Article Per Year (5 Year)
p-Index From 2021 - 2026
2.495
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika Biogenesis: Jurnal Ilmiah Biologi JOURNAL OF APPLIED INFORMATICS AND COMPUTING JURNAL ILMIAH INFORMATIKA Journal of Computer System and Informatics (JoSYC) Journal of Information System and Technology (JOINT) Jurnal Pustaka Data : Pusat Akses Kajian Database, Analisa Teknologi, dan Arsitektur Komputer Jurnal Ilmiah Teknologi dan Komputer (JITTER) J-SIGN (Journal Of Informatics, Information System, And Artificial Intelligence) JoDENS: Journal of Digital Ecosystem for Natural Sustainability JUTEKOM - Jurnal Teknologi dan Ilmu Komputer
Purnajaya, Akhmad Rezki
Universitas Universal
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Immunology & microbiology Industrial & Manufacturing Engineering Mechanical Engineering

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Ambarella Fruit Ripeness Classification based on EfficientNet Models Saragih, Raymond Erz; Roza, Yuni; Purnajaya, Akhmad Rezki; Kaharuddin, Kaharuddin
Journal of Digital Ecosystem for Natural Sustainability Vol 2 No 2 (2022): Desember 2022
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v2i2.106

Abstract

Evaluating the fruit’s maturity level is crucial to acquiring high-quality fruit. The skin color of some fruits may be used as one of the numerous indicators to determine whether they have achieved their peak degree of ripeness. Similar to other fruits, the skin color of an Ambarella fruit indicates its maturity. However, determining the ripeness of the Ambarella fruit was assessed manually, which is time-consuming, inefficient, taxing, requires a large number of employees, and has the potential to result in discrepancies. This study aims to classify the ripeness of the Ambarella fruit using the deep learning approach, specifically using the Convolutional Neural Network (CNN). The new family of EfficientNetV2 is trained to classify the Ambarella fruit ripeness. The pre-trained models are utilized in this work, and the training was done via transfer learning through fine-tuning. EfficientNetV2B0 achieves the highest accuracy of 100% despite having a smaller size than the other EfficientNetV2 models used in this work.
Implementasi Support Vector Machine dan Radial Basis Function untuk Klasifikasi Makanan Vegetarian Menggunakan Data Image Williams; Gunawan, Fery; Limuel, Patrick; Purnajaya, Akhmad Rezki
Journal of Digital Ecosystem for Natural Sustainability Vol 3 No 1 (2023): Juli 2023
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v3i1.123

Abstract

The vegetarian diet has become increasingly popular in the 21st century due to its potential to reduce the risk of chronic and degenerative diseases. Vegetarians are individuals who do not consume animal products, either for religious or health reasons. However, it can be difficult to determine whether a particular food is vegetarian or non-vegetarian based on visual inspection alone. Therefore, this study successfully developed an SVM & RBF model in RStudio that can accurately differentiate between vegetarian and non-vegetarian foods based on image data. The model achieved an accuracy rate of 95%, specificity of 100%, sensitivity of 88.89%, and an AUC value of 94.44%. It can be concluded that the SVM & RBF model is capable of predicting data with high accuracy and effectively distinguishing between vegetarian and non-vegetarian classes.
Metode Analytic Hierarchy Process (AHP) dalam Pemilihan Penerima Beasiswa (Studi Kasus: Prodi Teknik Perangkat Lunak Universitas Universal) Gunawan, Fery; Limuel, Patrick; Tayanto, Vincent; Purnajaya, Akhmad Rezki
Journal of Digital Ecosystem for Natural Sustainability Vol 3 No 2 (2023): Desember 2023
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v3i2.191

Abstract

Specific attention in this study is given to Universitas Universal's scholarship programs, which rely on entrance exam results for selection, prompting the exploration of more efficient and objective decision-making processes. The study draws inspiration from existing research, particularly those utilizing the Analytic Hierarchy Process (AHP), but distinguishes itself by evolving criteria to include exam scores, computer literacy, motivation, and program understanding. The primary focus is on addressing selection challenges in the software engineering program for post-admission students at Universitas Universal. By employing AHP, the study aims to provide a comprehensive decision support system, offering a prospective solution for future scholarship selection challenges. From the results of the AHP program that has been researched, it has been found that the scholarship recipient candidate is the first candidate with a score of 0.518.
Mango and Banana Ripeness Detection based on Lightweight YOLOv8 Saragih, Raymond Erz; Purnajaya, Akhmad Rezki; Syafrinal, Ilwan; Pernando, Yonky; Yodi
Jurnal Buana Informatika Vol. 15 No. 2 (2024): Jurnal Buana Informatika, Volume 15, Nomor 02, Oktober 2024
Publisher : Universitas Atma Jaya Yogyakarta

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

Abstract

Fruits like bananas and mangoes are harvested after reaching a specific ripeness stage. Traditionally, farmers rely on manual inspection to determine ripeness, a process that can be tedious, time-consuming, expensive, and subjective. This work proposes an automatic bananas and mangoes ripeness detector utilizing computer vision technology. The detected bananas and mangoes fall into two classes: ripe and unripe. The state-of-the-art YOLOv8 architecture serves as the core of the detector. Three YOLOv8 variants, YOLOv8n, YOLOv8s, and YOLOv8m, were investigated for their performance. Results show that YOLOv8s achieved the highest overall performance, 0.9991 recall, and a mean Average Precision (mAP) of 0.8897. While YOLOv8m achieved the highest precision of 0.9995, YOLOv8n is the most miniature model, making it suitable for deployment on devices with limited resources.
Application of Support Vector Machine for Multi-Class Migraine Classification Purnajaya, Akhmad Rezki; Jaya, Mega
Jurnal Teknologi informasi dan Ilmu Komputer Vol. 1 No. 4 (2025): Oktober 2025
Publisher : Nolsatu Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65258/jutekom.v1.i4.29

Abstract

Migraine is a prevalent, debilitating neurological disorder where accurate subtype classification is critical. Machine learning (ML) offers a promising avenue to enhance diagnostic accuracy. This study evaluates a Support Vector Machine (SVM) model for multi-class migraine classification. Utilizing a public Kaggle dataset, data was partitioned into 75% training and 25% testing sets. An SVM with a linear kernel was implemented to classify seven migraine subtypes. Performance was evaluated using overall accuracy, a confusion matrix, and detailed per-class metrics: Precision, Recall, and F1-Score. The model achieved 82.65% overall accuracy and a weighted-average F1-Score of 0.824. However, detailed metrics revealed significant variance. The model achieved perfect F1-Scores (1.000) for 'Migraine Without Aura' and 'Typical Aura without Migraine' but struggled with class confusion. 'Typical Aura With Migraine' exhibited a low Recall (0.533), and 'Basilar-Type Aura' had a poor F1-Score (0.400). Critically, the model completely failed to classify 'Sporadic Hemiplegic Migraine' (0.000 F1-Score), a failure masked by the high overall accuracy. These results suggest the linear SVM is a viable baseline, but its reliability varies drastically across subtypes. The granular F1-Score and Recall metrics are essential, exposing classification failures hidden by overall accuracy. Future work must address class imbalance and symptomatic overlap, likely via non-linear models, before this approach is clinically viable.
Co-Authors ., Very Alvaro, Charlos Charles Charles Darmawan, Justin Eva Tesvara Fatma Indriani Fery Gunawan Fuad Dwi Hanggara Gunawan, Fery Ilwan Syafrinal Jaden Gil Salim Jaya, Mega Joni Irwansyah Kaharuddin Limuel, Patrick Medria Kusuma Dewi Hardhienata Milson Nestelrody Muhammad Reza Faisal, Muhammad Reza Noverio, Oscar Pangestu, Amora Antonio Patrick Limuel Pernando, Yonky Raymond Erz Saragih Rika Jelita Roza, Yuni Saragih, Raymond Erz Steffany Tayanto, Vincent Vincent Tayanto Vinxencius Lieputra Williams Williams Wisnu Ananta Kusuma Yamin, Valerian Yodi Yuni Roza