[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-663429-105":3,"doc-detail-663429-en":81,"detail-sidebar-cat-0-en-105":98},{"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","symbol-detection-in-a-multi-class-dataset-based-on-single-line-diagrams-using-deep-learning-models","Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models","","Single Line Diagrams (SLDs) play a critical role in electrical power distribution systems, guiding engineers during installation, maintenance, and inspection. Deep learning object detection can digitize these documents, yet class imbalance in technical drawings limits effective symbol recognition. This paper proposes a solution using YOLOv8 for localization and detection, achieving nearly 95% symbol detection accuracy, and a GAN-based synthetic dataset augmentation approach where YOLOv5 classification exceeds 96.3%.",{"@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/symbol-detection-in-a-multi-class-dataset-based-on-single-line-diagrams-using-deep-learning-models/663429/",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/symbol-detection-in-a-multi-class-dataset-based-on-single-line-diagrams-using-deep-learning-models/663429.png","ImageObject",300,407,{"name":42,"@type":43},"Danger Angel","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-10-28",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is symbol detection on single-line diagrams challenging?","Question",{"text":63,"@type":64},"SLDs contain many symbols that can be visually similar but functionally different, and class imbalance in technical drawings complicates learning.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the approach detect symbols in SLDs?",{"text":68,"@type":64},"It uses YOLOv8 to localize and detect symbols present in the single-line diagrams, with experiments reporting almost 95% accuracy.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the method address class imbalance?",{"text":72,"@type":64},"It generates synthetic images with a multi-fake class GAN (MFCGAN), combines them with original images to form an augmented dataset, then uses YOLOv5 for classification.","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},663429,1793227701,{"code":4,"msg":82,"data":83},"success",{"doc_id":79,"user_id":84,"nickname":42,"user_avatar":85,"doc_module":4,"category_id":86,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":87,"file_id":88,"file_url":89,"file_type":90,"file_size":91,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":92,"language":93,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":94,"faqs":95,"seo_title":96,"seo_description":12,"update_tm":80,"read_time":97},962090769052,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models  \nHina Bhanbhro 1, Yew Kwang Hooi2, Worapan Kusakunniran3, Zaira Hassan Amur4 Computer and Information Science Department, Universiti Teknologi,  \nPETRONAS Seri Iskandar, Perak Darul Ridzuan, Malaysia 1, 2, 4  \nFaculty of Information and Communication Technology, Mahidol University, Thailand3  \nAbstract—Single Line Diagrams (SLDs) are used in electrical power distribution systems. These diagrams are crucial to engineers during the installation, maintenance, and inspection phases. For the digital interpretation of these documents, deep learning-based object detection methods can be utilized. However, there is a lack of efforts made to digitize the SLDs using deep learning methods, which is due to the class-imbalance problem of these technical drawings. In this paper, a method to address this challenge is proposed. First, we use the latest variant of You Look Only Once (YOLO), YOLO v8 to localize and detect the symbols present in the single-line diagrams. Our experiments determine that the accuracy of symbol detection based on YOLOv8 is almost 95%, which is more satisfactory than its previous versions. Secondly, we use a synthetic dataset generated using multi-fake class generative adversarial network (MFCGAN) and create fake classes to cope with the class imbalance problem. The images generated using the GAN are then combined with the original images to create an augmented dataset, and YOLO v5 is used for the classification of the augmented dataset. The experiments reveal that the GAN model had the capability to learn properly from a small number of complex diagrams. The detection results show that the accuracy of YOLO v5 is more than 96.3%, which is higher than the YOLO v8 accuracy. After analyzing the experiment results, we might deduce that creating multiple fake classes improved the classification of engineering symbols in SLDs.  \nKeywords—Single line diagrams; engineering drawings; synthetic data; symbol detection; deep learning; augmented dataset  \nI. INTRODUCTION  \nAn engineering drawing (ED) is an illustration of a schematic that demonstrates the operation or construction of an electrical system, procedure, or plant facility [1] . Engineering designs comprise of technical drawings such as mechanical or architectural blueprints, electrical circuits, and drawings [2] . In many different businesses, there is an increasing need for establishing digital systems for processing and analyzing these representations [3] . With such a framework, connected businesses will have the unusual opportunity to make extensive use of diagrams to direct their future practices.  \nA single-line diagram uses lines and symbols to represent the logical flow of power through physical processes and plant components. Although these components resemble each other in form and shape, they are highly asymmetrical in nature, which makes these documents complex [1] . Distinct power distributions are represented by lines of variable thickness, and each sign stands for a different component such as a  \ntransformer, generator, motor, switch, etc. [4] . A typical SLD diagram may have over 50 different symbols, making it an information-rich visual representation. While placing a purchase order or even when project teams are scheduling their work, these drawings are carefully inspected in order to estimate the numbers of various pieces of equipment [5] . When symbols on SLD diagrams are functionally different but visually identical, as in Fig. 1, this process can become considerably more difficult and complex. As a result, distinguishing one symbol from another can be both crucial and difficult. Misreading or omitting any material can also cause severe internal disagreements and be damaging to the progress of a project.  \nScientists, on the other hand, are looking into solutions fora power system to transform the conventional power system that existed before into ","cbCaitTeXouERFp7","https://ap.wps.com/l/cbCaitTeXouERFp7","pdf",1191696,14,"English","# Abstract\n# I. Introduction","[{\"question\":\"Why is symbol detection on single-line diagrams challenging?\",\"answer\":\"SLDs contain many symbols that can be visually similar but functionally different, and class imbalance in technical drawings complicates learning.\"},{\"question\":\"How does the approach detect symbols in SLDs?\",\"answer\":\"It uses YOLOv8 to localize and detect symbols present in the single-line diagrams, with experiments reporting almost 95% accuracy.\"},{\"question\":\"How does the method address class imbalance?\",\"answer\":\"It generates synthetic images with a multi-fake class GAN (MFCGAN), combines them with original images to form an augmented dataset, then uses YOLOv5 for classification.\"}]","Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models | PDF",35,{"code":4,"msg":82,"data":99},[100,104,108,112,116,121,126,129,134,137,141],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":113,"show_sort_weight":114,"slug":115},"Comic",60,"comic",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":118,"show_sort_weight":119,"slug":120},6,"Technology",50,"technology",{"id":122,"doc_module":4,"doc_module_name":25,"category_name":123,"show_sort_weight":124,"slug":125},7,"Healthcare",40,"healthcare",{"id":86,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":127,"slug":128},30,"research-report",{"id":130,"doc_module":4,"doc_module_name":25,"category_name":131,"show_sort_weight":132,"slug":133},9,"Religion & Spirituality",20,"religion-spirituality",{"id":132,"doc_module":4,"doc_module_name":25,"category_name":135,"show_sort_weight":132,"slug":136},"World Cup","world-cup",{"id":138,"doc_module":4,"doc_module_name":25,"category_name":139,"show_sort_weight":138,"slug":140},10,"Lifestyle","lifestyle",{"id":142,"doc_module":4,"doc_module_name":25,"category_name":143,"show_sort_weight":55,"slug":144},19,"General","general"]