cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Tri A. Sundara
Contact Email
tri.sundara@stmikindonesia.ac.id
Phone
+628116606456
Journal Mail Official
ijcs@stmikindonesia.ac.id
Editorial Address
Jalan Khatib Sulaiman Dalam 1, Padang, Indonesia
Location
Kota padang,
Sumatera barat
INDONESIA
The Indonesian Journal of Computer Science
Published by STMIK Indonesia Padang
ISSN : 25497286     EISSN : 25497286     DOI : https://doi.org/10.33022
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering Engineering
The Indonesian Journal of Computer Science (IJCS) is a bimonthly peer-reviewed journal published by AI Society and STMIK Indonesia. IJCS editions will be published at the end of February, April, June, August, October and December. The scope of IJCS includes general computer science, information system, information technology, artificial intelligence, big data, industrial revolution 4.0, and general engineering. The articles will be published in English and Bahasa Indonesia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,204 Documents
 117   118   119   120   121 
Frozen External Validation of a Calibrated, Uncertainty-Aware Swin Transformer for Thyroid Nodule Malignancy Classification on Ultrasound: Frozen external validation of thyroid ultrasound AI Akam Aziz; Umran Abdullah Haje; Kamaran H. Manguri
The Indonesian Journal of Computer Science Vol. 15 No. 4 (2026): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v15i4.5218

Abstract

Deep learning for thyroid ultrasound is usually reported through internal discrimination, yet independent validation shows that performance can deteriorate across institutions and scanner environments, and studies seldom evaluate calibration, transferred operating thresholds, uncertainty behaviour and referral utility together under a protocol frozen before external data are opened. This study aimed to quantify the internal-to-external change in discrimination, classification and calibration when a model, its temperature, thresholds and preprocessing are frozen before external evaluation. Methods. A public 3,115-image Kaggle archive underwent duplicate and label-conflict review, yielding 3,079 images in fixed Train (2,155), Validation (462) and internal Test (462) sets. Four baseline architectures and nine Swin-Tiny candidates were compared using Validation data only. The selected configuration used focal loss, Gaussian training noise (0.03), temperature scaling and 20-pass Monte Carlo (MC) Dropout. It was evaluated once internally, then on all 5,000 TN5000 images and the official 1,000-image Test subset without fine-tuning, recalibration or threshold reselection. Results. Internal Test AUROC was 0.879 (95% CI 0.848–0.909); sensitivity 0.827 and specificity 0.753 at threshold 0.50. Full external AUROC was 0.828 (95% CI 0.817–0.841), sensitivity 0.910 and specificity 0.529, producing 672 false positives among 1,426 benign images. The official Test subset yielded AUROC 0.825 and sensitivity 0.915. Exact deduplication had negligible effect (AUROC 0.827). At 70% coverage, referring the most uncertain cases raised accuracy to 0.857 and sensitivity to 0.951. Conclusion. Discrimination transferred but specificity did not, demonstrating that internal accuracy alone is insufficient to characterise transportability. The frozen, leakage-audited framework supports only human-supervised triage.
Performance Analysis of a Hybrid PLC–VLC Communication System with Coded OFDM and Realistic Indoor Optical Propagation Ei Mon Zaw; Zin Mar Lwin; Tin Tin Hla
The Indonesian Journal of Computer Science Vol. 15 No. 4 (2026): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v15i4.5220

Abstract

The paper presents a hybrid Power Line Communication–Visible Light Communication (PLC–VLC) system for indoor broadband connectivity using convolutionally coded 16-QAM OFDM in the PLC backbone and DCO-OFDM in the VLC downlink. The system is modeled in MATLAB, incorporating frequency-selective PLC channel characteristics and indoor optical propagation with both line-of-sight (LOS) and non-line-of-sight (NLOS) components. A 6 m × 6 m × 3 m room with four ceiling-mounted LED arrays is evaluated in terms of received optical power, RMS delay spread, illuminance, and achievable data rate. Simulation result are indicated a maximum received optical power of 658.52 μW, an RMS delay spread of 3.03 ns, and a maximum data rate of 75.7 Mbps. These results are demonstrated that the proposed PLC–VLC architecture can provide reliable, energy-efficient, and cost-effective indoor wireless communication for smart building and IoT applications.
Optimization of Surface Texturing and Reflector Geometry in AlGaN-Based Deep Ultraviolet Light Emitting Diode Using Monte-Carlo Ray-tracing method Hsu Wai Phyo; Tin Tin Hla
The Indonesian Journal of Computer Science Vol. 15 No. 4 (2026): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v15i4.5221

Abstract

The research presents on optimizing the light extraction efficiency of Deep Ultraviolet Light Emitting Diodes (DUV LEDs) remains a critical challenge due to severe optical losses. AlGaN DUV LEDs are essential for sterilization and biomedical applications; however, their efficiency is severely limited by high reflection, absorption, and scattering losses. Light Extraction Efficiency (LEE) and External Quantum Efficiency (EQE) are targeted for improvement by optimizing the LED package structure. Using Monte-Carlo ray-tracing method, the simulation models photon paths including reflections, refractions, and absorptions while considering spectral refractive indices and surface roughness. Light-trapping mechanisms caused by Total Internal Reflection (TIR) are identified, and the impacts of various reflectors, such as Metallic, Distributed Bragg (DBR), and Omni-Directional Reflectors (ODR), are evaluated in this investigation. A framework for optimizing layer thickness and surface textures to achieve a directional radiation pattern and higher output power is established through these findings, supporting commercial DUV LED applications.
Analysis of Efficiency Optimization for InGaN-based Blue Light-Emitting Diode Phyu Sin Zaw; Tin Tin Hla
The Indonesian Journal of Computer Science Vol. 15 No. 4 (2026): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v15i4.5222

Abstract

Efficiency optimization of an InGaN-based blue light-emitting diode (LED) is performed by analyzing the electron blocking layer (EBL), current spreading layer (CSL), and multiple quantum well (MQW) active region. Analytical calculations and MATLAB simulations are used to evaluate the device performance. Three InGaN/GaN quantum wells are selected for the active region, and an internal quantum efficiency (IQE) of 76% is obtained. The optimized EBL provides an efficiency of 96.57%, while the optimized CSL achieves 99.9962%. The overall LED efficiency is calculated from the efficiencies of the MQW, EBL, and CSL, giving an optimized value of approximately 73.39%. Based on the calculated results, the optimized EBL effectively suppresses electron leakage and improves carrier confinement. The optimized CSL also enhances current spreading, leading to better radiative recombination in the MQW region. The obtained results confirm that the proposed structural optimization improves the efficiency and performance of InGaN-based blue LEDs for solid-state lighting, display technology, and optical communication applications.

Page 121 of 121 | Total Record : 1204

 117   118   119   120   121 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 4 (2026): The Indonesian Journal of Computer Science Vol. 15 No. 3 (2026): The Indonesian Journal of Computer Science Vol. 15 No. 2 (2026): The Indonesian Journal of Computer Science Vol. 15 No. 1 (2026): The Indonesian Journal of Computer Science Vol. 14 No. 6 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 5 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 4 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 3 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science Vol. 13 No. 6 (2024): The Indonesian Journal of Computer Science Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science Vol. 13 No. 3 (2024): The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): The Indonesian Journal of Computer Science Vol. 13 No. 1 (2024): The Indonesian Journal of Computer Science Vol. 12 No. 6 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 5 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 3 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 2 (2023): The Indonesian Journal of Computer Science Vol. 12 No. 1 (2023): The Indonesian Journal of Computer Science Vol. 11 No. 3 (2022): The Indonesian Journal of Computer Science Vol. 11 No. 2 (2022): The Indonesian Journal of Computer Science Vol. 11 No. 1 (2022): The Indonesian Journal of Computer Science More Issue