Garuda - Garba Rujukan Digital

Pelatihan dan Penerapan Sistem Single Sign-On untuk Meningkatkan Efisiensi dan Keamanan Layanan Digital Baliyoni Saguna Udayana, I Putu Agus Eka Darma; Meinarni, Ni Putu Suci; Febyanti, Putu Ayu; Arta, I Putu Utama; Kerlania, I Gusti Ayu Agung Randhika
Jurnal KOMET Vol 2 No 2 (2025): Jurnal Komet: Kolaborasi Masyarakat Berbasis Teknologi : Volume 2 Nomor 2, Oktobe
Publisher : Yayasan Sinergi Widya Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70103/komet.v2i2.73

Mitra Baliyoni Saguna merupakan perusahaan yang mengelola berbagai layanan digital internal untuk mendukung aktivitas operasionalnya. Seiring bertambahnya jumlah aplikasi, perusahaan mengalami kesulitan dalam pengelolaan akses pengguna yang menyebabkan pengguna harus mengingat banyak akun dan kata sandi berbeda untuk tiap sistem. Kondisi ini tidak hanya menurunkan efisiensi kerja, tetapi juga meningkatkan risiko keamanan informasi karena kredensial sering disimpan secara tidak aman atau digunakan secara berulang. Berdasarkan permasalahan tersebut, tim pengabdi dari Institut Bisnis dan Teknologi Indonesia (INSTIKI) melaksanakan kegiatan pelatihan dan pendampingan kepada mitra dalam penerapan sistem autentikasi terpusat berbasis Single Sign-On (SSO) menggunakan protokol OAuth 2.0. Kegiatan ini dilaksanakan secara langsung di kantor Baliyoni Saguna dan melibatkan tim IT serta staf operasional sebagai peserta pelatihan. Materi yang diberikan mencakup pengenalan konsep dasar SSO, pemahaman alur kerja OAuth 2.0, serta simulasi penggunaan sistem secara langsung melalui antarmuka pengguna dan dashboard admin. Setelah pelatihan, sistem SSO langsung diimplementasikan dan diintegrasikan dengan berbagai aplikasi internal yang digunakan mitra. Hasil kegiatan menunjukkan bahwa sistem SSO berhasil diterapkan secara fungsional dan memberikan dampak positif terhadap efisiensi akses pengguna, keamanan autentikasi, serta pengelolaan hak akses secara terpusat. Peserta pelatihan juga menunjukkan peningkatan signifikan dalam pemahaman teknis dan kemampuan operasional. Kegiatan ini menjadi solusi nyata terhadap permasalahan autentikasi dan menjadi langkah awal menuju transformasi digital yang berkelanjutan dan terstandarisasi di lingkungan kerja Baliyoni Saguna.

Comparison of ResNet CNN and Optimized Vision Transformer Model for Classification of Dried Moringa Leaf Quality Santiyuda, Kadek Gemilang; Febyanti, Putu Ayu; Wibawa, Gusti Putu Sutrisna; Welson, Samuel; Sutrisna, I Made Adi
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 8 No 1 (2025): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.213

The quality classification of dried Moringa leaves is an essential task in the agricultural and food processing industries due to its direct impact on product value and consumer acceptance. This study aims to compare the performance of a Convolutional Neural Network (CNN) based on ResNet architecture with an optimized Vision Transformer (ViT) model for automated classification of dried Moringa leaf quality. The methodology involved preprocessing and normalization of image data, followed by training and evaluation of both models under identical experimental settings. The ResNet CNN achieved an overall accuracy of 68%, showing strong performance in certain classes such as “A” (precision 0.78, recall 0.90) and “F” (precision 0.80, recall 1.00), but poor recognition of class “D.” Conversely, the optimized Vision Transformer model attained an accuracy of 60%, demonstrating robust classification for classes “C” (f1-score 0.77) and “D” (f1-score 0.79), though it struggled with class “E.” The findings indicate that while ResNet CNN yields higher overall accuracy, the Vision Transformer shows potential in handling complex visual variations with optimization. This study contributes to the development of AI-based agricultural quality assessment systems by providing comparative insights into deep learning architectures for image-based classification.

Comparison of ResNet CNN and Optimized Vision Transformer Model for Classification of Dried Moringa Leaf Quality Santiyuda, Kadek Gemilang; Febyanti, Putu Ayu; Wibawa, Gusti Putu Sutrisna; Welson, Samuel; Sutrisna, I Made Adi
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 4 (2025): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.215

The quality classification of dried Moringa leaves is an essential task in the agricultural and food processing industries due to its direct impact on product value and consumer acceptance. This study aims to compare the performance of a Convolutional Neural Network (CNN) based on ResNet architecture with an optimized Vision Transformer (ViT) model for automated classification of dried Moringa leaf quality. The methodology involved preprocessing and normalization of image data, followed by training and evaluation of both models under identical experimental settings. The ResNet CNN achieved an overall accuracy of 68%, showing strong performance in certain classes such as “A” (precision 0.78, recall 0.90) and “F” (precision 0.80, recall 1.00), but poor recognition of class “D.” Conversely, the optimized Vision Transformer model attained an accuracy of 60%, demonstrating robust classification for classes “C” (f1-score 0.77) and “D” (f1-score 0.79), though it struggled with class “E.” The findings indicate that while ResNet CNN yields higher overall accuracy, the Vision Transformer shows potential in handling complex visual variations with optimization. This study contributes to the development of AI-based agricultural quality assessment systems by providing comparative insights into deep learning architectures for image-based classification.

Classification of Moringa Leaf Quality Using Vision Transformer (ViT) Sugiartawan, Putu; Murdhani, I Dewa Ayu Sri; Febyanti, Putu Ayu; Wibawa, Gusti Putu Sutrisna
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 4 (2025): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.219

Moringa (Moringa oleifera) leaves are widely recognized for their nutritional and medicinal value, making quality assessment crucial in ensuring their market and processing standards. Traditional manual classification of leaf quality is subjective, time-consuming, and prone to inconsistency. This study aims to develop an automated classification system for Moringa leaf quality using a Vision Transformer (ViT) model, a deep learning architecture that leverages self-attention mechanisms for image understanding. The dataset consists of six leaf quality categories (A–F), representing various conditions of color, texture, and defect severity. The ViT model was trained and evaluated using labeled image datasets with standard preprocessing and augmentation techniques to improve robustness. Experimental results show an overall accuracy of 56%, with class-specific performance indicating that the model achieved the highest recall for class D (1.00) and the highest precision for class F (0.74). Despite moderate performance, the results demonstrate the potential of ViT for complex agricultural image classification tasks, highlighting its capability to capture visual patterns in small. Future improvements may include larger datasets, fine-tuning with domain-specific pretraining, and hybrid transformer–CNN architectures to enhance model generalization and accuracy.

Title

Found 4 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 4 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 4 Documents
Search