{"title":"Perbandingan Metode Deep Residual Network 50 dan Deep Residual Network 152 untuk Deteksi Penyakit Pneumonia pada Manusia","authors":"Rifqi Rizqullah Eka Prasetyo, M. Ichwan","doi":"10.26760/mindjournal.v6i2.168-182","DOIUrl":null,"url":null,"abstract":"AbstrakPneumonia merupakan salah satu masalah Kesehatan yang sering dijumpai dan mempunyai dampak yang signifikan di seluruh dunia. Insiden pneumonia dilaporkan meningkat sesuai dengan bertambahnya usia. Pneumonia merupakan diagnosis terbanyak ketiga. Dalam penelitian ini penulis mengidentifikasi citra paru-paru dalam bentuk citra x-ray dengan metode ResNet-50 dan ResNet-152 sebagai ekstrasi ciri dan klasifikasinya. Performa sistem diukur berdasarkan nilai akurasi, presisi, recall, dan f-measure. Eksperimen dilakukan pada dataset paru-paru dengan menggunakan dua metode tersebut dan didapatkan akurasi terbaik pada ResNet-152. Hasil menunjukkan nilai rata-rata terbaik accuracy 89,3%, precision 88,8%, recall 89,6%, dan f-measure 89%. Hasil tersebut dipengaruhi oleh jumlah dataset dari citra training, citra validation, dan citra uji.Kata kunci: Penumonia, Deep Residual Network, RESNET-50, RESNET-152AbstractPneumonia is one of the most common health problems and has a significant impact throughout the world. The incidence of pneumonia is reported to increase with age. Pneumonia is the third most common diagnosis. In this study, the authors identified lung images in the form of x-ray images using the ResNet-50 and ResNet-152 methods as feature extraction and classification. System performance is measured based on the values of accuracy, precision, recall, and f-measure. Experiments were carried out on lung datasets using these two methods and the best accuracy was obtained on ResNet-152. The results show the best average value for accuracy is 89.3%, precision is 88.8%, recall is 89.6%, and f-measure is 89%. These results are influenced by the number of datasets from training images, validation images, and test images.Keywords: Penumonia, Deep Residual Network, RESNET-50, RESNET-152","PeriodicalId":43900,"journal":{"name":"Time & Mind-The Journal of Archaeology Consciousness and Culture","volume":"58 1","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Time & Mind-The Journal of Archaeology Consciousness and Culture","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26760/mindjournal.v6i2.168-182","RegionNum":4,"RegionCategory":"历史学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"ARCHAEOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
AbstrakPneumonia merupakan salah satu masalah Kesehatan yang sering dijumpai dan mempunyai dampak yang signifikan di seluruh dunia. Insiden pneumonia dilaporkan meningkat sesuai dengan bertambahnya usia. Pneumonia merupakan diagnosis terbanyak ketiga. Dalam penelitian ini penulis mengidentifikasi citra paru-paru dalam bentuk citra x-ray dengan metode ResNet-50 dan ResNet-152 sebagai ekstrasi ciri dan klasifikasinya. Performa sistem diukur berdasarkan nilai akurasi, presisi, recall, dan f-measure. Eksperimen dilakukan pada dataset paru-paru dengan menggunakan dua metode tersebut dan didapatkan akurasi terbaik pada ResNet-152. Hasil menunjukkan nilai rata-rata terbaik accuracy 89,3%, precision 88,8%, recall 89,6%, dan f-measure 89%. Hasil tersebut dipengaruhi oleh jumlah dataset dari citra training, citra validation, dan citra uji.Kata kunci: Penumonia, Deep Residual Network, RESNET-50, RESNET-152AbstractPneumonia is one of the most common health problems and has a significant impact throughout the world. The incidence of pneumonia is reported to increase with age. Pneumonia is the third most common diagnosis. In this study, the authors identified lung images in the form of x-ray images using the ResNet-50 and ResNet-152 methods as feature extraction and classification. System performance is measured based on the values of accuracy, precision, recall, and f-measure. Experiments were carried out on lung datasets using these two methods and the best accuracy was obtained on ResNet-152. The results show the best average value for accuracy is 89.3%, precision is 88.8%, recall is 89.6%, and f-measure is 89%. These results are influenced by the number of datasets from training images, validation images, and test images.Keywords: Penumonia, Deep Residual Network, RESNET-50, RESNET-152