Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract Compressed sensing (CS) enables efficient data acquisition and implicit encryption; however, its recovery stage remains a significant computational bottleneck, as it requires solving large-scale optimization problems or running iterative reconstruction algorithms. Here, we propose an event-driven CS recovery framework developed through an algorithm–hardware co-design approach. This framework employs memristor crossbar array (MCA)-based analog matrix computing (AMC) circuits as the hardware platform and incorporates a novel CS recovery algorithm (named constrained gradient descent (CGD) algorithm) designed to leverage them. Furthermore, the framework supports event-driven selective recovery via MCA-based feature detection. We fabricated the hardware to validate the proposed framework, and the experimental results demonstrate 15.49–34.21× improvements in energy efficiency over state-of-the-art methods for image and ECG signal processing. These results underscore the potential of the proposed framework as a competitive hardware solution for real-time sensing signal processing in edge devices.
Full text 20,087 characters · extracted from preprint-html · click to expand
Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing | 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 Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing Kyung Min Kim, Mingxin Deng, Yinan Wang, Hui Xu, Likang Sun, Lun Lu, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7734741/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Compressed sensing (CS) enables efficient data acquisition and implicit encryption; however, its recovery stage remains a significant computational bottleneck, as it requires solving large-scale optimization problems or running iterative reconstruction algorithms. Here, we propose an event-driven CS recovery framework developed through an algorithm–hardware co-design approach. This framework employs memristor crossbar array (MCA)-based analog matrix computing (AMC) circuits as the hardware platform and incorporates a novel CS recovery algorithm (named constrained gradient descent (CGD) algorithm) designed to leverage them. Furthermore, the framework supports event-driven selective recovery via MCA-based feature detection. We fabricated the hardware to validate the proposed framework, and the experimental results demonstrate 15.49–34.21× improvements in energy efficiency over state-of-the-art methods for image and ECG signal processing. These results underscore the potential of the proposed framework as a competitive hardware solution for real-time sensing signal processing in edge devices. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Materials science/Materials for devices/Electronic devices Physical sciences/Mathematics and computing/Information technology Full Text Additional Declarations There is NO Competing Interest. Supplementary Files CompressedSensingManuscriptSIFinal.docx Supplementary Infomation of Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing Cite Share Download PDF Status: Under Review 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-7734741","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":525415122,"identity":"27f15aa4-20b8-443e-ae57-44cb32ef4f7b","order_by":0,"name":"Kyung Min Kim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYBACCQYGZoYEBhsDIAUXIUpLGkgLYwPxWhgYDhsACSK1SE47wGzwMOe8MX87+/MHDDV2DJKzD+DXIi2dwJyQuO22mcRhHsMGhmPJDNJ8Cfi1yAG1HABqsWE4zAN0GNsBBjkeAg6DajlnI3+Y/WEDwz8itEAddsDM4DCDYQNj2wEGaUJaJGcnNhskbks2NgT6ZUZiXzKPZA8BLRK3kw9L/txmZzjv/PEHHz58s5OTOENACyw2ICCBgYGQs0bBKBgFo2AUEAMABkY6foEW8YMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-0190-4226","institution":"Korea Advanced Institute of Science and Technology (KAIST)","correspondingAuthor":true,"prefix":"","firstName":"Kyung","middleName":"Min","lastName":"Kim","suffix":""},{"id":525415123,"identity":"a0b55d03-1e80-4241-bd02-c8ba962b289a","order_by":1,"name":"Mingxin Deng","email":"","orcid":"","institution":"National University of defense technology","correspondingAuthor":false,"prefix":"","firstName":"Mingxin","middleName":"","lastName":"Deng","suffix":""},{"id":525415124,"identity":"588fc0ed-47e4-4d2c-9971-52f24be09739","order_by":2,"name":"Yinan Wang","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Yinan","middleName":"","lastName":"Wang","suffix":""},{"id":525415125,"identity":"959744c6-c9b5-496a-b323-f438b73f7fbd","order_by":3,"name":"Hui Xu","email":"","orcid":"","institution":"College of Electronic Science and Technology, National University of Defense Technology; Hunan Key Laboratory of Aerospace Intelligent ASIC Technology","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Xu","suffix":""},{"id":525415126,"identity":"af9234f3-7337-45bd-aeec-7edc3086024d","order_by":4,"name":"Likang Sun","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Likang","middleName":"","lastName":"Sun","suffix":""},{"id":525415127,"identity":"a885095f-f12b-4994-84fb-ee341a3bfbb8","order_by":5,"name":"Lun Lu","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Lun","middleName":"","lastName":"Lu","suffix":""},{"id":525415128,"identity":"eb35bc82-80ca-44ef-a068-904e20f0bf6c","order_by":6,"name":"Ao Xu","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Ao","middleName":"","lastName":"Xu","suffix":""},{"id":525415129,"identity":"4174b3f6-f4ae-4392-bf9c-f4ca1b3a5915","order_by":7,"name":"Nuo Xu","email":"","orcid":"","institution":"College of Computer, National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Nuo","middleName":"","lastName":"Xu","suffix":""},{"id":525415130,"identity":"fd07a84d-311c-4afe-82cc-33e49fc0b904","order_by":8,"name":"Zhiwei Li","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiwei","middleName":"","lastName":"Li","suffix":""},{"id":525415131,"identity":"7f572a87-64e1-4929-8c49-01ef5470e971","order_by":9,"name":"Qingjiang Li","email":"","orcid":"https://orcid.org/0000-0001-9779-3198","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Qingjiang","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-09-28 13:40:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7734741/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7734741/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92933060,"identity":"035be0f8-46b1-41c7-a635-d2845c829041","added_by":"auto","created_at":"2025-10-07 09:30:36","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2463381,"visible":true,"origin":"","legend":"","description":"","filename":"CompressedSensingManuscriptMaintextFinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/367b04633cb061a0d9d3de20.docx"},{"id":92932293,"identity":"3343ce81-dda8-4d52-911f-c29e6e721d7e","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10805,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS2577603.json","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/127814de57f47829233e482f.json"},{"id":92932307,"identity":"3e21314c-13b4-4d34-bb6e-f5a566bbf131","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3874790,"visible":true,"origin":"","legend":"","description":"","filename":"CompressedSensingManuscriptSIFinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/98dc7fe283c8d4d994b54e86.docx"},{"id":92932298,"identity":"0e1f84cb-274d-4548-882d-8e2c8127dcae","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122174,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25776030enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/92a33c7370bbb3770c4df195.xml"},{"id":92932294,"identity":"ce9dde9d-da93-4b57-b877-72a45b706d3b","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":280796,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/3e5e195286684eaa1c6ea1b1.png"},{"id":92933061,"identity":"f31c9d43-6905-400a-9f2d-0e179adf7e8c","added_by":"auto","created_at":"2025-10-07 09:30:36","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":669260,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/74ee8dc87bf45abac0737ef9.png"},{"id":92932296,"identity":"2bb7ec00-2aaf-4442-8e91-799e64e67b42","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":524944,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/dbcd59efde441e003494e99c.png"},{"id":92933059,"identity":"dca41cfa-6eb5-4de1-9a2e-a180b2a9dd42","added_by":"auto","created_at":"2025-10-07 09:30:36","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":329172,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/bd9652e6bf2fb2a7383a67ad.png"},{"id":92933465,"identity":"9cfed79c-b7a1-4c26-b397-b99586093a2f","added_by":"auto","created_at":"2025-10-07 09:38:36","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":261951,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/1cc44dc0353cfe3b2e4279a0.png"},{"id":92933063,"identity":"f6eb567a-9b04-4473-9487-1f58f035505e","added_by":"auto","created_at":"2025-10-07 09:30:36","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67652,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/23fef47b74d70e88cd21840f.png"},{"id":92932302,"identity":"93be03c1-17ab-423f-8e7f-76a5685e6d6f","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95602,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/185ab392de94d772ef2e022e.png"},{"id":92932299,"identity":"f3bc6011-71dc-459e-aeff-b491dae9c7ec","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81675,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/80599b00c927fda694226b36.png"},{"id":92932305,"identity":"987488e2-8bf9-4e2f-a2c5-8dc8dd3f6d70","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56272,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/8e3cdd2320f2f4cc6ecb0a20.png"},{"id":92933467,"identity":"6f971289-3159-4d72-8b4f-c6b683af35d8","added_by":"auto","created_at":"2025-10-07 09:38:36","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54057,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/7c3d3cad0a85ccbbfa924cf5.png"},{"id":92932308,"identity":"4d4d0878-760e-4b5c-a06e-37d4b39a8f4b","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"xml","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120985,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25776030structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/8c909e2d466cb58d1d40df7a.xml"},{"id":92932309,"identity":"585e5851-b50a-4aab-a6d5-fa3eba6ff552","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"html","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":140559,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/0a467c55da64cc9c9d73dbd4.html"},{"id":92934180,"identity":"4be5eb81-8e55-4e7d-bad8-134c64b77e90","added_by":"auto","created_at":"2025-10-07 09:46:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1467951,"visible":true,"origin":"","legend":"","description":"","filename":"CompressedSensingManuscriptMaintextFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1_covered_8b6aad5e-720d-4875-93f7-3638649f73e8.pdf"},{"id":92932304,"identity":"5a73b5a2-6347-4e53-9a6a-f6a5b2c78cfe","added_by":"auto","created_at":"2025-10-07 09:22:36","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3874790,"visible":true,"origin":"","legend":"Supplementary Infomation of Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing","description":"","filename":"CompressedSensingManuscriptSIFinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-7734741/v1/31eaf6e0fa71aeed51e1de5b.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7734741/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7734741/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCompressed sensing (CS) enables efficient data acquisition and implicit encryption; however, its recovery stage remains a significant computational bottleneck, as it requires solving large-scale optimization problems or running iterative reconstruction algorithms. Here, we propose an event-driven CS recovery framework developed through an algorithm\u0026ndash;hardware co-design approach. This framework employs memristor crossbar array (MCA)-based analog matrix computing (AMC) circuits as the hardware platform and incorporates a novel CS recovery algorithm (named constrained gradient descent (CGD) algorithm) designed to leverage them. Furthermore, the framework supports event-driven selective recovery via MCA-based feature detection. We fabricated the hardware to validate the proposed framework, and the experimental results demonstrate 15.49\u0026ndash;34.21\u0026times; improvements in energy efficiency over state-of-the-art methods for image and ECG signal processing. These results underscore the potential of the proposed framework as a competitive hardware solution for real-time sensing signal processing in edge devices.\u003c/p\u003e","manuscriptTitle":"Memristive Crossbar Array-based Hardware Framework for Compressed Sensing and Event-Driven Neuromorphic Processing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-07 09:22:31","doi":"10.21203/rs.3.rs-7734741/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"498100a5-d767-4ba3-be96-a41d1d0aff1f","owner":[],"postedDate":"October 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":55838313,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":55838314,"name":"Physical sciences/Materials science/Materials for devices/Electronic devices"},{"id":55838315,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2026-04-14T07:16:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-07 09:22:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7734741","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7734741","identity":"rs-7734741","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00