cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Andi Baso Kaswar
Contact Email
a.baso.kaswar@gmail.com
Phone
+6285656227888
Journal Mail Official
fakhri@diginus.id
Editorial Address
Antang, Makassar, South Sulawesi, Indonesia
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Journal of Deep Learning, Computer Vision and Digital Image Processing
Published by Sakura Digital Nusantara
ISSN : 29868920     EISSN : 29868939     DOI : https://doi.org/10.61255/decoding
Core Subject : Science,
Computer Science & IT
The Journal of Deep Learning, Computer Vision and Digital Image Processing (DECODING), covers all topics of artificial intelligence and soft computing and their applications, including but not limited to: • Neural networks • Reasoning and evolution • Intelligent search • Intelligent planning • Intelligence applications • Computer vision and speech understanding • Multimedia and cognitive informatics • Data mining and machine learning tools, heuristic and AI planning strategies and tools, computational theories of learning • Technology and computing (like particle swarm optimization); intelligent system architectures • Knowledge representation • Bioinformatics • Natural language processing • Automated reasoning • Logic programming • Machine learning • Visual/linguistic perception • Evolutionary and swarm algorithms • Derivative-free optimisation algorithms • Fuzzy sets and logic • Rough sets • Simulated biological evolution algorithms (like genetic algorithm, ant colony optimization, etc) • Multi-agent systems • Data and web mining • Emotional intelligence • Hybridisation of intelligent models/algorithms • Parallel and distributed realisation ofintelligent algorithms/systems • Application in pattern recognition, image understanding, control, robotics and bioinformatics • Application in system design, system identification, prediction, scheduling and game playing • Application in VLSI algorithms and mobile communication/computing systems
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 63 Documents
 3   4   5   6   7 
Comparative Analysis of XGBoost and CatBoost for Detecting AI-Generated Synthetic Faces Using Texture and Color Features indra firmansyah; Defry Hamdhana; Wahyu Fuadi
Journal of Deep Learning, Computer Vision, and Digital Image Processing Volume 4 Issue 3 September 2026
Publisher : CV. Sakura Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61255/decoding.v4i3.1677

Abstract

Purpose – The rapid advancement of Generative AI produces near-perfect synthetic face images, posing fraud risks. This study compares XGBoost and CatBoost for detecting real versus synthetic faces using texture and color features.Methods – Texture features were extracted using GLCM with four orientations (0°, 45°, 90°, 135°), generating 16 features, while YCbCr mean and standard deviation provided 6 color features (22 total). A balanced 750-image dataset (real and AI from GPT Image 2, Nano Banana, Leonardo AI, Canva, Dreamina AI) was split 80:20 and normalized with StandardScaler.Findings – On an asymmetric, source-shifted test split, where real test images were captured independently while synthetic test images came from the same generators as training, CatBoost outperformed XGBoost, achieving 84.67% accuracy (vs. 80.67%), 83.33% precision (vs. 78.05%), 86.67% recall (vs. 85.33%), and 84.97% F1-score (vs. 81.53%), reducing False Positives by 27.78% and False Negatives by 9.09%. However, repeated 5-fold stratified cross-validation (5×10 repeats) revealed only marginal, non-significant differences (0.05-0.87 percentage points, p > 0.09). Research implications – Although the moderate dataset excludes recent architectures such as StyleGAN, findings affirm the feasibility of efficient, interpretable detection through feature engineering. Since within-domain cross-validation shows no significant algorithmic difference, the observed cross-domain gap should be regarded as preliminary, pending validation through repeated cross-domain evaluations across diverse AI platforms.Originality – The novelty lies in comparing XGBoost and CatBoost on multi-orientation GLCM and YCbCr feature fusion for contemporary AI-generated images, identifying cr_std and contrast_0 as stable, interpretable discriminative markers.
Digital Forensic Investigation of Linux SSH Authentication Logs Using NIST SP 800-86 with GeoIP and ASN Enrichment Danur Wijayanto; Ahmad Widad Saksana
Journal of Deep Learning, Computer Vision, and Digital Image Processing Volume 4 Issue 3 September 2026
Publisher : CV. Sakura Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61255/decoding.v4i3.1758

Abstract

Purpose – This study applies the National Institute of Standards and Technology Special Publication (NIST SP 800-86) framework to investigate SSH authentication logs from the Lensa UNISA Server while preserving evidence integrity and enriching forensic findings using GeoIP and Autonomous System Number (ASN) information.Methods – The investigation followed the Collection, Examination, Analysis, and Reporting phases of NIST SP 800-86. The auth.log.1 file was acquired using Secure Copy Protocol (SCP), verified through SHA-256 hashing, and analyzed using standard Linux utilities. GeoIP and ASN information was obtained using MaxMind GeoLite2 and RDAP.Findings – SHA-256 verification confirmed identical hashes between the original evidence and working copy. The analysis identified 96,182 OpenSSH-related events, including 15,522 failed authentication attempts, 4,604 invalid-user messages, and eight successful sessions. Systematic username enumeration targeting institutional account names was observed. GeoIP and ASN enrichment showed that substantial authentication activity originated from source IP addresses in the Netherlands and Turkey, particularly AS43350, AS48090, and AS154383, consistent with activity associated with hosting infrastructure.Research Implications – The findings demonstrate the practical applicability of NIST SP 800-86 for SSH log investigation using standard Linux tools. GeoIP and ASN enrichment provide additional context for interpreting authentication artifacts.Originality – This study presents an operational forensic case study integrating NIST SP 800-86, Linux-based log analysis, and GeoIP–ASN enrichment
A Single-Node Performance Evaluation of Hash-Chain and Dependency-Graph Scheduling for Simulated Smart-Contract Workloads in Organic Certification Yuni Dwi Anggraeni; Arum Prasetyajati; Akhmad Unggul Priantoro
Journal of Deep Learning, Computer Vision, and Digital Image Processing Volume 4 Issue 3 September 2026
Publisher : CV. Sakura Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61255/decoding.v4i3.1777

Abstract

Purpose – This study evaluates when dependency-aware parallel scheduling improves a single-node simulated smart-contract workload for organic certification while separating scheduling effects from hash-chain and dependency-graph record representation.Methods – A deterministic Python rule engine evaluates 18 certification tasks per submission. The same transactions were executed under four conditions: hash-chain sequential (HS), hash-chain dependency-aware parallel (HP), dependency-graph sequential (DS), and dependency-graph dependency-aware parallel (DP). Main experiments varied 18–900 transactions and 1–3,000 iterative SHA-256 rounds, with five warm-ups and 30 paired technical repetitions. Worker, graph-shape, conflict, functional, integrity, and focused reconciliation tests were also performed.Findings – Representation-only ratios remained close to unity, whereas scheduling produced the dominant performance effect. At 3,000 rounds, HP/HS and DP/DS speedups were 1.680× and 1.620× at 450 transactions and 1.564× and 1.554× at 900 transactions. The focused reconciliation run showed that eight workers minimized makespan for both 180 and 900 transactions, although per-worker efficiency declined as worker count increased. All 12 functional and integrity tests passed.Research Implications – Dependency information is useful primarily as a scheduling mechanism; the observed speedup should not be interpreted as evidence that a distributed DAG ledger is intrinsically faster than a hash chain.Originality – The study provides a carefully documented 2 × 2 single-node benchmark that isolates record representation from execution policy for a simulated certification smart-contract workload.

Page 7 of 7 | Total Record : 63

 3   4   5   6   7 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Volume 4 Issue 3 September 2026 Volume 4 Issue 2 June 2026 Volume 4 Issue 1 March 2026 Volume 3 Issue 2 September 2025 Volume 3 Issue 1 Maret 2025 Volume 2 Issue 2 September 2024 Volume 2 Issue 1 Maret 2024 Volume 1 Issue 2 September 2023 Volume 1 Issue 1 Maret 2023