[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118583-en":3,"doc-seo-118583-105":30,"detail-sidebar-cat-0-en-105":91},{"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},118583,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Enhancing Eye Diseases Classification Using Imbalance Training - Machine Learning","The study evaluates the effectiveness of multiple machine learning algorithms for classifying eye diseases from retinal images, using a four-class dataset: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. A transfer-learning feature extraction pipeline based on ResNet50 is followed by SMOTE to address class imbalance, PCA for dimensionality reduction, and normalization for consistent scaling. Eleven models across baseline, ensemble, and neural network approaches are assessed with accuracy, precision, recall, F1-score, and K-Fold cross-validation. Results show XGBoost achieves the best accuracy (92.03%), exceeding LightGBM (91.88%) and MLP (91.50%), with K-Folds improving MLP stability.","Enhancing Eye Diseases Classification Using Imbalance Training &  \nMachine Learning  \nMuhammad Azrul Ihwan 1*, Ajie Kusuma Wardhana 2*  \n* Informatika, Universitas Amikom Yogyakarta  \n[muhammadazrulihwan@students.amikom.ac.id](muhammadazrulihwan@students.amikom.ac.id1)[1](muhammadazrulihwan@students.amikom.ac.id1), [ajiekusuma@amikom.ac.id](ajiekusuma@amikom.ac.id 2)[ 2](ajiekusuma@amikom.ac.id 2),  \n\n| Article history:\u003Cbr>Received 2025-07-13 Revised 2025-07-21 Accepted 2025-07-30 | This research aims to evaluate the effectiveness of various machine learning algorithms in classifying eye diseases based on retinal images. The dataset comprises four categories of eye diseases: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. The feature extraction method employed a transfer learning approach using ResNet50, followed by SMOTE for data balancing, PCA for dimensionality reduction, and normalization for scaling data consistently. Eleven machine learning models were evaluated, including basic algorithms, ensemble methods, and neural networks. The evaluation utilized metrics such as accuracy, precision, recall, and F1-score. K-Fold Cross Validation is also employed to observe all models'generalisation. The results revealed that the XGBoost algorithm achieved the highest performance with an accuracy of 92.03%, followed by LightGBM 91.88% and MLP 91.50%. K-Fold Validation also improved the MLP performance, which achieved an average accuracy of 91.94% with a standard deviation of 0.0178. This study successfully enhanced classification accuracy compared to previous studies and shows significant potential for clinical applications in resource-limited environments.\u003Cbr>\u003Cbr>This is an open access article under the CC–BY-SA license. |\n| --- | --- |\n| Keyword:\u003Cbr>Eye Disease Classification,\u003Cbr>XGBoost, LightGBM, SMOTE. |  |\n\nArticle Info ABSTRACT  \nI. PENDAHULUAN  \nPenyakit mata seperti katarak, glaukoma, dan retinopati diabetik merupakan penyebab utama gangguan penglihatan dan kebutaan yang memengaruhi kualitas hidup manusia secara global diperkirakan sebanyak 596 juta orang di seluruh dunia mengalami gangguan penglihatan jarakjauh pada tahun 2020, dengan sekitar 43 juta kasus di antaranya merupakan kebutaan[1]. Diagnosis umumnya dilakukan oleh dokter mata melalui pemeriksaan langsung atau analisis citra retina. Namun, dalam beberapa tahun terakhir, teknologi machine learning mulai dimanfaatkan untuk mendukung proses diagnosis[2]. Sejumlah penelitian menunjukkan bahwa metode berbasis machine learning mampu mengidentifikasi pola dan karakteristik visual dalam citra medis yang sulit dideteksi oleh mata manusia, serta meningkatkan kecepatan dan akurasi untuk penyakit mata[3],[4] .  \nNamun, Sebagian besar studi sebelumnya yang menggunakan teknik deep learning cenderung memerlukan dataset besar serta daya komputasi tinggi, dan sebagian besar hanya berfokus pada deteksi satu jenis penyakit mata seperti  \nDiabetic Retinopaty, Cataract atau Glaucoma secara terpisah. [5]. Saat ini, belum banyak yang mengeksplorasiklasifikasi multi-kelas untuk membedakan berbagai bentuk gangguan mata dalam satu system klasifikasi[6] . Meskipunefektivitas deep learning telah menunjukkan performa tinggidalam analisis citra medis, model deep learning masihdianggap sebagai “black box” karena kurangnya kejelasandalam mekanisme pengambilan Keputusan dan keterbatasanpada aspek interpretabilitasnya[7], [8]. Oleh karena itu, diperlukan metode alternatif yang lebih ringan dan fleksibel yang dapat memanfaatkan dataset terbatas secara efektif sambil tetap menjaga tingkat akurasi yang tinggi[9] .  \nMetode berbasis ekstraksi fitur dari citra retina menawarkan solusi alternatif yang lebih ringan dibanding pendekatan deep learning end-to-end. Dengan mengekstraksielemen-elemen penting seperti tekstur, warna, dan bentuk, informasi visual dari retina dapat di representasikan dalambentuk vector numerik. Hasil vector kemudian dapatdimanfaatkan oleh algoritma machine learning untuk mela","cbCairiO4e7vCdK5","https://ap.wps.com/l/cbCairiO4e7vCdK5","pdf",757605,1,11,"English","en",105,"# Introduction\n## Background and motivation\n## Limitations of prior deep learning approaches\n## Feature extraction as an alternative\n# Methodology\n## Dataset preparation\n## Feature extraction with ResNet50\n## SMOTE balancing and PCA reduction\n## Classification models and evaluation","[{\"question\":\"What eye disease classes are included in the dataset?\",\"answer\":\"The dataset contains four categories: Cataract, Diabetic Retinopathy, Glaucoma, and Normal.\"},{\"question\":\"How does the approach handle class imbalance?\",\"answer\":\"It applies SMOTE (Synthetic Minority Over-sampling Technique) to balance the number of samples across classes before training.\"},{\"question\":\"Which machine learning model achieves the highest classification performance?\",\"answer\":\"XGBoost delivers the best results, reaching 92.03% accuracy, followed by LightGBM at 91.88% and MLP at 91.50%.\"}]","Enhancing Eye Diseases Classification Using Imbalance Training - Machine Learning | PDF",1785684383,28,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"enhancing-eye-diseases-classification-using-imbalance-training-machine-learning","",{"@graph":36,"@context":85},[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/enhancing-eye-diseases-classification-using-imbalance-training-machine-learning/118583/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What eye disease classes are included in the dataset?","Question",{"text":75,"@type":76},"The dataset contains four categories: Cataract, Diabetic Retinopathy, Glaucoma, and Normal.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the approach handle class imbalance?",{"text":80,"@type":76},"It applies SMOTE (Synthetic Minority Over-sampling Technique) to balance the number of samples across classes before training.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning model achieves the highest classification performance?",{"text":84,"@type":76},"XGBoost delivers the best results, reaching 92.03% accuracy, followed by LightGBM at 91.88% and MLP at 91.50%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]