":false,"prefix":"","firstName":"Sagayapriya","middleName":"","lastName":"A","suffix":""}],"badges":[],"createdAt":"2025-10-14 01:51:04","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-7852982/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7852982/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93548540,"identity":"9f23f4e7-aab4-49a7-a6f4-fd037de66f9b","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139965,"visible":true,"origin":"","legend":"","description":"","filename":"ThermalComfortPredictionpreprint.docx","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/01343aaca6db28254910dfc7.docx"},{"id":93548538,"identity":"614cdf5c-2b0e-4b12-8263-02293291a991","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs7852982.json","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/037ede889bf163811bd599a1.json"},{"id":93548543,"identity":"7d179b35-c4f3-4723-9970-e12456b910a7","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81958,"visible":true,"origin":"","legend":"","description":"","filename":"rs78529820enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/5133254ffd04d7991b3e57e0.xml"},{"id":93548685,"identity":"b69b2a57-a41d-4260-a158-ac62767af0a6","added_by":"auto","created_at":"2025-10-15 04:19:47","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28200,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/e1375a2cc12d15cc4a65fe4b.png"},{"id":93548541,"identity":"acb7a58c-4b04-4e72-b390-5918f3ce9400","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17290,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/d54a7848d2e44eea82ad04d4.png"},{"id":93548549,"identity":"7bf4b264-5c12-4cea-b3bd-1b66e43dc8f7","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32190,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/9eeb741cafcfb7efba358f0e.png"},{"id":93548539,"identity":"0ee62a26-aa0c-4bc2-bb2d-a83bbd2718bc","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10782,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/6e1155577bbe95c86807f4b6.png"},{"id":93548687,"identity":"53a47e92-44ea-484b-b027-e745c4b8f4f6","added_by":"auto","created_at":"2025-10-15 04:19:49","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9301,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/632418a558fae9f521cb0429.png"},{"id":93548544,"identity":"df0108a8-ca25-44da-8621-691a3f8ee4a7","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6413,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/a66da730be926122ec2be595.png"},{"id":93548548,"identity":"8295c6de-48b7-4463-af14-23c15726d14c","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81004,"visible":true,"origin":"","legend":"","description":"","filename":"rs78529820structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/35b7217c4fb33d1b9e7171b7.xml"},{"id":93548545,"identity":"997ef73b-67a2-4bd7-8082-580c263abee9","added_by":"auto","created_at":"2025-10-15 04:11:47","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89703,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1/d01e15d5f490623696a40949.html"},{"id":93549168,"identity":"750622d6-6553-479c-9d62-34ecb46fbeea","added_by":"auto","created_at":"2025-10-15 04:27:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":431342,"visible":true,"origin":"","legend":"","description":"","filename":"ThermalComfortPredictionpreprint.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7852982/v1_covered_7900e64c-11e1-47a7-9a99-12b544ec23c6.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eThermal Comfort Prediction Using Machine Learning: A Comparative Study of Algorithms and Features\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Thermal comfort prediction, indoor environment, architecture, deep learning (DL), heating, ventilation, and air conditioning (HVAC) systems","lastPublishedDoi":"10.21203/rs.3.rs-7852982/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7852982/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePredicting thermal comfort with precision is vital for enhancing indoor environments and promoting occupant well-being. As the focus on energy-efficient and occupant-focused buildings intensifies, the demand for accurate comfort modeling has grown. However, many existing models struggle to accommodate diverse environmental conditions and individual preferences. This study deploys predictive models using deep learning (DL) algorithms to solve challenges. For this purpose, the research utilizes a Multi-Input LSTM-Attention Based Deep Neural Network (MI-LSTM-ATTN) DL algorithm. The method begins by collecting global thermal comfort data. It performs preprocessing to remove missing or duplicate elements and compresses the dataset from 70 columns to 12 columns. Following this, wavelet scattering-based feature extraction is applied to enrich the dataset by capturing vital temporal and frequency-based attributes of thermal comfort parameters. Two feature selection methods are then used to determine the optimal feature sets, enhancing the accuracy of thermal preference predictions. The MI-LSTM-ATTN model is ultimately employed for classification, capitalizing on its ability to handle sequential data and highlight significant time-dependent patterns through the attention mechanism. D.The algorithm's performance is evaluated using statistical error measures such as the Root Mean Square error (RMSE), the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the constant error (R\u0026sup2;). According to the research results, the proposed method has excellent performance, with a maximum R\u0026sup2; score of 0.982, MAE of 0.986, MSE of 0.048, and RMSE of 0.154. We achieved a maximum error of 1.398 using competitive error metrics.\u003c/p\u003e","manuscriptTitle":"Thermal Comfort Prediction Using Machine Learning: A Comparative Study of Algorithms and Features","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-15 04:11:42","doi":"10.21203/rs.3.rs-7852982/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":"57f40122-0734-47b8-9145-adcaac13a5ee","owner":[],"postedDate":"October 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56239932,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-10-15T04:11:42+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-15 04:11:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7852982","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7852982","identity":"rs-7852982","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}