Article Per Year (5 Year)
p-Index From 2021 - 2026
2.169
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika Jurnal Media Infotama CogITo Smart Journal Jurnal Teknik Informatika dan Elektro (JURTIE) Abdimas : Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Kepada Masyarakat Sisthana Literacy : International Scientific Journals of Social, Education, Humanities Riau Jurnal Teknik Informatika Jurnal Teknik Informatika dan Teknologi Informasi Jurnal Pendidikan dan Sastra Inggris
Salaki, Reynaldo Joshua
Universitas Sam Ratulangi
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Environmental Science Health Professions Library & Information Science Materials Science & Nanotechnology Medicine & Pharmacology Nursing Public Health Social Sciences

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
DIGNITY AS SEEN IN TENNESSEE WILLIAMS’ A STREETCAR NAMED DESIRE Tini Mogea; Salaki Reynaldo Joshua
Jurnal Pendidikan dan Sastra Inggris Vol. 2 No. 3 (2022): Desember: Jurnal Pendidikan dan Sastra Inggris
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jupensi.v2i3.749

Abstract

This research is carried out to trace dignity in A Streetcar Named Desire. The dignity is focused on Blanche as a Southern woman, who has a different characterization from her sister Stella. This research is qualitative research since the data are in the form of words and quotations. The data are collected from the drama itself, A Streetcar Named Desire, and other books or references to support the analysis. In analyzing the data, the writer used a mimetic approach. The approach views literature as the imitation and combination of the reality and imagination of the playwright or the result of his imagination that comes from reality. The result shows the existence of the dignity of Blanche as a Southern Woman who lives on wealth and has a plantation in Belle Reve. Blanche’s region and its society have unique values in their social status. It is gentility that includes the manner of treating the caller. Blanche shows that her dignity comes from her cultural and social background as a Southern woman. Blanche serves to symbolize what she felt about the Southern aristocracy as she tries to escape poverty and her reputation although her ancestry is dead. Blanche's struggle with dignity and fantasy serves as one of the main causes of her character’s downfall. Although she puts on a veneer of social snobbery and has a manner that is dainty and frail, in reality, Blanche lies because she refuses to accept the hand fate has dealt her. In the Old South, women depended on men for comfort and status. She is taken away from her dignity. She also desperately clings to and is dragged into a new world of reality and a New South.
Komparasi Supervised dan Self-Supervised Learning untuk Klasifikasi Sel Darah pada Skenario Keterbatasan Data Berlabel Misella Mambu; Oktavian Abraham Lantang; Salaki Reynaldo Joshua
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4555

Abstract

The development of blood cell image classification models is often hindered by the scarcity of labeled data. This study evaluates the effectiveness of supervised baseline models, supervised fine-tuning, and self-supervised learning (SSL) based on SimCLR and BYOL using the ResNet-50 and DenseNet-121 architectures. Data-limited simulation was performed using 10% labeled data for the classification stage and 90% unlabeled data for SSL pre-training on 17,092 images from 8 morphological classes. The results show that SSL achieves competitive performance, with the highest accuracy on ResNet-50 at 95.31% (SimCLR) and 94.27% (BYOL), and on DenseNet-121 at 93.75% (SimCLR) and 89.58% (BYOL). The SSL approach also demonstrated robustness against overfitting, good robustness against class imbalance, and Grad-CAM visualizations that align with medical expert assessments on ResNet-50. In conclusion, SSL effectively optimizes unlabeled data to improve the performance of classification models in scenarios with limited data annotation.
Peningkatan Akurasi Deteksi Penyakit Daun Padi Menggunakan Augmentasi Data Berbasis Generative Adversarial Networks (GAN) Nasya Sunia Tubuon; Nancy Jeane Tuturoong; Salaki Reynaldo Joshua
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4585

Abstract

Rice is a staple food crop for more than half of the global population, with Asia contributing approximately 90% of global production. Leaf diseases, particularly Blast and Bacterial Blight, are major factors contributing to reduced rice productivity in Indonesia. Conventional detection methods based on visual observation are often subjective and time-consuming, highlighting the need for more reliable automated detection systems. This study aims to implement StyleGAN2-ADA to generate synthetic rice leaf disease images and evaluate its impact on the performance of Convolutional Neural Network-based classification. This research employed a quantitative experimental approach by comparing two scenarios: Baseline without GAN augmentation and Proposed with StyleGAN2-ADA synthetic image augmentation. Two CNN architectures, EfficientNetB0 and ResNet50, were evaluated using accuracy, precision, recall, F1-Score, and confusion matrix metrics. The quality of synthetic images was assessed using the Fréchet Inception Distance. The results demonstrated that StyleGAN2-ADA augmentation improved the overall F1-Score of EfficientNetB0 from 97.62% to 98.20%, with the largest improvement observed in the Blight class, increasing by 3.11%. For ResNet50, the overall F1-Score increased from 97.60% to 98.20%, although the Blast class showed no performance improvement after augmentation. GAN augmentation provided the most consistent benefits for the minority Blight class, while its impact on the Blast class varied across metrics. In EfficientNetB0, improvements in precision and F1-Score were accompanied by a decrease in recall. These findings indicate that model evaluation should consider class-specific performance and the trade-off between precision and recall rather than relying solely on aggregate metrics
Pengembangan dan Pengujian Performa Progressive Web App pada Sistem Reservasi Ruangan Fakultas Teknik Universitas Sam Ratulangi Veronica Waeo; Alwin Melkie Sambul; Salaki Reynaldo Joshua
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4680

Abstract

The manual room reservation process at the Faculty of Engineering, Sam Ratulangi University leads to uncertain application status, scheduling conflicts, and limited transparency. Existing reservation practices also lack offline accessibility and installable web capabilities. This study aims to develop and evaluate a Progressive Web App (PWA)-based room reservation system to improve accessibility while maintaining performance. The system was developed using the Rapid Application Development method and evaluated through automated black box testing with Selenium and performance testing using Google Lighthouse. Performance measurements were conducted on four representative pages using Google Chrome and Lighthouse under online and offline scenarios, with each test repeated three times on the same desktop environment. The PWA achieved average performance scores of 100 for cache-offline and cache-online scenarios, 98.5 for no-cache offline, and 96 for no-cache online. The non-PWA version achieved average scores of 99.75 and 96.25 under online conditions but could not function offline. These results demonstrate that the proposed PWA provides installation capability and limited offline access while maintaining online performance comparable to a conventional web application, making it a practical solution for room reservation services in higher education.
Komparasi Metode K-Means dan Hierarchical Clustering untuk Pengelompokan Pola Bermain Pemain Mobile Legends Savior Podung; Reynaldo Joshua Salaki
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4692

Abstract

The rapid growth of Mobile Legends: Bang Bang esports produces large volumes of gameplay statistics that remain underutilized beyond individual match summaries. This study compares K-Means and Hierarchical Clustering to group player playstyles using five gameplay variables (kill, death, assist, gold, and match duration) from 990 valid records in the MPL Cambodia Season 6 - BoxMatch dataset, following CRISP-DM preprocessing and Min-Max normalization. The Elbow Method identified K=3 as the optimal number of clusters. K-Means produced three interpretable groups - Carry/Damage Dealer, Late Game Fighter, and Sacrificial/Tank - with a Silhouette Score of 0.252 and a balanced distribution (42.6%, 18.5%, 38.9%), outperforming Hierarchical Clustering with Ward linkage (Silhouette Score 0.2203, less balanced distribution). The results were deployed into an interactive Flask-based web application for dataset upload, clustering visualization, and method comparison, which was validated through black box testing. This research demonstrates that combining clustering with web-based visualization can effectively reveal player playstyle patterns from competitive Mobile Legends gameplay statistics.
Sistem Pendukung Keputusan Menggunakan Fuzzy Logic Tahani Untuk Penentuan Golongan Obat Sesuai Dengan Penyakit Diabetes Charolina Debora Mait; Josua Armando Watuseke; Prince David Gibrael Saerang; Salaki Reynaldo Joshua
Jurnal Media Infotama Vol 18 No 2 (2022): Oktober
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v18i2.2936

Abstract

Abstract: Consuming foods and drinks that contain a lot of Glucose, allows the risk of developing Diabetes. Diabetes is a disorder of the metabolic system of carbohydrates, proteins, and fats in the body due to disturbances that occur in insulin secretion that cause a decrease in insulin performance. Please be aware that Diabetes can lead to death, blindness, heart disease and kidney failure. According to data from the International Diabetes Federation in 2019, Indonesia is ranked 7th, where 10.7% of the total population suffers from Diabetes. For this reason, we are interested in making fuzzy logic on determining drug classes in diabetes based on the patient's blood glucose levels. The purpose of this study is to prove that fuzzy logic can be a solution for classifying drugs in diabetic patients. We'll create a fuzzy Logic that uses The Hard Way graphic model on each variable membership function. For the fuzzy manufacturing process toolbox we used a Jupyter Notebook on anaconda Navigator.The limitation of the study is the use of doses on drugs. This research can contribute to the field of health. Keywords: Fuzzy Logic, Artificial Intelligence, Diabetes, Jupyter Notebook, Tahani Method.
Co-Authors Alfrina Mewengkang Alwin Melkie Sambul Charolina Debora Mait Daniel Febrian Sengkey Heilbert Armando Mapaly Henry Valentino Florensius Kainde Josua Armando Watuseke Kainde, Henry Valentino Kainde, Henry Valentino Florensius Kambey, Feisy Diane Mapaly, Heilbert Armando Marssel Michael Sengkey Misella Mambu Nancy Jeane Tuturoong Nasya Sunia Tubuon Oktavian Abraham Lantang Prince David Gibrael Saerang Rampo, Vania Yori salvius paulus lengkong Salvius Paulus Lengkong Savior Podung Siwu, Britney Hanna Maria Tini Mogea Veronica Waeo Yuri Vanli Akay