[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290658-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290658-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","machine-learning-assisted-speckle-based-pof-sensor-for-detecting-microvibrations","MACHINE-LEARNING ASSISTED SPECKLE-BASED POF SENSOR FOR DETECTING MICROVIBRATIONS","","We present a machine-learning assisted real-time speckle-based step-index plastic optical fiber (SI-POF) sensor designed to detect microvibrations. A dual-wavelength scheme is introduced to improve sensitivity, accuracy, and resolution. Specklegrams are analyzed with a convolutional neural network (CNN) to estimate perturbation frequency and to recover both micro-displacement strength and spatial location along the fiber. The system operates in transmissive and reflective topologies using wavelength multiplexing and webcam-based capture.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/machine-learning-assisted-speckle-based-pof-sensor-for-detecting-microvibrations/290658/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/machine-learning-assisted-speckle-based-pof-sensor-for-detecting-microvibrations/290658.png","ImageObject",300,407,{"name":42,"@type":43},"Levi","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-27","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",13,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"How does the sensor detect microvibrations?","Question",{"text":63,"@type":64},"It detects changes in speckle patterns generated by mode interference in an SI-POF. A CNN processes the captured specklegrams to extract vibration frequency, micro-displacement strength, and perturbation location along the fiber.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What role does the dual-wavelength approach play?",{"text":68,"@type":64},"Using two wavelengths increases sensitivity, accuracy, and resolution compared with a single-wavelength approach.",{"name":70,"@type":61,"acceptedAnswer":71},"Which measurement topologies are supported?",{"text":72,"@type":64},"The sensor is implemented for both transmissive and reflective topologies, enabling light to propagate through the setup and be reflected back to the detector in the reflective configuration.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290658,1789642296,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":33,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":124,"preview_page_count":4},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","MACHINE-LEARNING ASSISTED SPECKLE-BASED POF SENSOR FOR DETECTING MICROVIBRATIONS  \nD. S. Montero1*, J. Yaque1, R. Altuna1, J. Barco1, J. Zubía2, C. Vázquez1,  \n1: Electronics Technology Department / Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganés (Madrid) Spain.  \n2: Department of Electronic Technology, Engineering School of Bilbao, University of the Basque Country (UPV/EHU), Plaza Ingeniero Torres Quevedo, 1, 48013 Bilbao, Spain.  \nCorresponding author: [dsmontero@ing.uc3m.es](dsmontero@ing.uc3m.es)  \nAbstract: We present a Machine-Learning (ML) assisted real-time speckle-based step-index plastic optical fiber (SI-POF) sensor for detecting microvibrations. A dual-wavelength approach to increase the system sensitivity, accuracy and resolution is implemented. Specklegrams are processed by means ofa Convolutional Neural Network (CNN) to analyze and extract the frequency of the perturbation as both its strength (micro-displacement) and its location throughout the fiber.  \nKeywords: dual-wavelength, plastic optical fiber, speckle pattern, Machine Learning, vibration measurements.  \n1. Introduction  \nWhen a highly coherent light propagates through a multimode optical fiber via a number of modes interference between these modes yields a speckle pattern, so−called modal noise, at the fiber end−face. This speckle pattern is extremely sensitive to the phase difference among the propagated modes, which can arise from time−varying fiber disturbances resulting from external forces or thermal drifts, among others. The sensing community has envisioned this physical effect to be potentially suitable to measure a wide range of measurands (pressure, temperature, vibration, etc.) [1-4], mostly with direct application to the biomedical sector. One of the benefits of POFs, compare to those related to their silica counterparts, is their biocompatibility properties. The use of silica fiber is sometimes inappropriate due to the risks from breakages.  \nDue to the high sensitivity of speckle pattern changes, this can be a drawback in final applications due to the random nature of the interference of the fiber modes produced by ambient perturbations as well as the modal noise of the light source. Reflective configurations have been proposed to increase sensitivity in different sensing configurations as well as to provide a centralized remote sensor interrogation scheme [5]. Focusing on speckle-sensors, in most of the cases a single-wavelength approach is reported although a dual−wavelength approach has been proposed [6] with the aim of enhancing the system accuracy and resolution.  \nDespite the numerous applications speckle sensor have found solutions for, most of the current methods of analyzing and comparing specklegram images are purely statistical. The cumulative effect of external perturbations is averaged along the fiber, furthermore, all pixels in the specklegram contribute to a single value quantifying a correlation/difference [7]. In this way, they do not offer any physical insight into how the multimode transmission is occurring throughout the length of the fiber, nor do they offer distributed sensing capabilities, and suffer dynamic range limits. Additionally, the process of fitting calculation requires a long time thus resulting in a low temporal sensing resolution [8] . For instance, in the work reported in [6] a delay of around 1.5 s due to data processing is achieved that can be impractical in some applications. This is why, in recent years, computational methods using neural networks have been explored as a solution in various sensing applications utilizing speckle patterns such as image reconstruction, object classification and recognition [9,10] .  \nIn this work, we present a Machine-Learning (ML) assisted speckle-based 980/1000μm core/cladding diameter step-index plastic optical fiber (SI-POF) sensor for detecting microvibrations in both transmissive and reflective topologies. A piezoelectric stack is use","cbCaikNp7dN6HrWJ","https://ap.wps.com/l/cbCaikNp7dN6HrWJ","pdf",521068,"English","# 1. Introduction\n# 2. System description\n# 3. CNN results\n# 4. Conclusion and discussion","[{\"question\":\"How does the sensor detect microvibrations?\",\"answer\":\"It detects changes in speckle patterns generated by mode interference in an SI-POF. A CNN processes the captured specklegrams to extract vibration frequency, micro-displacement strength, and perturbation location along the fiber.\"},{\"question\":\"What role does the dual-wavelength approach play?\",\"answer\":\"Using two wavelengths increases sensitivity, accuracy, and resolution compared with a single-wavelength approach.\"},{\"question\":\"Which measurement topologies are supported?\",\"answer\":\"The sensor is implemented for both transmissive and reflective topologies, enabling light to propagate through the setup and be reflected back to the detector in the reflective configuration.\"}]","MACHINE-LEARNING ASSISTED SPECKLE-BASED POF SENSOR FOR DETECTING MICROVIBRATIONS | PDF"]