{"id":12702,"date":"2021-12-23T15:31:05","date_gmt":"2021-12-23T14:31:05","guid":{"rendered":"https:\/\/www.teoresigroup.com\/?post_type=thesis&#038;p=12702"},"modified":"2022-01-26T15:53:54","modified_gmt":"2022-01-26T14:53:54","slug":"nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale","status":"publish","type":"thesis","link":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/","title":{"rendered":"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale"},"content":{"rendered":"\n<div class=\"wp-block-columns align-center row sezione\">\n<div class=\"wp-block-column small-12 medium-10 large-8\">\n<h5 class=\"has-text-align-center wp-block-heading\">Abstract<\/h5>\n\n\n\n<p>Questa ricerca descrive lo sviluppo di un approccio di deep learning per la stima della frequenza cardiaca a distanza.<br>Domanda di ricerca: le riprese video di un essere umano trasmettono informazioni grafiche sufficienti per stimare accuratamente alcuni parametri clinici?<br>Nel lavoro proposto, cerchiamo di rispondere a questa domanda costruendo un sistema end-to-end che riceve immagini (o frame) come input e produce la stima della frequenza cardiaca.<br>Il campo del rilevamento della frequenza cardiaca senza contatto \u00e8 vasto, pertanto tutti i metodi proposti in precedenza sono stati studiati e analizzati. L&#8217;approccio di deep learning proposto si chiama NrPPG-NNET ed \u00e8 stato sviluppato applicando la conoscenza di una Rete Neurale Convoluzionale precedentemente addestrata per il riconoscimento delle immagini e riaddestrata per risolvere il nuovo task. NrPPG-NNET ottiene risultati competitivi in termini di Errore Medio Assoluto (espresso in bpm) ed \u00e8 significativamente pi\u00f9 leggero della maggior parte dei metodi precedentemente proposti, infatti pu\u00f2 essere eseguito in tempo reale su laptop di fascia media (anche senza GPU). Grazie alla sua velocit\u00e0 e facilit\u00e0 d&#8217;uso, NrPPG-NNET potrebbe potenzialmente trovare applicazione nel campo dell&#8217;interazione uomo-computer e del monitoraggio clinico. Inoltre, durante lo sviluppo sono emersi indizi importanti per il lavoro futuro che forniscono una solida base per ulteriori ricerche.<\/p>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">Obiettivo Tesi<\/h5>\n\n\n\n<p>Sviluppo di un modello per la predizione Heart rate basato su intelligenza artificiale, che prende in input un video da cui vengono estratti i frame, i quali vengono preprocessati al fine di ottenere un opportuno dataset per la rete neurale responsabile della stima del battito cardiaco.<\/p>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">Metodologia di ricerca<\/h5>\n\n\n\n<p>Preprocessing video per la creazione di mappe spazio-temporali. Sviluppo e training di una rete neurale con successiva validazione del modello.<\/p>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">Conclusioni<\/h5>\n\n\n\n<p>Realizzato un modello per la predizione del battito cardiaco che ottiene buoni risultati e che ad oggi si pone in linea con lo stato dell\u2019arte.<\/p>\n\n\n\n<h5 class=\"has-text-align-center wp-block-heading\">Sviluppi futuri<\/h5>\n\n\n\n<p>Testing su diversi dataset e miglioramento del modello attuale.<\/p>\n<\/div>\n<\/div>\n","protected":false},"featured_media":0,"template":"","university":[245],"thesis_type":[273,275,255],"keyword":[241,243,242,240,187,239],"class_list":["post-12702","thesis","type-thesis","status-publish","hentry","university-universita-di-utrecht-it","thesis_type-artificial-intelligence-it","thesis_type-deep-learning-it","thesis_type-python-it","keyword-ai","keyword-computer-vision","keyword-deep-learning","keyword-heart-rate-contactless-prediction","keyword-python","keyword-pytorch"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group<\/title>\n<meta name=\"description\" content=\"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group\" \/>\n<meta property=\"og:description\" content=\"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/\" \/>\n<meta property=\"og:site_name\" content=\"Teoresi Group\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/pages\/Gruppo-Teoresi\/118393464917205\" \/>\n<meta property=\"article:modified_time\" content=\"2022-01-26T14:53:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.teoresigroup.com\/wp-content\/uploads\/2021\/02\/og-image.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"630\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/thesis\\\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\\\/\",\"url\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/thesis\\\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\\\/\",\"name\":\"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#website\"},\"datePublished\":\"2021-12-23T14:31:05+00:00\",\"dateModified\":\"2022-01-26T14:53:54+00:00\",\"description\":\"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/thesis\\\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/thesis\\\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/thesis\\\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\",\"item\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#website\",\"url\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/\",\"name\":\"Teoresi Group\",\"description\":\"Engineering for Human life.\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#organization\",\"name\":\"Teoresi Group\",\"url\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.teoresigroup.com\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/teoresi-logo-color.svg\",\"contentUrl\":\"https:\\\/\\\/www.teoresigroup.com\\\/wp-content\\\/uploads\\\/2020\\\/12\\\/teoresi-logo-color.svg\",\"width\":1,\"height\":1,\"caption\":\"Teoresi Group\"},\"image\":{\"@id\":\"https:\\\/\\\/www.teoresigroup.com\\\/it\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/pages\\\/Gruppo-Teoresi\\\/118393464917205\",\"https:\\\/\\\/www.instagram.com\\\/teoresigroup\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/teoresigroup\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCNdBBSSax2EWPmFk5QzYP8Q\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group","description":"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/","og_locale":"it_IT","og_type":"article","og_title":"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group","og_description":"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.","og_url":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/","og_site_name":"Teoresi Group","article_publisher":"https:\/\/www.facebook.com\/pages\/Gruppo-Teoresi\/118393464917205","article_modified_time":"2022-01-26T14:53:54+00:00","og_image":[{"width":1200,"height":630,"url":"https:\/\/www.teoresigroup.com\/wp-content\/uploads\/2021\/02\/og-image.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Tempo di lettura stimato":"2 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/","url":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/","name":"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale - Teoresi Group","isPartOf":{"@id":"https:\/\/www.teoresigroup.com\/it\/#website"},"datePublished":"2021-12-23T14:31:05+00:00","dateModified":"2022-01-26T14:53:54+00:00","description":"Discover all you need to know about NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale on Teoresi Group - Teoresi Group is high profile engineering. It offers an innovative approach in close synergy with the Research and Development departments of the main industrial players.","breadcrumb":{"@id":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.teoresigroup.com\/it\/thesis\/nrppg-nnet-un-approccio-endtoend-di-deep-learning-per-la-stima-della-frequenza-cardiaca-a-distanza-attraverso-la-rappresentazione-temporale-spaziale\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"","item":"https:\/\/www.teoresigroup.com\/it\/"},{"@type":"ListItem","position":2,"name":"NrPPG-NNET: un approccio end-to-end di Deep Learning per la stima della frequenza cardiaca a distanza attraverso la rappresentazione temporale spaziale"}]},{"@type":"WebSite","@id":"https:\/\/www.teoresigroup.com\/it\/#website","url":"https:\/\/www.teoresigroup.com\/it\/","name":"Teoresi Group","description":"Engineering for Human life.","publisher":{"@id":"https:\/\/www.teoresigroup.com\/it\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.teoresigroup.com\/it\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"it-IT"},{"@type":"Organization","@id":"https:\/\/www.teoresigroup.com\/it\/#organization","name":"Teoresi Group","url":"https:\/\/www.teoresigroup.com\/it\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/www.teoresigroup.com\/it\/#\/schema\/logo\/image\/","url":"https:\/\/www.teoresigroup.com\/wp-content\/uploads\/2020\/12\/teoresi-logo-color.svg","contentUrl":"https:\/\/www.teoresigroup.com\/wp-content\/uploads\/2020\/12\/teoresi-logo-color.svg","width":1,"height":1,"caption":"Teoresi Group"},"image":{"@id":"https:\/\/www.teoresigroup.com\/it\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/pages\/Gruppo-Teoresi\/118393464917205","https:\/\/www.instagram.com\/teoresigroup\/","https:\/\/www.linkedin.com\/company\/teoresigroup\/","https:\/\/www.youtube.com\/channel\/UCNdBBSSax2EWPmFk5QzYP8Q"]}]}},"acf":[],"_links":{"self":[{"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/thesis\/12702","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/thesis"}],"about":[{"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/types\/thesis"}],"version-history":[{"count":5,"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/thesis\/12702\/revisions"}],"predecessor-version":[{"id":13443,"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/thesis\/12702\/revisions\/13443"}],"wp:attachment":[{"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/media?parent=12702"}],"wp:term":[{"taxonomy":"university","embeddable":true,"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/university?post=12702"},{"taxonomy":"thesis_type","embeddable":true,"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/thesis_type?post=12702"},{"taxonomy":"keyword","embeddable":true,"href":"https:\/\/www.teoresigroup.com\/it\/wp-json\/wp\/v2\/keyword?post=12702"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}