Brain tumor has been acknowledged as the most dangerous disease through all its circles. Early identification of tumor disease is considered pivotal to identify the spread of brain tumors in administering the appropriate treatment. This study proposes a Convolutional Neural Network method to detect brain tumor on MRI images. The 3264 datasets were undertaken in this study with detailed images of Glioma tumor (926 images), Meningioma tumors (937 images), pituitary tumors (901 images), and other with no-tumors (500 images). The application of CNN method combined with Hyperparameter Tuning is proposed to achieve optimal results in classifying the brain tumor types. Hyperparameter Tuning acts as a navigator to achieve the best parameters in the proposed CNN model. In this study, the model testing was conducted with three different scenarios. The result of brain tumor classification depicts an accuracy of 96% in the third model testing scenario.
ABSTRAKPenyakit COVID-19 dapat timbul karena berbagai faktor sebab dan akibat, sehingga penyakit ini memiliki efek buruk bagi penderita. Pencitraan CT-Scan memiliki keunggulan dalam memproyeksikan kondisi paru-paru pasien penderita, sehingga dapat membantu dalam mendeteksi tingkat keparahan penyakit. Dalam studi ini, penelitian dilakukan untuk mendeteksi penyakit COVID-19 melalui citra CT-Scan menggunakan metode Filter Gabor dan Convolutional Neural Networks (CNN) dengan Hyperparameter Tuning. Data yang digunakan yaitu citra CT-Scan SARSCoV-2 berjumlah 2481 gambar. Sebelum melatih model, dilakukan preprocessing data, seperti pelabelan, pengubahan ukuran, dan augmentasi gambar. Pengujian Model dilakukan dengan beberapa skenario uji. Hasil terbaik diperoleh pada skenario untuk model Filter Gabor dan CNN dengan Hyperparameter Tuning mendapatkan akurasi sebesar 97,9% dan AUC sebesar 99% dibandingkan dengan model tanpa Hyperparameter Tuning dan Filter Gabor.Kata kunci: COVID-19, CNN, Filter Gabor, Hyperparameter Tuning, COVID-19 Classification ABSTRACTCOVID-19 disease can arise due to various causal and causal factors, so it has an adverse effect on patients. CT-Scan imaging has an advantage in projecting the lung condition of patients with the patient, so it can help in detecting the severity of the disease. In this study, research was conducted to detect COVID-19 disease through CT-Scan imagery using Gabor Filter method and Convolutional Neural Networks (CNN) with Hyperparameter Tuning. The data used is CT-Scan SARSCoV-2 imagery amounting to 2481 images. Before training the model, preprocessing data is performed, such as labeling, resizing, and augmentation of images. Model testing is performed with multiple test scenarios. The best results were obtained in scenarios for The Gabor Filter model and CNN with Hyperparameter Tuning getting 97.9% accuracy and AUC by 99% compared to models without Hyperparameter Tuning and Gabor Filter.Keywords: COVID-19, CNN, Filter Gabor, Hyperparameter Tuning, COVID-19 Classification
Diabetic Retinopathy (DR) is a disease that causes visual impairment and blindness in patients with it. Diabetic Retinopathy disease appears characterized by a condition of swelling and leakage in the blood vessels located at the back of the retina of the eye. Early detection through the retinal fundus image of the eye could take time and requires an experienced ophthalmologist. This study proposed a deep learning method, the Efficientnet-b7 model to identify diabetic retinopathy disease automatically. This study applies three preprocessing techniques that could be implemented in the dataset "APTOS 2019 Blindness Detection". In preprocessing technique trial scenarios, Usuyama preprocessing technique obtained the best results with accuracy of 89% of train data and 84% in test data compared to Harikrishnan preprocessing technique which has 82% accuracy in test data, and Ben Graham preprocessing has 81% accuracy in test data. In this study, Hyperparameter tuning was conducted to find the best parameters for use on the EfficientNet-B7 Model. In this study, we tested the Efficientnet-B7 model with an augmentation process that can reduce the occurrence of overfitting compared to models without augmentation. Preprocessing techniques and augmentation techniques can influence the proposed EfficientNet-B7 model in terms of performance results and reduce the overfitting of models.
Seiring berjalannya waktu, jalan dapat mengalami penurunan kualitas hingga kerusakan. Kerusakan jalan tentunya sangat mengganggu aktivitas masyarakat dan akan menjadi lebih buruk ketika banyak jalan yang rusak secara bersamaan dalam waktu dekat. Maka dari itu, diperlukan tindakan perawatan dan perbaikan jalan dengan cepat dan tepat. Penelitian ini dilakukan di Desa Gawan dan bertujuan untuk menentukan prioritas perbaikan jalan menggunakan metode AHP. Kriteria yang digunakan dalam metode AHP ini adalah kondisi jalan, perkerasan jalan, status jalan, fungsi jalan, dan kelas jalan. Berdasarkan penelitian ini, kriteria yang memiliki bobot tertinggi adalah kondisi jalan dengan bobot 0.505 dan ruas jalan dengan kode 540900081082 menjadi prioritas pertama untuk perbaikan dengan bobot akhir 0.312172641 dan kondisi jalan rusak.Seiring berjalannya waktu, jalan dapat mengalami penurunan kualitas hingga kerusakan. Kerusakan jalan tentunya sangat mengganggu aktivitas masyarakat dan akan menjadi lebih buruk ketika banyak jalan yang rusak secara bersamaan dalam waktu dekat. Maka dari itu, diperlukan tindakan perawatan dan perbaikan jalan dengan cepat dan tepat. Penelitian ini dilakukan di Desa Gawan dan bertujuan untuk menentukan prioritas perbaikan jalan menggunakan metode AHP. Kriteria yang digunakan dalam metode AHP ini adalah kondisi jalan, perkerasan jalan, status jalan, fungsi jalan, dan kelas jalan. Berdasarkan penelitian ini, kriteria yang memiliki bobot tertinggi adalah kondisi jalan dengan bobot 0.505 dan ruas jalan dengan kode 540900081082 menjadi prioritas pertama untuk perbaikan dengan bobot akhir 0.312172641 dan kondisi jalan rusak.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.