Abdullah, Ryan Gading
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

SISTEM DETEKSI PENYAKIT PADA OTAK DENGAN PENDEKATAN KLASIFIKASI CNN DAN PREPROCESSING IMAGE GENERATOR Kurniawan, Muchamad; Abdullah, Ryan Gading
Jurnal Informatika dan Teknik Elektro Terapan Vol 12, No 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4371

Abstract

In today's digital era, artificial intelligence technology has become an important part of various human activities, including in the healthcare sector. One of its focal points is the detection of brain diseases, which have significant implications for health and medical expenses. This study addresses the issue of accuracy in brain disease detection through the utilization of Convolutional Neural Network (CNN) methodology and preprocessing Image Generator. Previous research suggests that CNN with preprocessing Image Generator has the potential to enhance detection accuracy. The research employs the Computed Tomography (CT) of the Brain dataset from Kaggle, comprising 259 data points categorized into three classes: aneurysm, tumor, and cancer. Experimental findings indicate that the CNN method with preprocessing Image Generator yields higher accuracy in both training and testing phases, with reduced complexity. In conclusion, this method holds promise for more effective detection of brain diseases
Klasifikasi Bangunan secara Otomatis Menggunakan Pembelajaran Mendalam dari Gambar Street-View Abdullah, Ryan Gading; A., M. Mahameru; Rewina, Anggita Eka; Kurniawan, Muhammad Andhika; Hapsari, Dian Puspita
Prosiding Seminar Nasional Teknik Elektro, Sistem Informasi, dan Teknik Informatika (SNESTIK) 2025: SNESTIK V
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/p.snestik.2025.6874

Abstract

Urban population density mapping or urban utility planning requires a classification map based on individual buildings that are considered much more informative. The goal of this research is to determine how to extract the fine-grained boundaries of individual buildings from a street-view dataset. This paper proposes a general framework for classifying individual building functionality using a deep learning approach. The proposed method is based on a Convolutional Neural Network (CNN) that classifies facade structures from street view images, such as Street-View images. From the experiments conducted, the CNN classifier with the ResNet architecture was able to classify the Street-View data group with an accuracy value of 86.79%. We construct a dataset to train and evaluate the CNN classifier. Furthermore, the method is applied to generate a building classification map at the urban area scale.
SISTEM DETEKSI PENYAKIT PADA OTAK DENGAN PENDEKATAN KLASIFIKASI CNN DAN PREPROCESSING IMAGE GENERATOR Kurniawan, Muchamad; Abdullah, Ryan Gading
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4371

Abstract

In today's digital era, artificial intelligence technology has become an important part of various human activities, including in the healthcare sector. One of its focal points is the detection of brain diseases, which have significant implications for health and medical expenses. This study addresses the issue of accuracy in brain disease detection through the utilization of Convolutional Neural Network (CNN) methodology and preprocessing Image Generator. Previous research suggests that CNN with preprocessing Image Generator has the potential to enhance detection accuracy. The research employs the Computed Tomography (CT) of the Brain dataset from Kaggle, comprising 259 data points categorized into three classes: aneurysm, tumor, and cancer. Experimental findings indicate that the CNN method with preprocessing Image Generator yields higher accuracy in both training and testing phases, with reduced complexity. In conclusion, this method holds promise for more effective detection of brain diseases