Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JURNAL REKAYASA INFORMASI SWADHARMA (JRIS) Intechno Journal : Information Technology Journal
Ruli Susanti
Universitas Majalengka
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
EVOLUSI PENDEKATAN DEEP LEARNING BERBASIS ATTENTION MECHANISM PADA PENINGKATAN RESOLUSI CITRA: TINJAUAN KOMPREHENSIF Dezein Hibatullah; Ruli Susanti
JRIS : Jurnal Rekayasa Informasi Swadharma Vol 6, No 2 (2026): JURNAL JRIS EDISI JULI 2026
Publisher : Institut Teknologi dan Bisnis (ITB) Swadharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56486/jris.vol6no2.1342

Abstract

This study presents a Systematic Literature Review (SLR) on the development of attention-based deep learning methods for Single Image Super-Resolution (SISR) for the period 2022–2026. Using the PRISMA 2020 framework, 53 articles were selected from 1,116 identified articles from Scopus, IEEE Xplore, ScienceDirect, and SpringerLink. The study results show that hybrid CNN-Transformer architectures with attention mechanisms dominate the current trend, with channel attention being the most widely used (71.7%). Application domains include medical imaging, remote sensing, surveillance, multimedia, and industry. Key challenges identified include model complexity, limited generalization, and the trade-off between reconstruction quality and inference efficiency. This study provides a comprehensive roadmap for developing more adaptive and efficient attention-based SISR systems.Penelitian ini menyajikan Systematic Literature Review (SLR) terhadap perkembangan metode deep learning berbasis attention mechanism untuk Single Image Super-Resolution (SISR) pada periode 2022–2026. Menggunakan kerangka PRISMA 2020, sebanyak 53 artikel dipilih dari 1.116 artikel teridentifikasi dari Scopus, IEEE Xplore, ScienceDirect, dan SpringerLink. Hasil kajian menunjukkan bahwa arsitektur hibrida CNN-Transformer dengan attention mechanism mendominasi tren terkini, dengan channel attention sebagai jenis yang paling banyak digunakan (71,7%). Domain aplikasi mencakup pencitraan medis, pengindraan jauh, surveillance, multimedia, dan industri. Tantangan utama yang teridentifikasi meliputi kompleksitas model, keterbatasan generalisasi, dan trade-off antara kualitas rekonstruksi dan efisiensi inferensi. Penelitian ini memberikan peta jalan komprehensif bagi pengembangan sistem SISR berbasis attention yang lebih adaptif dan efisien.
A Hybrid Rule-Based and Multinomial Naïve Bayes System for Sentiment and Intent Classification of Indonesian Public Reports with Sarcasm Detection Suhendri Suhendri; Sahal Ubaidillah Gunardo; Kartika Dwi Mulyana; Ruli Susanti; Dika Alfaizal Akbar; Amelia Putri
Intechno Journal : Information Technology Journal Vol. 8 No. 1 (2026): July
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/intechnojournal.2026v8i1.2765

Abstract

Public service reporting systems in Indonesia face significant challenges in processing large volumes of unstructured citizen feedback efficiently. This study proposes Aspiralytica, a mobile-based citizen report classification system that integrates TF-IDF feature extraction with a Multinomial Naive Bayes (MNB) classifier within a hybrid rule-based and machine learning architecture. The system simultaneously performs three-class sentiment classification (positive, negative, neutral) and five-class intent classification (complaint, appreciation, request, emergency, suggestion), with automated priority level determination and a rule-based sarcasm detection module achieving F1 of 0.8980. Evaluated on an augmented dataset of 1,137 sentiment-labeled and 2,187 intent-labeled Indonesian-language citizen report texts using Stratified 10-Fold Cross-Validation, the proposed MNB model achieved sentiment classification accuracy of 96.59% (F1: 96.59%) and intent classification accuracy of 96.97% (F1: 96.96%). An ablation study confirmed TF-IDF with MNB as the dominant performance driver, and a computational efficiency benchmark empirically justified MNB selection with mean inference latency of 0.3955 ms and throughput of 52,312 requests per second. The system is deployed as a FastAPI backend integrated with a React Native mobile frontend, delivering real-time classification through a citizen-facing interface.
Co-Authors Amelia Putri Dezein Hibatullah Dika Alfaizal Akbar Kartika Dwi Mulyana Sahal Ubaidillah Gunardo Suhendri Suhendri