cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jumanto
Contact Email
jumanto@mail.unnes.ac.id
Phone
+628164243462
Journal Mail Official
sji@mail.unnes.ac.id
Editorial Address
Ruang 114 Gedung D2 Lamtai 1, Jurusan Ilmu Komputer Universitas Negeri Semarang, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
Published by Universitas Negeri Semarang
ISSN : 24077658     EISSN : 24600040     DOI : https://doi.org/10.15294/sji.vxxix.xxxx
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering
Scientific Journal of Informatics (p-ISSN 2407-7658 | e-ISSN 2460-0040) published by the Department of Computer Science, Universitas Negeri Semarang, a scientific journal of Information Systems and Information Technology which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. The SJI publishes 4 issues in a calendar year (February, May, August, November).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 142 Documents
 11   12   13   14   15 
Ultra-Low-Cost Hybrid OCR–LLM Architecture for Production Grade E-KTP Extraction Saputro, Anjar Tiyo; Herlambang, Bambang Agus; Novita, Mega
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.38200

Abstract

Purpose: The purpose of this study is to be able to avoid limitations of inexpensive ID card data extraction services and preserve privacy, which can simultaneously achieve reliable operation even under an environment with minimum infrastructure, in particular if no dependency on GPU-based servers are required. Method: The proposed approach is a microservice pipeline with three stages: (1) local lightweight pre-processing on devices, (2) Tesseract CPU-based OCR. js, (3) fast text tokenization through a small premature external LLM. The system is developed as TypeScript backend utilizing the Hono framework with all image processing taking place locally in order to keeping user data private. Result: The result of the experimental evaluations with real ID card samples is that the system can run stably in low-performance VPS (1 vCPU, 1 GB RAM) with operation cost approximately IDR 2.5047 per extraction process and its accuracy level is acceptable for use in a production environment. Moreover, the results indicate that system latency is dominated by LLM inference at the cloud. Novelty: The main contribution and novelty of this study is that we demonstrate, for the first time, a cost-effective (privacy-preserving) OCR-LLM hybrid pipeline without demanding expensive GPU models at large scale which makes our system suitable under limited storage and resource constraints on-premises or edge environments in small organizations including micro-SaaS services.
Optimized LSTM Model Using Simulated Annealing for Autoignition Temperature (AIT) Prediction as a Hazard Indicator Zahra, Nurul Izzah Abdussalam
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.38278

Abstract

Autoignition temperature (AIT) is the minimum temperature at which a substance sparks spontaneously in air under normal atmospheric pressure without an external ignition source, such as a flame. This parameter is crucial for industrial safety, particularly in the production, processing, handling, transportation, and storage of flammable materials. However, conventional AIT measurement methods are time-consuming, expensive, and carry significant risk. As an alternative, in silico approaches based on machine learning can be used to develop AIT prediction models. Among these approaches, Long Short-Term Memory (LSTM) networks are particularly effective for modeling complex non-linear relationships. However, the performance of LSTM models is highly sensitive to the configuration of numerous hyperparameters, making manual tuning inefficient. Consequently, an automated optimization strategy is required to identify the optimal model architecture. This study aims to develop an AIT prediction model as a hazard indicator using the Long Short-Term Memory (LSTM) method optimized with Simulated Annealing (SA). Experimental results demonstrated that the proposed SA-LSTM Model with a cooling schedule of ΔT = 0.7 outperformed the unoptimized baseline architecture. The optimization process improved the R2 on the data test from 0.5682 to 0.5939 and reduced the RMSE from 74.35 K to 72.10 K. Furthermore, the MAPE decreased from 9.29% to 8.87%. These findings confirm that the SA optimized LSTM model provides a more reliable and robust hazard indicator.

Page 15 of 15 | Total Record : 142

 11   12   13   14   15 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 12 No. 4: November 2025 Vol. 12 No. 3: August 2025 Vol. 12 No. 2: May 2025 Vol. 12 No. 1: February 2025 Vol. 11 No. 4: November 2024 Vol. 11 No. 3: August 2024 Vol. 11 No. 2: May 2024