Jiko (Jurnal Informatika dan komputer)
Jiko (Jurnal Informatika dan Komputer) Ternate adalah jurnal ilmiah diterbitkan oleh Program Studi Teknik Informatika Universitas Khairun sebagai wadah untuk publikasi atau menyebarluaskan hasil - hasil penelitian dan kajian analisis yang berkaitan dengan bidang Informatika, Ilmu Komputer, Teknologi Informasi, Sistem Informasi dan Sistem Komputer. Jurnal Informatika dan Komputer (JIKO) Ternate terbit 2 (dua) kali dalam setahun pada bulan April dan Oktober
Articles
11 Documents
Search results for
, issue
"Vol 9 No 1 (2026)"
:
11 Documents
clear
<![CDATA[PERFORMANCE EVALUATION OF HYBRID CLUSTERING K-MEANS AND DBSCAN WITH FEATURE WEIGHT OPTIMIZATION ]]>
<![CDATA[Vic Devlin]]>;
<![CDATA[Robet Robet]]>;
<![CDATA[Octara Pribadi]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.10859
<![CDATA[This research evaluates the performance of a hybrid clustering model that integrates K-Means and DBSCAN, enhanced through Feature Weight Optimization (FWO) using a Genetic Algorithm (GA), to achieve more precise consumer data segmentation. Two benchmark datasets, Customer Personality Analysis (CPA) and Online Retail (OR), were utilized to examine how different clustering techniques respond to variations in data structure. The feature weighting process was optimized using GA to improve the representational contribution of each variable toward the final cluster configuration. The Silhouette Score was adopted as the primary evaluation metric to measure intra-cluster cohesion and inter-cluster separation. Experimental findings reveal that for the CPA dataset, the Hybrid + FWO method achieved the best performance with a Silhouette Score of 0.9600, while the K-Means + FWO method recorded the highest score of 0.9804 on the OR dataset. Across all scenarios, the inclusion of FWO consistently enhanced clustering stability and interpretability. These results highlight that algorithm selection must consider dataset characteristics, and that feature weight optimization is pivotal in strengthening segmentation quality and ensuring more meaningful insights in consumer behavior analytics.]]>
<![CDATA[FIELD LEVEL ENCRYPTION IMPLEMENTATION USING AES-256 FOR SECURE ACADEMIC INFORMATION SYSTEMS ]]>
<![CDATA[Adi Fajaryanto Cobantoro]]>;
<![CDATA[Elok Putri Nimasari]]>;
<![CDATA[Sincan Maulana]]>;
<![CDATA[Mohd Zuber]]>;
<![CDATA[Shaikh Ameer]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.10884
<![CDATA[Data protection in higher education remains a pressing concern as student records and program registration data are frequent targets of cyber incidents. This paper presents the design and implementation of AES-256 to secure the registration feature within an academic information system (AIS). Specifically, this study delivers three main contributions: a modular cryptographic implementation at the controller level, a granular field-level encryption policy for sensitive attributes, and a validated security mechanism. We integrated a cryptographic module into a Fastify (Node.js) backend and PostgreSQL datastore. The results demonstrate the fulfillment of these contributions: first, the modular implementation effectively isolates encryption logic from the database layer; second, the field-level policy successfully secures sensitive PII while maintaining 100% query efficiency for non-sensitive data; and third, the security mechanism was validated through 17 white-box scenarios and dual-layer API testing. These results confirmed 100% functional correctness in encryption/decryption cycles and robust handling of invalid data inputs. The study contributes a practically deployable pattern for field level encryption in university information systems.]]>
<![CDATA[INFORMATION SECURITY RISK MATURITY ASSESSMENT OF CENTRAL JAVA DATA CENTER BASED ON GOVERNMENT REGULATIONS AND ISO 27001:2022 ]]>
<![CDATA[Fajar Andy Daniarta]]>;
<![CDATA[Aji Supriyanto]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.10965
<![CDATA[The increasing use of E-government (SPBE) has accelerated digital change in public administration but has also created real risks to information security. This study aims to evaluate the level of information security risk management maturity at the Central Java Provincial Data Center by merging the Indonesian SPBE Risk Management framework (PermenPANRB No. 5/2020) with SNI ISO/IEC 27001:2022. The evaluation utilized a descriptive qualitative method, backed by observations, interviews, and a survey-based maturity assessment that aligns with the control areas of ISO/IEC 27001. Findings reveal that the overall maturity sits between “Managed and Measurable” (Level 4) and “Optimized” (Level 5), indicating that most procedures are organized, documented, and consistently observed; however, some sub-controls still need enhancement, especially those related to incident response, ongoing improvement, and staff awareness. This research emphasizes the necessity for a more flexible security governance approach and contributes by integrating national regulatory guidelines with global information security frameworks to enhance the maturity assessment of government data centers.]]>
<![CDATA[A HYBRID DEEP LEARNING AND TREE BOOSTING APPROACH FOR BBCA STOCK PRICE FORECASTING WITH SHAP EXPLAINABILITY ]]>
<![CDATA[Muhamad Sabri Ahmad]]>;
<![CDATA[H. Hadiyanto]]>;
<![CDATA[Ridwan Sanjaya]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11102
<![CDATA[Forecasting stock price movement is a complex task due to nonlinear patterns, market volatility, and the influence of various technical and fundamental factors. This study proposes a hybrid forecasting framework that integrates the sequential learning capability of the Gated Recurrent Unit (GRU) with the nonlinear regression strength of Extreme Gradient Boosting (XGBoost) to predict the daily closing price of Bank Central Asia Tbk (BBCA). The dataset consists of historical BBCA prices from 2017 to 2025 and includes technical indicators such as moving averages, RSI, MACD, and Bollinger Bands. An 80:20 chronological split was used to evaluate model generalization through MAE, RMSE, MAPE, and R² metrics. Experimental results show that the hybrid GRU–XGBoost model outperforms both standalone GRU and XGBoost models, achieving the best performance with MAE of 229.09, RMSE of 312.26, and R² of 0.874 MAPE of 2.37%. Furthermore, SHAP-based explainability analysis highlights that price-based features and trend–momentum indicators contribute most significantly to the prediction output, while the GRU-derived sequential feature enhances temporal pattern recognition. These findings demonstrate that combining deep learning and boosting techniques produces a more accurate and interpretable forecasting model suitable for financial decision-making and risk analysis.]]>
<![CDATA[COMPARATIVE ANALYSIS OF ENSEMBLE CLASSIFICATION MODELS AND SUPPORT VECTOR MACHINES IN MEASURING STRESS LEVELS BASED ON EEG SIGNALS ]]>
<![CDATA[Seftia Angelina]]>;
<![CDATA[Sau Dohot Siregar]]>;
<![CDATA[Achmad Ridwan]]>;
<![CDATA[Lewis Francolim]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11151
<![CDATA[Stress is a physiological and psychological response that can develop into serious health issues when prolonged. EEG-based stress detection has become an important approach; however, many studies still lack validation for multilevel classification and real-world conditions. This study focuses on inmates at Binjai Correctional Facility and compares the performance of Support Vector Machine (SVM), Random Forest (RF), and a combined ensemble model of Random Forest and AdaBoost for classifying three stress levels: stressed, relaxed, and neutral, using EEG signals. Experimental results show that the SVM model achieved an accuracy of 81% with a Minimum Classification Error (MCE) of 0.16. The Random Forest model significantly improved performance, reaching 96% accuracy and an MCE of 0.04. The best performance was obtained by the ensemble model combining Random Forest and AdaBoost, which achieved an accuracy of 97% and reduced the MCE to 0.03, indicating a 1% improvement over Random Forest alone.]]>
<![CDATA[REAL-TIME DOLPHIN DETECTION IN AQUATIC ENVIRONMENTS USING YOLO11-NANO ]]>
<![CDATA[Febriyanti Ludja]]>;
<![CDATA[Florensce Sumarauw]]>;
<![CDATA[Robby Moody Lintong]]>;
<![CDATA[Steven R. Sentinuwo]]>;
<![CDATA[Alwin M. Sambul]]>;
<![CDATA[Muhamad Dwisnanto Putro]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11256
<![CDATA[Dolphin monitoring plays a crucial role in maintaining the balance of marine ecosystems and supporting the ecotourism sector. However, in practice, automated dolphin monitoring still faces significant challenges, particularly when deployed in real-time applications within dynamic underwater environments. Previous research on computer vision-based dolphin detection generally uses models with high computational complexity. This condition has resulted in increased resource requirements and long inference times, making it difficult to apply to underwater device-based monitoring systems with limited computing power. Therefore, it is necessary to develop more efficient detection models and algorithms so that the system can operate reliably under real-world monitoring scenarios in resource-limited environments. Moreover, the adoption of the latest-generation lightweight detection architectures in aquatic scenarios remains limited. To address these challenges, this study proposes the application of YOLOv11-Nano as a lightweight detection architecture designed for low-latency dolphin monitoring on resource-constrained devices. The proposed model is optimized to strike a balance between inference speed and detection accuracy, enabling competitive performance under challenging underwater conditions. Experimental results show that YOLOv11-Nano achieves a computational complexity of 6.4 GFLOPs with 2.59 million parameters, while attaining 65.0% mAP@50, 43.1% mAP@50:95, and an inference speed of 18.34 FPS. These results show that YOLOv11-Nano is capable of delivering stable and efficient performance with relatively low computational requirements and high inference speed, demonstrating strong potential for application in real-time monitoring systems based on devices with limited resources to support automatic dolphin detection as part of marine ecosystem conservation efforts.]]>
<![CDATA[AN EVALUATION OF MOBILE BANKING USER INTERFACE AND USER EXPERIENCE USING THE FUZZY KANO METHOD: EVIDENCE FROM BCA MOBILE AND PERMATA ME USERS ]]>
<![CDATA[Palma Juanta]]>;
<![CDATA[Glenaldo Glenaldo]]>;
<![CDATA[Raja Zulkarnain Hasibuan]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11306
<![CDATA[This study aims to evaluate general mobile banking user interface (UI) and user experience (UX) quality using BCA Mobile and Permata ME as representative applications of digital banking services in Indonesia through the Fuzzy Kano approach, which is capable of accommodating uncertainty and subjectivity in user assessments. This study involved 95 active users in Medan City. A total of 20 application features were evaluated based on levels of satisfaction (delight) and dissatisfaction (disgust) and then classified into Must-be, One-dimensional, and Attractive quality attributes. The analysis was conducted in an aggregate manner to capture overall user expectations toward mobile banking applications rather than to compare competitive superiority between the two platforms. The results indicate that the feature “Clear Icons” has the highest priority in the Must-be category, “Well-Organized Transaction History” is the most dominant feature in the One-dimensional category, and “Two-Step Verification for Large Transactions” ranks highest in the Attractive category. These findings suggest that most mobile banking user satisfaction is driven by features with a linear relationship between performance and satisfaction, while additional security features function as satisfaction enhancers. From an academic perspective, this study strengthens the application of the Fuzzy Kano method in evaluating mobile banking UI/UX by emphasizing aggregated user perceptions across multiple applications. Practically, the findings provide guidance for prioritizing feature development to enhance customer satisfaction and loyalty in mobile banking services.]]>
<![CDATA[IMPLEMENTATION BLOCKCHAIN IN MOBILE APPLICATIONS SEMINAR ON E-CERTIFICATE VERIFICATION USING SMART CONTRACTS ]]>
<![CDATA[Sahri Ramadan]]>;
<![CDATA[Sawali Wahyu]]>;
<![CDATA[Budi Tjahjono]]>;
<![CDATA[Riya Widayanti]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11356
<![CDATA[The increasing adoption of electronic certificates in academic and professional environments raises critical challenges related to authenticity, data integrity, and verification reliability. Conventional certificate management systems commonly rely on centralized architectures and manual validation procedures, which are vulnerable to manipulation, duplication, and single points of failure (SPoF). This study proposes a blockchain-based electronic certificate verification system implemented on a private Hyperledger Fabric network using smart contracts. The system records certificate verification metadata on a distributed ledger to ensure integrity and traceability while maintaining storage efficiency. Smart contracts automate the issuance and validation lifecycle, enabling transparent and tamper-resistant certificate management. The verification process is conducted by comparing document authentication data with records stored on the blockchain. Experimental evaluation demonstrates that the proposed system can accurately identify document alterations and consistently distinguish between valid and invalid certificates. The results indicate that the integration of blockchain and smart contracts as an active validation mechanism enhances transparency, reduces dependence on centralized authorities, and improves trust in mobile-based digital credential systems. Therefore, the proposed approach provides a secure and reliable framework for electronic certificate verification in academic environments.]]>
<![CDATA[STUDENT ACADEMIC PERFORMANCE ANALYSIS USING SUPPORT VECTOR REGRESSION AND MULTILAYER PERCEPTRON: AN EDUCATIONAL DATA MINING APPROACH ]]>
<![CDATA[Nisa Miftachurohmah]]>;
<![CDATA[Nasruddin Nasruddin]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11442
<![CDATA[Predicting student academic performance lays a foundation for data- informed educational decisions. This work uses the public Student Performance Data set from Kaggle website which contains 10,000 records and is used for predicting ‘Performance Index’. Median imputation, one hot encoding for categorical variables and feature standardization were used for preprocessing of data. The model was evaluated through 5-fold cross-validation, and the proportions of training and testing data were set at 80:20 in each fold. Two different regressi on models were utilized: Support Vector Regression (SVR) with RBF kernel and a Multilayer Perceptron(MLP) consisting of two hidden layers(128–64 neurons). Both models achieved excellent prediction accuracy. SVR achieved an MAE of 1.6653, RMSE of 2.0991 and R²=0.9881 whereas MLP slightly performed better than SVR with a MAE 1.6596, RMSE of 2.0872 and R²=0.9882. Learning curve analysis showed stable convergence with little overfitting. The results show their efficiency and they are both kernel-based and neural network-based methods to predict academic performance. Future work will need to test the models on much more diverse data sets and may incorporate further context variables to improve model robustness and interpretability.]]>
<![CDATA[MOBILE APPLICATION FOR IDENTIFICATION OF EMPLOYEE STRESS PATTERN USING DEEP LEARNING APPROACH ]]>
<![CDATA[Sawali Wahyu]]>;
<![CDATA[Silvia Ratna Juwita]]>;
<![CDATA[Ryan Putra Laksana]]>;
<![CDATA[Lista Meria]]>
<![CDATA[ JIKO (Jurnal Informatika dan Komputer) Vol 9 No 1 (2026) ]]>
Publisher : <![CDATA[Program Studi Teknik Informatika Universitas Khairun ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33387/jiko.v9i1.11527
<![CDATA[Employee stress has become a critical issue affecting organizational productivity, well-being, and performance, especially in dynamic work environments. This study proposes an integrated mobile-based stress prediction and recommendation system that combines Long Short-Term Memory (LSTM) and Neural Collaborative Filtering (NCF) to identify employee stress levels and provide personalized improvement recommendations. Experimental evaluation using 1000 datasets was used to test the LSTM and NCF models. The LSTM model was used to predict stress levels due to its ability to capture complex patterns in multidimensional data, while NCF was used to generate personalized recommendations based on collaborative patterns. The results showed that the LSTM model achieved superior classification performance with 98% accuracy and the recommendation evaluation showed good convergence performance, with a Hit Ratio reaching 0.92 and a Normalized Discounted Cumulative Gain (NDCG) reaching 0.89, indicating high recommendation relevance. Furthermore, the system usability evaluation using the System Usability Scale (SUS) involving 30 respondents resulted in an average score of 80.81, which is categorized as excellent usability. The integration of deep learning and collaborative filtering into a mobile platform provides an effective and intelligent solution for employee stress prediction and intervention. This study contributes to the development of an adaptive occupational health monitoring system and demonstrates the potential of AI-based mobile applications in supporting mental health management in the workplace.]]>
