cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Furizal
Contact Email
furizal.id@gmail.com
Phone
-
Journal Mail Official
sjer.editor@gmail.com
Editorial Address
Jl. Poros Seroja, Kesra, Kepenuhan Barat Sei Rokan Jaya, Kec. Kepenuhan, Kab. Rokan Hulu, Riau
Location
Kab. rokan hulu,
Riau
INDONESIA
Scientific Journal of Computer Science
Published by PT. Teknologi Futuristik Indonesia
ISSN : -     EISSN : 31103170     DOI : https://doi.org/10.64539/sjcs
Core Subject : Science,
Computer Science & IT
The Scientific Journal of Computer Science (SJCS) (e-ISSN: 3110-3170) is a peer-reviewed and open-access scientific journal, managed and published by PT. Teknologi Futuristik Indonesia in collaboration with Universitas Qamarul Huda Badaruddin Bagu and Peneliti Teknologi Teknik Indonesia. The SJCS dedicated to publishing high-quality research across all areas of computer science, with a particular focus on emerging technologies that are shaping the future of computing. SJCS invites original research, review papers, and studies that involve practical applications, simulations, and theoretical advancements. The journal scope includes, but is not limited to: Artificial Intelligence and Machine Learning Data Science and Big Data Cybersecurity and Cryptography Cloud Computing and Distributed Systems Software Engineering Human-Computer Interaction Computer Vision and Natural Language Processing Internet of Things (IoT) Blockchain Technologies Robotics and Automation Computational Biology and Bioinformatics All fields related to computer science SJCS aims to advance the development of innovative computing systems that contribute to technological progress across industries.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 37 Documents
 1   2   3   4 
Automated Dermatologist-Level Classification of Malignant Melanoma Using Voting Ensemble Learning System Racheal Shade Akinbo; Tosin Precious Adeyemi; Bamidele Moses Kuboye
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.416

Abstract

Skin cancer is a life-threatening dermatological disease, with malignant melanoma representing its most aggressive form. Early detection and accurate classification of skin lesions remain challenging despite advances in computer-aided diagnostic techniques. However, further comparative evaluation is still needed to determine whether a Voting Ensemble framework offers meaningful performance improvements over individual machine learning classifiers for malignant melanoma classification. This study aimed to design and evaluate an automated classification system using a Voting Ensemble framework and compare its performance with individual machine learning classifiers. The International Skin Imaging Collaboration (ISIC) dataset containing 10,000 dermoscopic images was preprocessed, and Principal Component Analysis (PCA) was applied for dimensionality reduction. Four machine learning models, namely Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Logistic Regression (LR), were evaluated alongside the proposed Voting Ensemble model. Experimental results showed that SVM achieved the highest classification accuracy (90.70%), outperforming the Voting Ensemble (89.50%), XGBoost (89.70%), RF (86.40%), and LR (81.60%). Although the proposed Voting Ensemble integrated the predictive strengths of multiple classifiers, it did not surpass the standalone SVM under the current experimental setting, indicating that SVM achieved the best classification performance under the selected dataset and experimental setting. These findings provide useful evidence for selecting appropriate machine learning models for automated melanoma screening and highlight the importance of rigorous comparative evaluation before adopting ensemble approaches in clinical decision-support systems. The results further suggest that ensemble learning does not necessarily outperform a carefully optimized standalone classifier under all experimental conditions.
D2ANN-RL: Defense-in-Depth ANN-Reinforcement Learning Framework for LLM Chatbot Code Injection Mitigation Victor Omoboye Oluwasegun; Oluwatosin Samuel Falebita; Nabeela Temitayo Adebola; Victor Aduragbemi Adekunle; Divine Chukwuemeka Uzodinma; Toluhi Michael Lanre; David Oyewumi Oyekunle; Chima-Duru Goodness Goziechukwu; Ugochukwu Okwudili Matthew
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.506

Abstract

The growing cybersecurity vulnerabilities in artificial intelligence (AI) service models, particularly Large Language Models (LLMs), highlight code injection as a critical threat to chatbot reliability and safe deployment. On the account that LLMs process inputs as undifferentiated token sequences, they cannot reliably distinguish trusted system prompts from untrusted user inputs. This architectural limitation enables attackers to exploit direct and indirect prompt injection channels, resulting in insecure code generation, altered execution flows, and potential data exfiltration or remote code execution. In mission critical environments such as cloud platforms, IoT ecosystems, and defense systems, these risks escalate into unauthorized access and operational compromise. To address this challenge, the present study introduced a D2ANN-RL framework that integrates input/output sanitization, context isolation, sandboxing, and secure prompt engineering, supported by hybridization of Artificial Neural Network (ANN)–Reinforcement Learning (RL) detection model. The ANN component ensures robust feature extraction, while RL dynamically adapts defense strategies to evolving adversarial vectors. Computational evaluation demonstrates the framework’s effectiveness, achieving 96.95% detection accuracy, precision of 96.9%, recall of 97%, and F-Score of 96.95%. The Defense Performance Index (DPI) reached 84.9%, validating model resilience, scalability, and balanced classification integrity. These findings highlight the broader implications of deploying transparent, adaptive, and generalizable safeguards for LLM based chatbot systems, advancing secure AI integration and mitigating systemic vulnerabilities in mission critical operations.
A Lightweight Stacking Ensemble Intrusion Detection Framework for Software-Defined Networking Using the InSDN Dataset Ubakaghinwa Paul Chigbu; Abdulrashid Abdulrauf; Ishaq Isa; Badamasi Usman Zuntu; Maryam Abubakar Sharif
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.511

Abstract

Software-Defined Networking (SDN) has become a key enabler of next-generation communication infrastructures because of its centralized control, programmability, and global network visibility. However, the centralized architecture also introduces significant security vulnerabilities, making SDN environments highly susceptible to attacks such as DoS, DDoS, probing, brute-force, and botnet activities. Although deep learning-based intrusion detection systems have achieved high detection accuracy, many existing approaches suffer from high computational complexity, long training time, and limited suitability for real-time deployment. This study addresses this gap by developing a lightweight stacking ensemble intrusion detection framework for SDN using the InSDN dataset. The proposed framework employs XGBoost, LightGBM, CatBoost, Random Forest, and Extra Trees as base learners, with Logistic Regression serving as the meta-learner. Experiments were conducted using 48-feature, 6-feature, and 4-feature configurations derived from previous feature-reduction studies. The results demonstrate consistently high detection performance, achieving accuracies above 99% across all feature subsets, with only marginal degradation under reduced feature dimensions. The framework showed excellent detection capability for major attack categories while maintaining reliable performance for most minority classes. These findings demonstrate that stacking ensemble learning is a practical and computationally efficient alternative to complex deep learning architectures for SDN intrusion detection, with strong potential for scalable and real-time cybersecurity deployment in modern network environments.
A Binary Firefly Optimized Stacking Ensemble Model for Customer Churn Prediction in the Telecommunications Industry Abdulrashid Abdulrauf; Maaruf Mohammed Lawal; Oluwatoyin Omoloba; Omolara Busayo Abodunrin; Minkail Mohammad
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.507

Abstract

Customer churn prediction remains a critical challenge in the telecommunications industry because subscriber attrition directly affects revenue generation, customer retention, and long-term business sustainability. Although numerous studies have employed machine learning and deep learning techniques for churn prediction, many existing approaches rely on standalone models that have limited ability to simultaneously capture complex nonlinear customer behaviour, exploit model diversity, and eliminate redundant features. Building upon our previous study, this research proposes an enhanced heterogeneous stacking ensemble framework that integrates Binary Firefly Algorithm (BFA)-based feature optimization with Deep Neural Network (DNN), Support Vector Machine (SVM), and Random Forest (RF) as base learners, while Logistic Regression serves as the meta-learner for final churn classification. To ensure a fair and controlled comparison, the same Maven Analytics Telecom Customer Churn dataset and preprocessing strategy adopted in the previous study were retained, including data cleaning, feature transformation, stratified data partitioning, and normalization. Model development further incorporated 5-fold cross-validation on the training dataset, while BFA was introduced to identify the most informative pre-churn features. Experimental results demonstrate that the proposed framework achieved strong and balanced predictive performance and demonstrated improvements in several classification metrics compared with the previously developed BFA-based Hybrid TabNet-DNN model. Furthermore, its performance was competitive with the Random Forest baseline, which exhibited comparable classification effectiveness. These findings show that optimized feature selection and heterogeneous ensemble learning improve prediction stability and generalization. The proposed framework provides an effective decision-support tool for proactive customer retention in the telecommunications industry.
Enhancing Binary Image Classification Accuracy Using Low-Rank Adaptation (LoRA) for Deepfake Detection Tam Thanh Thi Pham; Thao Thanh Thi Nguyen; Thai Hoang Le; Hai Son Tran
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.475

Abstract

Deepfake technology poses an increasingly serious threat to personal reputation and social trust, necessitating the development of accurate yet computationally efficient detection systems. Although large pre-trained vision models offer exceptional feature extraction capabilities, full fine-tuning them demands prohibitive computational resources and risks overfitting. This study investigates the application of Low-Rank Adaptation (LoRA) to enhance binary image classification accuracy for deepfake face detection, bridging the gap between parameter efficiency and high classification performance. We systematically integrate LoRA into two dominant architectural paradigms: the Vision Transformer (Swin-T) and ResNet-50. Computational evaluations are conducted on a 40K sub-dataset from the 140K Real and Fake Faces dataset, comparing LoRA against full fine-tuning baselines under identical environments. Experimental results demonstrate that Swin-T + LoRA achieves an outstanding test accuracy of 99.14% and an F1-score of 0.9913, outperforming its full fine-tuning baseline by 9.95 percentage points while training only 5.88% of the total parameters. Conversely, ResNet-50 + LoRA improves test accuracy by 14.11 percentage points over its full fine-tuning baseline, although its performance remains substantially below that of Swin-T + LoRA, indicating that LoRA effectiveness varies across architectural paradigms. These findings demonstrate that parameter-efficient fine-tuning, particularly when combined with Transformer attention layers, offers a promising approach for developing accurate and computationally efficient deepfake detection systems under resource constraints.
Fuzzy-Based Model for Respiratory Disease Classification Auwal Umar; Abdullahi Musa Yola; Musbahu Bala Ibrahim; Muawiyya Modibbo Musa; Habimana Jean Bosco; Haruna Kawuwa; Nura Muhammad Sani; Rutarindwa Jean Pierre
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.480

Abstract

Respiratory diseases remain a major global health concern, highlighting the need for accurate and interpretable computer-aided diagnostic systems. This study proposes a Mamdani Fuzzy Inference System (FIS) for the classification of four respiratory disease categories: Chronic Obstructive Pulmonary Disease (COPD), Asthma, Infected, and Healthy Control (HC). The proposed model utilizes the original variables provided in the Exasens dataset, including dielectric permittivity measurements (Real Permittivity Minimum, Real Permittivity Average, Imaginary Permittivity Minimum, and Imaginary Permittivity Average) together with demographic attributes (Age, Gender, and Smoking Status). A stratified subset of 100 records was selected from the publicly available Exasens dataset and preprocessed using min–max normalization before fuzzification with triangular and trapezoidal membership functions. Expert-defined fuzzy IF–THEN rules were employed within a Mamdani inference framework, and centroid defuzzification was used to obtain the final disease classification. The proposed model was evaluated using stratified 10-fold cross-validation and achieved an overall classification accuracy of 93.00%, with a macro-average F1-score of 91.87%. The experimental results demonstrate that the proposed Mamdani FIS provides accurate, transparent, and interpretable respiratory disease classification while preserving methodological reproducibility. These findings indicate its potential as a decision support tool for respiratory disease diagnosis.
SMOTETomek-DNN: A Machine Learning Framework for Credit Risk Prediction with an Imbalanced Dataset Tiruneh Kebede Dubale; Siraj Sebhatu Seyoum
Scientific Journal of Computer Science Vol. 2 No. 2 (2026): December (Article in Process)
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v2i2.2026.520

Abstract

Accurate credit risk prediction plays a critical role in strengthening the financial stability of microfinance institutions, especially in developing economies, where increasing loan defaults and imbalanced borrower records create significant challenges for reliable decision-making. Although machine learning approaches have improved credit assessment practices, existing models often favor majority-class borrowers and fail to detect high-risk default cases effectively because of severe class imbalance. This limitation highlights the need for more robust and imbalanced-sensitive predictive frameworks. This study aims to develop an effective machine learning-based credit risk prediction framework by integrating data balancing strategies with ensemble and deep learning models. This study systematically investigates the impact of baseline learning and multiple resampling techniques, including oversampling, undersampling, and hybrid methods, when applied to Random Forest, XGBoost, LightGBM, CatBoost, and Deep Neural Network classifiers. The effectiveness of the proposed models was assessed using imbalance-aware evaluation measures, particularly ROC-AUC and Geometric Mean, along with conventional classification metrics. The experimental findings demonstrate that incorporating resampling techniques substantially improved the default detection performance. The DNN model combined with SMOTETomek achieved the best results, obtaining 94.9% F1-score, ROC-AUC 98%, and 97.2% of G-Mean. CatBoost also exhibited consistent competitiveness across different sampling configurations. These findings suggest that hybrid sampling integrated with advanced learning architectures can provide a reliable and practical solution for managing credit risk in imbalanced microfinance datasets, supporting improved lending decisions and sustainable financial operations in the future.

Page 4 of 4 | Total Record : 37

 1   2   3   4 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Vol. 2 No. 2 (2026): December (Article in Process) Vol. 2 No. 1 (2026): June Vol. 1 No. 2 (2025): December Vol. 1 No. 1 (2025): June