cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
KARONA CAHYA SUSENA
Contact Email
karona.cs@unived.ac.id
Phone
+6281541234500
Journal Mail Official
karona.cs@unived.ac.id
Editorial Address
Jl. Meranti Raya No. 32, Sawah Lebar, Kota Bengkulu
Location
Kota bengkulu,
Bengkulu
INDONESIA
Jurnal Media Computer Science
Published by Universitas Dehasen Bengkulu
ISSN : -     EISSN : 28280490     DOI : https://doi.org/10.37676/jmcs
Core Subject : Science,
Computer Science & IT
Jurnal Media Computer Science merupakan jurnal nasional yang diterbitkan oleh Universitas Dehasen Bengkulu sejak tahun 2022. Jurnal Media Computer Science memuat artikel hasil-hasil penelitian di bidang Komputer, Sistem Informasi dan Teknologi. Jurnal Media Computer Science berkomitmen untuk menjadi jurnal nasional terbaik dengan mempublikasikan artikel berbahasa Indonesia yang berkualitas dan menjadi rujukan utama para peneliti.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 230 Documents
 18   19   20   21   22 
Gold Price Prediction Based On Long Short-Term Memory (LSTM) For Investment Decision-Making Indra Yustiana; Siti Khoerunisa; M. Ikhsan Thohir
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9233

Abstract

The movement of gold prices serves as a critical indicator in investment decision-making, especially in dynamic and uncertain market conditions. This study aims to develop a gold price prediction model based on Long Short-Term Memory (LSTM), a type of Recurrent Neural Network (RNN) capable of capturing temporal patterns in historical price data. The goal of implementing this model is to generate more accurate predictions compared to conventional methods, thereby supporting more informed investment decisions. The research utilizes daily gold price data over a specific period, combined with other economic indicators such as oil prices, exchange rates, and interest rates. The data undergoes preprocessing steps, including normalization and division into training, validation, and testing sets. The proposed model architecture consists of a single LSTM layer with 64 neurons and an output layer, trained over 50 epochs with a batch size of 32. The results show that the LSTM model achieves high prediction accuracy. This is demonstrated by evaluation metrics including a Mean Absolute Error (MAE) of 26.12, Mean Squared Error (MSE) of 1269.15, Root Mean Squared Error (RMSE) of 35.63, and an R² score of 0.9858, indicating that the model can explain 98.58% of the variance in actual gold price data. Furthermore, the visualization of the results indicates that the model is capable of closely following gold price trends and consistently predicting upward price movements over the next 30 days. The model has also been successfully implemented into a web-based platform using TensorFlow.js, enabling users to access real-time predictions in an efficient and responsive manner.
Strategi Komunikasi Pengelolaan Sampah di Kota Ambon: Perspektif SCCT dan Konstruksi Sosial Christ J. Belseran; Ridzki Rinanto Sigit
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9245

Abstract

This study aims to analyze the waste management communication strategy by the Ambon City government using the Situational Crisis Communication Theory (SCCT) and the Social Construction Theory. This research employed a qualitative case study approach in the riverbank areas of Way Batu Merah and Way Ruhu Galala. The results show that the behavior of disposing waste into the river is a long-standing social construction reinforced by weak infrastructure and public communication. The government’s communication strategy still relies heavily on bolstering and diminishing approaches, while rebuilding and attenuating are not yet optimal. The study recommends integrating the Theory of Planned Behavior (TPB) to understand community behavioral tendencies better and to develop culturally rooted public communication strategies.
Analysis Of The Accuracy Of The Naive Bayes Algorithm In Classifying The Quality Of Malang Manalagi Apples Arif Permana; Yuza Reswan
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9312

Abstract

Apples are one of the most popular fruits in Indonesia and around the world. Manalagi apples, originating from the city of Malang in East Java, are renowned for their unique taste and quality. In the fruit distribution and trade channels, determining apple quality quickly and accurately is crucial, especially to ensure the quality of the product received by consumers. However, the current apple quality assessment method is still manual and relies on visual observation by individuals, making it susceptible to subjectivity, fatigue, and errors in assessment. thus prone to subjectivity and inconsistency. To overcome this, this study developed a naive Bayes algorithm accuracy analysis system in classifying the quality of Malang Manalagi apples. The system was built on the MATLAB platform with an interactive graphical interface, and utilizes color feature extraction (Rmean, Gmean, Bmean), texture (GLCM), and image statistical features such as entropy, smoothness, skewness, and intensity. This method enables automatic and accurate classification of fresh and rotten apples. This research is expected to be a supporting solution in the process of assessing fruit quality more efficiently and objectively, and applicable to the needs of the agricultural industry.
Data-Based Health Insurance Premium Modeling at KUD Tirta Kencana Using a Machine Learning Approach Sukardi Sukardi; Syafri Arlis
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9354

Abstract

The Village Unit Cooperative (KUD) plays a strategic role in improving the economic welfare of rural communities. However, attention to the health aspects of members is often not a priority. This study aims to analyze the health insurance costs required by members of the Tirta Kencana KUD in Kuantan Singingi District using a data-based approach and predictive modeling. The methods used include collecting membership and health claim data, processing the data using Principal Component Analysis (PCA), and applying predictive algorithms to estimate ideal and sustainable insurance costs. The analysis results indicate a significant correlation between age, membership status, and health history with the amount of premiums that should be covered. The predictive model successfully identified the optimal premium scheme with a predictive accuracy of 92%. These findings are expected to serve as a basis for policy-making in planning more efficient and equitable cooperative-based insurance. This research also opens opportunities for the application of data science in optimizing community-based microhealth systems.
Automated Medical Classification of Human Brain Tumors Leveraging the Xception Convolutional Neural Network Bambang Supperianto; Syafri Arlis
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9356

Abstract

Brain tumors are among the most critical neurological disorders, marked by abnormal cell proliferation within the brain, either benign or malignant,adversely impacting cognitive, motor, and overall patient quality of life.Accurate and prompt diagnosis is pivotal for determining effective treatment and improving survival outcomes. While Magnetic Resonance Imaging (MIRI) remains the standard diagnostic tool due to its high soft-tissue contrast, manual interpretation is labor-intensive, expertise-dependent, and subject to observer bias. Consequently, deep learning approaches, particularly Convolutional Neural Networks (CNN), have garnered considerable attention for automating brain tumor classification with superior efficiency and accuracy. This study presents a medical classification model for human brain tumors based on the Xception CNN architecture. The model was developed using a publicly available MRI dataset comprising 2,875 images categorized into glioma, meningioma, and pituitary tumor classes. Preprocessing involved resizing, normalization, and data augmentation. The model was initialized with ImageNet weights and fine-tuned for the three-class classification task with softmax activation.The proposed model achieved robust performance, recording test accuracy of 98.4% and an average F1-score of 98.5%, indicating balanced precision and recall. Confusion matrix and error analysis revealed minimal and evenly distributed misclassifications, while training dynamics showed rapid convergence with no significant overfitting.These findings demonstrate the effectiveness and clinical feasibility of the Xception CNN for automated brain tumor diagnosis. Future research should validate the approach on larger, multi-institutional datasets and integrate interpretability techniques to strengthen clinical applicability.
Expert System for Diagnosing Mental Disorders at Soeprapto Psychiatric Hospital in Bengkulu Province Using Forward Chaining Method Ahmad Syukron Ali; Siswanto Siswanto; Jhoanne Fredricka
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9426

Abstract

Expert systems are a branch of artificial intelligence designed to mimic the ability of an expert to make decisions or solve problems in a particular field. This study aims to develop a web-based expert system capable of performing diagnoses using the forward chaining method as an inference mechanism. This system is intended to help the public recognize specific problems, particularly in the field of health. Unfortunately, people often lack access to professional psychological services. This study aims to build web-based expert system that can help make an initial diagnosis of mental disorders using forward chaining method. This system is designed to collect symptoms from users, process them using a rule base determined by experts, and provide automatic diagnosis results. In its development, the system uses the PHP programming language and MySQL database to store symptom data, disease information, and consultation results. The inference process is conducted sequentially (forward chaining) based on the symptoms selected by the user until a conclusion is reached regarding the type of mental disorder and its likelihood. Testing results indicate that the system can provide reasonably accurate results in identifying users' mental conditions based on the symptoms entered. This system is expected to serve as a useful initial consultation tool, particularly in communities with limited access to mental health services. However, this system is not intended to replace the role of professionals but rather as a form of technological support to aid in early detection.
Implementation Of Htb And Cacti Methods For Bandwidth Allocation And Network Monitoring At SMA N 2 Bengkulu City Oki Zainal Abidin; Hari Aspriyono; Abdussalam Al Akbar
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9496

Abstract

SMAN 2 Bengkulu City is one of the senior high schools that has utilized computer networks to support teaching and learning activities, particularly in its computer laboratory. However, problems arise due to the absence of a system that can fairly distribute bandwidth and monitor connected devices. This study aims to implement the Hierarchical Token Bucket (HTB) method for bandwidth allocation and employ Cacti as an open-source network monitoring tool. HTB enables proportional bandwidth distribution by determining network usage priorities, while Cacti monitors devices based on IP addresses and presents the network conditions (active/inactive) in graphical form. The results indicate that the application of HTB improves the fairness of bandwidth distribution, while Cacti provides real-time information about network conditions, thereby supporting administrators in effectively managing the school’s network.
Application Of The K-Medoid Method In Clustering Population Data By Subdistrict At The Population And Civil Registration Office Of Central Bengkulu Regency Reza Vebriansyah; Yupianti Yupianti; Fahrul Ikram Nizar
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9501

Abstract

The application of the K-Medoid Method in grouping population data per sub-district at the Population and Civil Registration Office of Central Bengkulu Regency can provide information in the form of population density levels of sub-districts/villages in Central Bengkulu Regency which are divided into 3 groups, namely high, medium and low density levels, and can assist local governments in formulating more targeted policies. From the population data of 143 sub-districts/villages, data grouping analysis was carried out using the K-Medoid Method through the application that has been built, so that the results of the grouping of population data per sub-district/village which stopped at the 2nd iteration, namely a high population density level of 4 sub-districts/villages, a medium population density level of 17 sub-districts/villages, and a low population density level of 122 sub-districts/villages. Based on the tests that have been carried out, it is seen that the application of the K-Medoid Method can group population data per sub-district at the Population and Civil Registration Office of Central Bengkulu Regency which is summarized based on the data collection year.
Penerapan Metode Hierarchical Token Bucket Dalam Managemen Bandwidth Pada Pt Galempa Sejahtera Bersama Liovi Egi Likardo; Khairil Khairil; Abdussalam Al Akbar
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9555

Abstract

Bandwidth management is necessary to ensure that the available bandwidth is allocated according to the needs of each connected user. One method that can stabilize the allocation of bandwidth is the Hierarchical Token Bucket (HTB) method. The purpose of this research is to regulate the amount of bandwidth to meet the internet usage requirements for each user without allowing any single user to dominate the bandwidth usage on the internet network. The research was conducted in five stages: problem analysis, data collection, design and implementation of HTB, HTB implementation, and analysis of the final results of the system using HTB. Problem analysis and data collection were obtained through direct observation. The design and implementation were carried out using the HTB method on MikroTik routers. The HTB method allows us to create queues in a more structured manner by performing hierarchical groupings. Testing results show that the HTB method can manage bandwidth usage for each user when using the internet simultaneously. The analysis of the application of the HTB method at PT. GSB indicates that each user receives bandwidth based on limit-at and priority.
Sikurma: Development Of A Google Apps Script–Based Document Repository Information System For Optimizing Digital Archive Management In Higher Education Indra Surya Permana; Ade Sutriyono; Citra Setyo Dwi Andhini; Sabili Muhammad Azka
Jurnal Media Computer Science Vol 5 No 1 (2026): Januari
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v5i1.9560

Abstract

Strategic document management for accreditation and Key Performance Indicator (KPI) reporting poses significant challenges for higher education institutions due to unstructured digital archives and high implementation costs of commercial Electronic Document Management Systems (EDMS). This research aims to design, develop, and evaluate SIKURMA (Document Repository and Archive Management Information System), a low-cost and easily replicable document repository solution based on Google Workspace. The development method employs a prototyping approach with user-centered design orientation, including stages of needs analysis, system design, development using Google Apps Script, and evaluation through the DeLone & McLean Information System Success Model framework. The research results demonstrate a functional SIKURMA prototype capable of dynamically displaying file lists from Google Drive, equipped with hierarchical navigation features, global and per-folder search capabilities, and a simple spreadsheet-based authentication system. Quantitative evaluation involving 35 lecturer respondents from various study programs shows that all system success hypotheses were accepted with high significance levels. The system successfully achieves zero-cost infrastructure by utilizing available Google Workspace, making it easily replicable by various higher education work units. SIKURMA proves to offer practical and efficient solutions for optimizing digital document governance in higher education institutions with limited resources

Page 20 of 23 | Total Record : 230

 18   19   20   21   22 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol 5 No 3 (2026): Juli Vol 5 No 2 (2026): April Vol 5 No 1 (2026): Januari Vol 4 No 2 (2025): Juli Vol 4 No 1 (2025): Januari Vol 3 No 2 (2024): Juli Vol 3 No 1 (2024): Januari Vol 2 No 2 (2023): Juli Vol 2 No 1 (2023): Januari Vol 1 No 2 (2022): Juli Vol 1 No 1 (2022): Januari More Issue