cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mutammimul Ula
Contact Email
mutammimul@unimal.ac.id
Phone
+6281328661999
Journal Mail Official
jurnal.sisfo@unimal.ac.id
Editorial Address
Prodi Sistem Informasi Fakultas Teknik Universitas Malikussaleh Kampus Utama Cot Tengku Nie Reuleut Muara Batu, Aceh Utara, Provinsi Aceh, Indonesia Telp : +62.645.41373, Fax : +62.645.44450
Location
Kota lhokseumawe,
Aceh
INDONESIA
Sisfo: Jurnal Ilmiah Sistem Informasi
Published by Universitas Malikussaleh
ISSN : 2598599X     EISSN : 25990330     DOI : https://doi.org/10.29103/sisfo.v6i1.7950
Core Subject : Science, Education, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Education Engineering Library & Information Science Mechanical Engineering
Jurnal Sistem Informasi Merupakan bidang keilmuan sistem informasi dan teknologi informasi dengan memuat artikel ilmiah penelitian murni dan terapan serta ulasan mengenai metode dan perkembangan teori, serta ilmu-ilmu terapan yang terkait dengan teknologi informasi serta informatika.Jurnal Sistem Informasi diterbitkan oleh Program Studi Sistem Informasi. Redaksi mengundang para peneliti, praktisi untuk menulis artikel ilmiah di bidang yang berkaitan dengan sistem informasi dan teknologi informasi serta informatika.Jurnal Sistem Informasi diterbitkan 2 (dua) kali dalam 1 tahun pada bulan Mei dan Oktober.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 260 Documents
 22   23   24   25   26 
Android-Based Digitalization of Fresh Fruit Bunch Harvest and Supply Chain with Geo-Tagging and Online-Offline Cloud Synchronization Ifan Gultom; Ratu Mutiara Siregar; Andi Prayogi
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27375

Abstract

Background: Manual recording of Fresh Fruit Bunch (FFB) harvest activities at Kebun Tanah Putih PTPN IV Regional 3 results in reporting delays of up to 24 hours, a human error rate of approximately 15–20% per entry, inability to verify harvest locations spatially, and absence of real-time monitoring under limited network connectivity. Objective: This study develops HarvestTrack, an Android and web-based mobile information system for FFB harvest recording and supply chain monitoring, aimed at improving data accuracy, operational efficiency, and transparency in oil palm plantation management. Method: A Research and Development (R&D) methodology with a prototyping approach was employed, covering requirements analysis, system design, implementation, and testing. The system was built with Flutter, Firebase Firestore (cloud backend), and SQLite (local storage) using an offline-first architecture. Delta synchronization via WorkManager and geo-tagging via Fused Location Provider API (≤10 m accuracy) were implemented. Testing included functional, performance, and User Acceptance Testing (UAT). Results: Functional testing confirmed 100% success for offline data recording and automatic cloud synchronization (<5 seconds/entry). Geo-tagging achieved ≤10 m accuracy in 95% of 40 field test locations. Last-Write-Wins (LWW) conflict resolution attained an error rate below 2%. Three role-based user modules (KCS, Foreman, Admin) were fully implemented with differentiated access controls. Contribution: HarvestTrack is the first integrated system combining offline-first architecture, real-time geo-tagging, automated conflict handling, and web-based monitoring dashboard for FFB supply chain digitalization in Indonesia's oil palm sector.
Perancangan Sistem Informasi Pendaftaran dan Seleksi Magang Berbasis Website di PT. Pelindo Multi Terminal Lhokseumawe Athiyatul Ulya; Shufiana Shufiana; Anni Zulfia
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 9 No. 2 (2025): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2025
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v9i2.27390

Abstract

Proses pendaftaran dan seleksi magang di PT. Pelindo Multi Terminal Lhokseumawe masih dilakukan secara manual, menyebabkan keterlambatan pengelolaan data, risiko kehilangan berkas, serta sulitnya proses seleksi dan pelaporan. Kondisi tersebut menyebabkan proses administrasi magang menjadi kurang efektif dan efisien. Oleh karena itu, diperlukan sebuah sistem informasi terkomputerisasi yang mampu mengelola proses pendaftaran dan seleksi magang secara terintegrasi. Penelitian ini bertujuan merancang dan mengimplementasikan sistem informasi pendaftaran dan seleksi magang berbasis website yang terintegrasi di PT. Pelindo Multi Terminal Lhokseumawe. Sistem informasi dikembangkan menggunakan metode Waterfall yang meliputi analisis kebutuhan, perancangan, implementasi, dan pengujian. Sistem dibangun dengan PHP, MySQL, HTML, dan CSS. Hasil penelitian berupa sistem dengan fitur pendaftaran daring, unggah dokumen, pengelolaan data pelamar, seleksi oleh admin, dan penentuan status kelulusan. Pengujian fungsional menunjukkan seluruh fitur berjalan sesuai spesifikasi. Sistem ini dinyatakan layak digunakan di PT. Pelindo Multi Terminal Lhokseumawe.
IoT Based Monitoring System for Fresh Fruit Bunch (FFB) Quality Indicators Using TCS3200 Color Sensor and LoRa Communication at the Palm Oil Mill Receiving Process Nabil Azzaidan Nasution; Ratu Mutiara Siregar; Muhammad Akbar Syahbana Pane
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27518

Abstract

Abstract The quality of Fresh Fruit Bunches (FFB) has a substantial impact on the efficiency of palm oil processing. Nevertheless, traditional assessment techniques remain manual and subjective. This research introduces an Internet of Things (IoT)-based monitoring system designed for the real-time and objective evaluation of FFB maturity. The system employs a TCS3200 color sensor alongside a DHT22 sensor, which are integrated with an ESP32 microcontroller and utilize LoRa communication for long-distance data transmission. The data collected is sent to the ThingSpeak platform for real-time visualization.Field trials conducted at the Cinta Raja plantation indicate that the system is capable of categorizing FFB maturity into ripe, unripe, and undetected based on the predominant color components. However, its performance is affected by environmental variables, especially lighting conditions.In summary, the system offers a practical and cost-effective solution for monitoring FFB quality, although further enhancements in calibration and environmental control are necessary to improve accuracy and reliability.
Design and Development of a Geotagging and QR Code-Based Oil Palm Fertilization Tracking System Using Android Mobile Integration and LoRa SX1278 Mohammad Farodis Azhari; Ratu Mutiara Siregar; Andi Prayogi
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27547

Abstract

This research proposes the development of an Internet of Things (IoT) monitoring system for tracking and verifying palm oil fertilization based on Geotagging and QR Code to overcome challenges in manual fertilization supervision, such as location accuracy, dose precision, and transmission vulnerabilities in remote areas. The system ensures compliance with field standard operating procedures (SOP) through a dual-validation mechanism: spatial coordinate recording via geotagging for location audit trails, and QR Code scanning for fertilizer identity verification. The hardware system architecture integrates a ESP32 microcontroller, a NEO-6M GPS module, and a LoRa Ra-02 SX1278 (433 MHz) transceiver mounted directly on the wheelbarrow. Field workers utilize a Flutter-based mobile Android application to scan the fertilizer labels, which wirelessly forwards data via a Bluetooth Low Energy (BLE 4.2) link to the ESP32. Field integration trials conducted at the ITSI Campus estate demonstrated that the wheelbarrow unit successfully captures high-precision coordinates by locking onto 7 active satellites under dense palm oil canopies with a 3-second refresh rate. Out of 20 live fertilization check-ins executed during the field-testing sessions, the system successfully logged 14 valid transactions and flagged 6 operational deviations, achieving a definitive 70.0% geotagging compliance rate. Furthermore, the offline-first local cache layer guaranteed zero data loss inside cellular blank spots by securely holding transaction logs before automatically synchronizing them to the Firebase Realtime Database. This architecture effectively mitigates the telecommunication infrastructure barrier in remote plantation sectors while generating verifiable, tamper-proof digital audit trails.
Hyperparameter Tuning of Support Vector Machine Using Grid Search for Heart Disease Prediction Reza Mardiansyah Putra; Annisa Rahmadani; Aditya Warman
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27556

Abstract

Hyperparameter tuning plays a crucial role in determining the accuracy and reliability of machine learning models for medical diagnosis, particularly in the identification of critical diseases such as heart disease, which involve complex clinical data characteristics. However, standard machine learning models such as Support Vector Machine (SVM) often suffer from classification bias when hyperparameters are not properly configured. To address this limitation, this study aims to improve heart disease prediction performance through SVM optimization using the Grid Search method. The experiments were conducted using the Cleveland heart disease dataset obtained from the UCI Machine Learning Repository, consisting of 303 patient records and 13 predictive features. The target variable was transformed into a binary classification problem (healthy versus diseased). To prevent data leakage, preprocessing procedures—including missing value imputation and feature normalization—were strictly integrated within a closed machine learning pipeline. The performance of the optimized SVM model was then compared with a baseline SVM model using an independent hold-out test set and a nested cross-validation framework evaluated through ROC-AUC metrics. The experimental results demonstrate that systematic hyperparameter optimization significantly improves predictive performance. The findings indicate that the combination of Grid Search and a rigorous validation strategy produce a robust heart disease prediction model with strong generalization capability when applied to unseen clinical data.
Designing a Smart Reminder System for Monitoring Tuberculosis Patient Medication Adherence Using the Support Vector Machine (SVM) Method Putri Annisa Fadli; Lindawati Lindawati; Sholihin Sholihin
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27713

Abstract

Tuberculosis (TB) remains a major public health challenge that requires continuous monitoring of patient medication adherence to ensure treatment success. However, conventional monitoring methods often rely on manual supervision, making it difficult for healthcare workers to track patient adherence effectively. This study aims to develop a mobile-based smart reminder system for monitoring tuberculosis medication adherence at Puskesmas Ariodillah and to classify patient adherence levels using the Support Vector Machine (SVM) algorithm. The experimental results show that the dataset consists of 503 records categorized as recovered patients and 397 records categorized as patients continuing medication. The SVM model achieved an average cross-validation accuracy of 69.03%. Furthermore, kernel comparison results indicate that the Radial Basis Function (RBF) kernel produces the lowest error rate compared to linear, polynomial, and sigmoid kernels, demonstrating better classification performance. The developed smart reminder system successfully supports tuberculosis medication monitoring and provides useful information regarding patient adherence. These findings indicate that integrating mobile health technology with machine learning can improve adherence monitoring and assist healthcare workers in identifying patients who require additional attention during treatment.
Analysis and Optimization of Cryptocurrency Mining Efficiency Using unMineable and XMRig for Shiba Inu (SHIB) Token Acquisition Baringin Sianipar
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Cryptocurrency mining under a non-native token payout scheme presents multidimensional challenges involving technical performance, economic viability, and environmental impact. This study evaluates the operational feasibility of acquiring Shiba Inu (SHIB) tokens through the unMineable platform combined with XMRig mining software by applying a multidimensional efficiency framework. A descriptive-analytical mixed-methods approach was used, in which nine computing units equipped with Intel Core i5 processors and mid-range GPUs were observed continuously for approximately 30 days. The recorded variables included hashrate, power consumption, operating temperature, SHIB payout volume, electricity cost, and estimated carbon emissions. The results show that GPU units achieved a relative efficiency of approximately 208 H/W under the KAWPOW/Ethash algorithm, whereas CPU units running RandomX reached approximately 46 H/W, indicating that GPU mining was about 4.5 times more efficient per watt in the tested configuration. Economically, the combined configuration consumed 133.2 kWh per month with an electricity cost of IDR 213,120, while generating approximately 1,250,000 SHIB tokens valued at IDR 175,000 under the assumed price of IDR 0.14 per token. This resulted in a monthly deficit of IDR 38,120 and a profitability margin of -21.8%. Environmentally, the operation produced an estimated 93.24 kg CO₂ per month, equivalent to 1,118.88 kg CO₂ annually. These findings confirm that mining evaluation should integrate hashrate, power consumption, payout mechanisms, electricity tariffs, and carbon intensity rather than relying solely on computational speed. The study contributes a replicable evaluation framework and recommends GPU power throttling, XMRig huge-page optimization, and operational scheduling as realistic near-term interventions.
Design of a Web-Based E-Archive Information System for Project Report Documents at BPJN Aceh Nurrizqa Nurrizqa; Nurrisma Nurrisma; Anni Zulfia; Annisa Karima; Muhammad Ghifari Al-Wafi
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Digital transformation in governance is driving the urgent need for a more modern and structured archive management system. The Aceh National Road Implementation Center (BPJN), especially the PPK 2.5 Subfield, still relies on conventional methods based on physical documents in managing project report archives, causing various problems such as difficulty tracing documents, risk of damage, and operational inefficiencies. Different from previous e-archive research which is generally applied to academic environments or general public services, this study presents the integration of the RAD method with the design of interfaces based on the needs of multi-role users in the context of managing technical reports of infrastructure projects in government agencies, a context that has not been widely studied in previous studies. This research aims to design an effective web-based e-archive information system equipped with an interactive user interface to increase the productivity of internal employees. The system development uses the Rapid Application Development (RAD) approach with the PHP programming language and MySQL database, and is built using the CodeIgniter framework with the Model-View-Controller (MVC) architecture. Data collection was carried out through field observation and structured interviews, while system validation used the black-box testing method. All 15 functional test scenarios were declared successful. A Likert scale user satisfaction evaluation involving three internal respondents showed a satisfaction rate of 86.7%, which falls into the excellent category.  The evaluation includes five aspects, namely ease of navigation, clarity of view, system response, design consistency, and general satisfaction, which are the basis for calculating the percentage. Given the limited number of respondents, further research is recommended to expand the number of samples and apply standard usability instruments such as the System Usability Scale (SUS) to strengthen the validity of the evaluation results. In addition, this study has not included comparative quantitative data before and after the implementation of the system, such as the measurement of document search time or the rate of archive loss in the manual mechanism compared to the new system, so the amount of efficiency improvement cannot be measured verified. System functionality validation also includes black-box testing, without additional testing such as stress testing, performance testing, or security testing, so the strength of the evidence for efficiency improvement claims is still limited and indicative. The developed system contains the features of uploading documents, searching archives, downloading reports, and managing user access rights. Although initial results show positive indications of system functionality and user satisfaction, the strength of the evidence for claims of improved archive management efficiency is still limited given the lack of comparative quantitative data before and after implementation and the new testing scope including black-box testing. The developed system still shows initial feasibility to be implemented gradually within BPJN Aceh, with a more comprehensive follow-up evaluation.
Human Face Deepfake Detection Using the YOLO Algorithm Sutri Wandani; Zara Yunizar; Rizki Suwanda
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Deepfake technology has emerged as a significant challenge to digital security because it can generate highly realistic manipulated facial images and videos. The rapid spread of deepfake content has increased the risks of identity fraud, misinformation, privacy violations, and various forms of cybercrime. This study proposes an Android-based human face deepfake detection system using the YOLOv8 algorithm. The dataset consisted of authentic facial images collected from Universitas Malikussaleh students and deepfake facial images generated using artificial intelligence techniques. The research methodology included data collection, image preprocessing, annotation using Roboflow, YOLOv8 model training, model evaluation, TensorFlow Lite (TFLite) conversion, and Android application development. Experimental results demonstrated that the proposed model achieved 95% precision and 95% recall in detecting real and manipulated facial images from both images and videos, indicating reliable detection performance. Nevertheless, several limitations remain. The dataset does not fully represent real-world facial variations, including differences in ethnicity, illumination, facial expressions, head poses, and occlusion caused by masks, glasses, or other objects covering facial regions. These limitations may reduce the model's generalization capability when deployed in real-world environments outside the testing dataset. Furthermore, the deepfake dataset only includes several manipulation techniques and has not been evaluated using more recent deepfake generation methods, such as diffusion model-based face swapping or other advanced generative approaches. Consequently, the model's performance may decrease when encountering manipulation techniques that were not included during training. In addition, the evaluation has not comprehensively considered challenging imaging conditions, such as motion blur, image noise, low-bitrate video compression, and quality variations introduced by different mobile device cameras, which may affect the robustness of the proposed deepfake detection system in practical applications.
Selection-Based Optimization of Naive Bayes and Decision Trees for Intelligent Classification of Sharia Financing Eligibility Tomy Nanda Putra; Atika Fauziyyah; Dori Gusti Alex Candra; Eka Sofiati
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.27634

Abstract

Assessing sharia financing eligibility is a critical process for Islamic microfinance institutions such as Baitul Maal wat Tamwil (BMT), as inaccurate financing decisions may increase financing risk and affect institutional sustainability. However, financing evaluations are often conducted manually and rely heavily on subjective judgment, leading to inconsistencies and potential bias in decision-making. Therefore, this study aims to evaluate the effectiveness of Correlation-Based Feature Selection (CFS) in identifying relevant financing attributes and to compare the classification performance of the Naïve Bayes and Decision Tree (J48) algorithms for sharia financing eligibility assessment. The dataset used in this study consists of 500 historical financing records obtained from BMT Indragiri, comprising 127 eligible and 373 ineligible financing applications. The research process included data preprocessing, feature selection using CFS with the BestFirst search strategy, model construction, and classification using WEKA 3.8. Model performance was evaluated using 10-fold cross-validation based on accuracy, precision, recall, F1-score, Kappa statistic, and Area Under the Curve (AUC). The feature selection results showed that all predictor attributes, namely income, number of dependents, employment status, and financing history, were retained by the CFS algorithm, indicating that each attribute contributes relevant information to financing eligibility classification. Experimental results revealed that the Naïve Bayes classifier achieved an accuracy of 92.4%, precision of 92.3%, recall of 92.4%, F1-score of 92.2%, Kappa statistic of 0.7896, and AUC of 0.971. Meanwhile, the Decision Tree (J48) classifier achieved superior performance with an accuracy of 95.6%, precision of 95.7%, recall of 95.6%, F1-score of 95.6%, Kappa statistic of 0.8851, and AUC of 0.957. In addition, the Decision Tree model generated 23 decision rules and a tree size of 42 nodes, providing transparent and interpretable knowledge to support financing eligibility assessment. The findings indicate that the Decision Tree (J48) algorithm outperformed Naïve Bayes in classifying sharia financing eligibility and offers the additional advantage of interpretable decision rules. The proposed approach can support more objective, consistent, and transparent financing decision-making processes in Islamic microfinance institutions.

Page 25 of 26 | Total Record : 260

 22   23   24   25   26 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026 (In Press) Vol. 10 No. 1 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2026 Vol. 9 No. 2 (2025): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2025 Vol. 9 No. 1 (2025): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2025 Vol. 8 No. 2 (2024): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2024 Vol. 8 No. 1 (2024): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2024 Vol. 7 No. 2 (2023): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2023 Vol. 7 No. 1 (2023): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2023 Vol. 6 No. 2 (2022): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2022 Vol. 6 No. 1 (2022): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2022 Vol. 5 No. 2 (2021): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2021 Vol. 5 No. 1 (2021): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2021 Vol. 4 No. 2 (2020): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2020 Vol. 4 No. 1 (2020): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2020 Vol. 3 No. 2 (2019): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2019 Vol. 3 No. 1 (2019): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2019 Vol. 2 No. 2 (2018): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2018 Vol. 2 No. 1 (2018): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2018 Vol. 1 No. 2 (2017): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2017 Vol. 1 No. 1 (2017): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2017 More Issue