Article Per Year (5 Year)
p-Index From 2020 - 2025
1.259
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal International Journal of Community Service TRIMAS: Jurnal Inovasi dan Pengabdian Kepada Masyarakat Mathematics Education Journal
Samsuryadi
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Civil Engineering, Building, Construction & Architecture Computer Science & IT Education Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Public Health Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : ComEngApp : Computer Engineering and Applications Journal

 1 
Detection of Diabetic Retinopathy Using Convolutional Neural Network (CNN) Yazid, Rizq Khairi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 11 No. 3 (2022)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

One of the complications of Diabetes Mellitus, namely Diabetic Retinopathy (DR) damages the retina of the eye and has five levels of severity: Normal, Mild, Medium, Severe and Proliferate. If not detected and treated, this complication can lead to blindness. Detection and classification of this disease is still done manually by an ophthalmologist using an image of the patient's eye fundus. Manual detection has the disadvantage that it requires an expert in the field and the process is difficult. This research was conducted by detecting and classifying DR disease using Convolutional Neural Network (CNN). The CNN model was built based on the VGG-16 architecture to study the characteristics of the eye fundus images of DR patients. The model was trained using 4750 images which were rescaled to 256 X 256 size and converted to grayscale using the BT-709 (HDTV) method. The CNN-based software with VGG- 16 architecture developed resulted in an accuracy of 62% for the detection and classification of 100 test images based on five DR severity classes. This software produces the highest Sensitivity value in the Normal class at 90% and the largest Specificity value in the Mild class at 97.5%.
Brahmi Script Classification using VGG16 Architecture Convolutional Neural Network Vincen; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 11 No. 2 (2022)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Many Indonesians have difficulty reading and learning the Brahmi script. Solving these problems can be done by developing software. Previous research has classified the Brahmi script but has not had an output that matches the letter. Therefore, letter classification is carried out as part of the process of recognizing Brahmi script. This study uses the Convolutional Neural Network (CNN) method with the VGG16 architecture for classifying Brahmi script writing. Training results from various amounts of image data. Smooth model. The requested image data is a 224x224 binary image. This study has the highest quality, accuracy is 96%, highest recall is 98% and highest precision is 98%.
Classification of Epilepsy Diagnostic Results through EEG Signals Using the Convolutional Neural Network Method Sari, Tri Kurnia; Rini, Dian Palupi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 12 No. 2 (2023)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The brain is one of the most important organs in the human body as a central nervous system which functions as a controlling center, intelligence, creativity, emotions, memories, and body movements. Epileptic seizure is one of the disorder of the brain central nervous system which has many symptoms, such as loss of awareness, unusual behavior and confusion. These symptoms lead in many cases to injuries due to falls, biting one’s tongue. Detecting a possible seizure beforehand is not an easy task. Most of the seizures occur unexpectedly, and finding ways to detect a possible seizure before it happens has been a challenging task for many researchers. Analyzing EEG signals can help us obtain information that can be used to diagnose normal brain activity or epilepsy. CNN has been demonstrated high performance on detection and classification epileptic seizure. This research uses CNN to classify the epilepsy EEG signal dataset. AlexNet and LeNet-5 are applied in CNN architecture. The result of this research is that the AlexNet architecture provides better precision, recall, and f1- score values on the epilepsy signal EEG data than the LeNet-5 architecture.
Optimization of Deep Neural Networks with Particle Swarm Optimization Algorithm for Liver Disease Classification Sidqi, Muhammad Nejatullah; Rini, Dian Palupi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 12 No. 1 (2023)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Liver disease has affected more than one million new patients in the world. which is where the liver organ has an important role function for the body's metabolism in channeling several vital functions. Liver disease has symptoms including jaundice, abdominal pain, fatigue, nausea, vomiting, back pain, abdominal swelling, weight loss, enlarged spleen and gallbladder and has abnormalities that are very difficult to detect because the liver works as usual even though some liver functions have been damaged. Diagnosis of liver disease through Deep Neural Network classification, optimizing the weight value of neural networks with the Particle Swarm Optimization algorithm. The results of optimizing the PSO weight value get the best accuracy of 92.97% of the Hepatitis dataset, 79.21%, Hepatitis 91.89%, and Hepatocellular 92.97% which is greater than just using a Deep Neural Network.
Co-Authors Abidin Pasaribu, Abidin Adhitya, Bimo Brata Apit Fathurohman Aprilisa, Shinta Dian Palupi Rini Hamzah Hasyim Hendro Cahyono Jayanti Kistiono M. Nejatullah Sidqi Meryansumayeka Meryansumayeka Muhammad Yusup Mulyadi Eko Purnomo Nur Alam Fajar Nusantara, Duano Sapta Pratiwi, Riszky Pabela Ratu Ilma Indra Putri Sari, Tri Kurnia Seira, Erazando Alfa Sepriliani, Sisca Puspita Sistyawati, Risda Intan Tanjung, Ayu Luviyanti Vincen Yazid, Rizq Khairi Zahra Alwi, Zahra Zulkardi