[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126955-en":3,"doc-seo-126955-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126955,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques - 关键方法与分类结果优化","Electroretinography (ERG) provides a non-invasive assessment of retinal function by recording responses to brief light flashes. This study improves ERG waveform classification by applying Short-Time Fourier Transform (STFT) spectrogram preprocessing paired with machine learning decision systems. Multiple STFT window functions with different sizes and overlaps are compared to enhance feature extraction for specific algorithms. Spectrograms support deep learning models, while classical machine learning models also benefit from manual feature extraction. Results show Visual Transformer with a Hamming window performs best for ERG classification, whereas RF is recommended when manual features are required, especially with Boxcar or Bartlett windows, advancing clinical diagnostic capability.","bioengineering  \nArticle  \nElectroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques  \nFaisal Albasu 1,2, *,†, Mikhail Kulyabin 3, *,†, Aleksei Zhdanov 1, Anton Dolganov 1 ,  \nMikhail Ronkin 1, Vasilii Borisov 1, Leonid Dorosinsky 1, Paul A. Constable 4, Mohammed A. Al-masni 2, * and Andreas Maier 3  \nCitation: Albasu, F. ; Kulyabin, M.; Zhdanov, A.; Dolganov, A.; Ronkin, M.; Borisov, V.; Dorosinsky, L.;  \nConstable, P.A.; Al-masni, M.A.; Maier, A. Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques. Bioengineering 2024, 11, 866 .  \n[https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)bioengineering11090866  \nAcademic Editors: Qifa Zhou and Xuejun Qian  \nReceived: 4 July 2024  \nRevised: 18 August 2024  \nAccepted: 21 August 2024  \nPublished: 26 August 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Engineering School of Information Technologies, Telecommunications and Control Systems, Ural Federal University Named after the First President of Russia B. N. Yeltsin, 620002 Yekaterinburg, Russia;  \n[a.e.zhdanov@urfu.ru](a.e.zhdanov@urfu.ru) (A.Z.); [anton.dolganov@urfu.ru](anton.dolganov@urfu.ru) (A.D.); [m.v.ronkin@urfu.ru](m.v.ronkin@urfu.ru) (M.R.);  \n[v.i.borisov@urfu.ru](v.i.borisov@urfu.ru) (V.B.); [l.g.dorosinskiy@urfu.ru](l.g.dorosinskiy@urfu.ru) (L.D.)  \n2 Department of Artificial Intelligence and Data Science, College of Software & Convergence Technology, Daeyang AI Center, Sejong University, Seoul 05006, Republic of Korea  \n3 Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91058 Erlangen, Germany; [andreas.maier@fau.de](andreas.maier@fau.de)  \n4 College of Nursing and Health Sciences, Caring Futures Institute, Flinders University, Adelaide, SA 5042, Australia; [paul.constable@flinders.edu.au](paul.constable@flinders.edu.au)  \n* Correspondence: [falbasu@urfu.ru](falbasu@urfu.ru) (F.A.); [mikhail.kulyabin@fau.de](mikhail.kulyabin@fau.de) (M.K.);  \n[m.almasani@sejong.ac.kr](m.almasani@sejong.ac.kr) (M.A.A.-m.)† These authors contributed equally to this work.  \nAbstract: Electroretinography (ERG) is a non-invasive method of assessing retinal function by recording the retina’s response to a brief flash of light. This study focused on optimizing the ERG waveform signal classification by utilizing Short-Time Fourier Transform (STFT) spectrogram preprocessing with a machine learning (ML) decision system. Several window functions of different sizes and window overlaps were compared to enhance feature extraction concerning specific ML algorithms. The obtained spectrograms were employed to train deep learning models alongside manual feature extraction for more classical ML models. Our findings demonstrated the superiority of utilizing the Visual Transformer architecture with a Hamming window function, showcasing its advantage in ERG signal classification. Also, as a result, we recommend the RF algorithm for scenarios necessitating manual feature extraction, particularly with the Boxcar (rectangular) or Bartlett window functions. By elucidating the optimal methodologies for feature extraction and classification, this study contributes to advancing the diagnostic capabilities of ERG analysis in clinical settings.  \nKeywords: electroretinography; biomedical signal processing algorithms; short-time Fourier transform; spectrogram; feature extraction; classification; machine learning; deep learning; neural network; retinal study  \n1. Introduction  \nElectroretinography (ERG) is a non-invasive form of assessing the functional health of the retina through it","cbCaisBEphEVA2r2","https://ap.wps.com/l/cbCaisBEphEVA2r2","pdf",5659891,1,21,"English","en",105,"# Introduction\n## Electroretinography as a Non-invasive Retinal Function Assessment\n## ERG Waveform Components and Signal Characteristics\n# STFT Spectrogram Preprocessing and Feature Extraction\n## Window Functions, Sizes, and Overlaps\n## Spectrograms for Deep Learning and Classical ML\n# Machine Learning and Deep Learning Models for ERG Classification\n## Visual Transformer with Hamming Window\n## Manual Feature Extraction and Random Forest Recommendations","[{\"question\":\"What is the main goal of this ERG study?\",\"answer\":\"To optimize ERG waveform signal classification by using STFT spectrogram preprocessing together with machine learning decision systems and feature extraction strategies.\"},{\"question\":\"How does STFT contribute to improving ERG classification?\",\"answer\":\"STFT converts ERG signals into spectrogram representations, and comparing window functions, sizes, and overlaps helps enhance the extracted features used by different ML algorithms.\"},{\"question\":\"Which model and preprocessing choice shows the best performance?\",\"answer\":\"The Visual Transformer architecture combined with a Hamming window provides superior results for ERG signal classification.\"},{\"question\":\"When is the Random Forest (RF) algorithm recommended?\",\"answer\":\"RF is recommended for scenarios requiring manual feature extraction, particularly when using Boxcar (rectangular) or Bartlett window functions.\"}]","Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques - 关键方法与分类结果优化 | PDF",1785935876,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"electroretinogram-analysis-using-a-short-time-fourier-transform-and-machine-learning-techniques-key-method-and-classification-results","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/electroretinogram-analysis-using-a-short-time-fourier-transform-and-machine-learning-techniques-key-method-and-classification-results/126955/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this ERG study?","Question",{"text":75,"@type":76},"To optimize ERG waveform signal classification by using STFT spectrogram preprocessing together with machine learning decision systems and feature extraction strategies.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does STFT contribute to improving ERG classification?",{"text":80,"@type":76},"STFT converts ERG signals into spectrogram representations, and comparing window functions, sizes, and overlaps helps enhance the extracted features used by different ML algorithms.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model and preprocessing choice shows the best performance?",{"text":84,"@type":76},"The Visual Transformer architecture combined with a Hamming window provides superior results for ERG signal classification.",{"name":86,"@type":73,"acceptedAnswer":87},"When is the Random Forest (RF) algorithm recommended?",{"text":88,"@type":76},"RF is recommended for scenarios requiring manual feature extraction, particularly when using Boxcar (rectangular) or Bartlett window functions.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]