cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Christian Harito
Contact Email
christian.harito@binus.edu
Phone
+6221-5350660
Journal Mail Official
aagung@binus.edu
Editorial Address
Universitas Bina Nusantara Jl. Kebon Jeruk Raya No.27 Kebon Jeruk, Jakarta Barat 11530
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
Engineering, Mathematics and Computer Science Journal (EMACS)
Published by Universitas Bina Nusantara
ISSN : -     EISSN : 26862573     DOI : https://doi.org/10.21512/emacs
Core Subject : Science, Education, Engineering,
Civil Engineering, Building, Construction & Architecture Computer Science & IT Engineering Industrial & Manufacturing Engineering Mathematics
Engineering, MAthematics and Computer Science (EMACS) Journal invites academicians and professionals to write their ideas, concepts, new theories, or science development in the field of Information Systems, Architecture, Civil Engineering, Computer Engineering, Industrial Engineering, Food Technology, Computer Science, Mathematics, and Statistics through this scientific journal.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 14 Documents
 1   2 
Search results for , issue "Vol. 7 No. 3 (2025): EMACS" : 14 Documents clear
Analysis of the Relationship Between Implementation and Policy for Regional-Scale Waste Management in Garut District Maulana, Suhenra
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.12689

Abstract

Waste management is currently still a big challenge for all cities/regencies in Indonesia where there is still a lot of household waste that has not been managed and still relies on open dumping. This study aims to determine the relationship between the existence of a policy for the provision of regional-scale Waste Treatment Facilities with TPS 3R and its implementation in each village/sub-district in Garut District. The research method used is quantitative, and the data analysis used in this study is explanatory research which aims to explain whether or not there is a relationship between the independent variables, namely knowing the regent's instruction letter regarding the provision of regional-scale Waste Treatment Facilities with TPS 3R. The process of analyzing research data using the Fisher's Exact Test statistical test shows that the p-value is 0.158. Based on the applicable provisions, if the p-value is smaller than the significance level (α = 0.05) then H_0 (null hypothesis) is rejected and H_1 (alternative hypothesis) is accepted. Therefore, it was found that the p-value is greater than the significance level (0.158 > 0.05) then H_0 is accepted, which means that there is no statistically significant relationship between knowing the policy of providing regional-scale Waste Treatment Facilities with TPS 3R with the implementation of the provision of waste treatment facilities. This means that knowledge of the existence of policies through the regent's instruction letter does not have a significant effect on the implementation of waste treatment in villages/sub-district areas, this could mean that there are other factors that have a greater influence on the implementation of waste treatment in villages/sub-districts.
Proof of Data Weigher Analysis (DWA) and Its Application to Dynamic Meta Data Weigher Goenawan, Stephanus Ivan
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13155

Abstract

Data Weigher Analysis (DWA) addresses the persistent problem of objectively quantifying whether the values in a data set lean more heavily toward the left or right side, a challenge that becomes increasingly complex in irregular or large-scale data sets. Motivated by the need for a simple yet rigorous quantitative framework, this study compares two DWA techniques—the data weighting method and the data mean difference method—designed to compute balance points in a sequence. The data weighting method assigns balanced linear weights to left and right subsets, whereas the data mean difference method calculates first- and second-order mean differences to capture asymmetry in data distribution. We provide a theoretical proof of equivalence between these two formulations, showing that the mean difference approach produces the same linear weighting as the original data weighting scheme. Building on this theoretical result, we introduce a sliding-window algorithm to operationalize DWA on large, dynamic data streams, allowing automated detection of local imbalances in real time. Empirically, we validate our approach on real-world metadata and trade datasets, comparing it against baseline descriptive statistics to assess efficiency and precision. Quantitative findings show that the mean difference method reduces computation processes without loss of accuracy compared with manual weighting. Overall, this work contributes to a unified theoretical foundation, a lightweight algorithmic implementation, and evidence of practical benefits for using DWA in decision-making contexts such as questionnaire analysis, market dynamics, and trade flow monitoring.
Hybrid CNN-Based Classification of Coffee Bean Roasting Levels Using RGB and GLCM Features Halim, Rico; Riftiarrasyid, Mohammad Faisal
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13420

Abstract

This study aims to develop a hybrid Convolutional Neural Network (CNN) model for classifying the roasting levels of Coffea arabica beans by integrating RGB color and GLCM texture features. A total of 1,600 high-resolution images were used, consisting of 1,200 training images and 400 testing images, evenly distributed across four roasting levels: Green, Light, Medium, and Dark. Local feature extraction was performed using a sliding window approach to capture fine-grained color and texture information from each image. Three model types were evaluated: a CNN with RGB-only input, a CNN with GLCM-only input, and a hybrid CNN with dual inputs. The hybrid model consistently demonstrated superior performance, achieving a validation accuracy of 99.74%, with minimal misclassification and stable convergence throughout training. Furthermore, six architectural variations of the hybrid model were tested by applying dropout and L2 regularization techniques. The model combining both dropout and L2 regularization achieved the most balanced results in terms of accuracy, generalization, and training stability. This research contributes an effective feature fusion strategy for fine-grained visual classification tasks, particularly in domains where inter-class visual differences are subtle. The proposed approach offers a cost-effective and scalable solution that is well-suited for real-time implementation in small to medium-sized coffee production facilities, and it shows strong potential for broader applications in agricultural product quality assessment.
Gender Classification Using Keystroke Dynamics: Enhancing Performance with Feature Selection and Random Forest Maulina, Ayu; Charisma, Rifqi Alfinnur
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13445

Abstract

The purpose of this study is to improve gender categorization by examining the usage of keyboard dynamics, with enhanced model performance through data standardization and appropriate feature selection. Features including gender, age, handedness, language, education, and metrics measuring typing behavior like mean_latency, std_latency, and frequency are all included in the dataset. Correlation analysis served as the foundation for the feature selection procedure, which is essential for effective model training, and data normalization was performed to guarantee consistency among the characteristics that were chosen. Because of its stability and capacity to handle complicated data, the Random Forest classifier was selected. The findings demonstrate that the Random Forest model achieved an accuracy of 95% and an F1-score of 95% when using all features, and 82% accuracy with an F1-score of 82.5% when using only the selected features. The results emphasize how important it is to choose the appropriate characteristics and standardize the data in order to increase predictive accuracy. By showcasing keystroke dynamics' capacity for gender categorization, this study advances the area and creates opportunities for further research in user experience improvement, digital service customization, and online behavioral analysis. Overall, the study emphasizes the importance of feature engineering, normalization, and model tuning for achieving accurate and reliable classification outcomes.
Cost Analysis of Construction Cost Planning for Landfill Site Junaedi, Nurhayati; Bayuaji, Ridho; Susilo, Alfred Jonathan
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13800

Abstract

Accurate construction cost planning is essential to ensure project success, as inaccurate estimates may lead to delays, cost overruns, and reduced quality. Landfill construction, which is more complex than many other infrastructure projects, includes several components such as landfill work, leachate treatment facilities, and supporting infrastructure. The purpose of this study is to determine the major cost factors that have a major impact on the overall cost of building landfill sites.  With the aid of SPSS software, a regression analysis was carried out using cost data from six landfill projects in Java Island that were completed between 2013 and 2018.  With a Sig value of 0.000 (<0.05) and a very strong correlation (Pearson Correlation 0.991, within the 0.8–1.0 interval), the results show that landfill work (X3) significantly affects total costs (Y).  Leachate treatment facilities (X4) are another crucial element in a number of situations, but landfill work (X3) consistently represents the largest portion of construction costs, according to proportion analysis. These results demonstrate the growing significance of environmental facilities and point to landfill work as the main factor influencing landfill construction costs.  The study offers contractors and federal and local governments useful information for creating more precise cost estimates, maximizing budgetary allotments, and enhancing planning and development efficiency for landfill projects.
Rice Hull Management System: A Mobile-based Application Tool for Cooperatives Usita, Maricris; Timalog, Cris Ann Fogusa; Javier, Maychiel; Indap, Jhune Carlo; Calera, Gricelyn; Ramos, Jessa Jane
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13839

Abstract

This study focuses on the design and thorough assessment of the Rice Hull Management System RHMS for mobile devices, which targets cooperatives located specifically in Occidental Mindoro, Philippines. The Philippines is well-known for its rice production; however, there are severe concerns regarding environmental sustainability due to the poor management of rice hulls. To offer a solution, the Rice Hull Management System mobile application was created for user cooperatives from Occidental Mindoro. The application was developed using the RAD methodology with React Native and Firebase, enabling the system to be responsive, scalable, and secure. Through the utilization of RHMS, rice hull transactions are processed more efficiently with automated summaries, precision reports, advanced analytics, and real-time updates, all of which facilitate information-based decision-making and foster eco-friendly agricultural practices within and outside the region. The implementation evaluation of the system was conducted using a combination of surveys, usability tests, and performance benchmarks, which included IT specialists, cooperative staff, and members. System reliability was demonstrated to be high, with a Cronbach’s alpha greater than 0.80 and high user satisfaction, with grand mean scores ranging from 4.08 to 4.23 (“Very Good”). Evaluated criteria for the RHMS included efficiency, integration, usability, reliability, safety, and mobility, all of which received excellent ratings, confirming the system's effectiveness in resolving operational manual inefficiencies and enhancing transparency. This study focuses on the application of technology in rice hull waste management to promote environmental sustainability while meeting the requirements of agricultural cooperatives. The RHMS showcases considerable promise for development and implementation across agricultural supply chains, given its secure, easy-to-use, and flexible interface for users, administrators, and cooperatives. Proposed recommendations included continuous system enhancements, compliance with health regulations, integration with other platforms, and training programs to foster sustained system utilization and impact.
Comparative Analysis of CNN, LSTM, and CNN–LSTM for Indonesian Stock Prediction Joddy, Setiawan
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.14326

Abstract

Predicting the stock market remains a challenging task brought by the nonlinear, volatile, and dynamic nature of financial time series. While deep learning techniques have been widely applied in developed markets, studies in emerging markets such as Indonesia remain scarce. This study conducts a comparative analysis of three deep learning models—Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and a hybrid CNN–LSTM—on five randomly selected constituents of the IDX30 index. The data range from January 2020 to December 2024, providing a general view of stock movement in recent years. The models were trained on daily OHLCV (Open, High, Low, Close, Volume) data, which was formatted using a sliding-window approach. Results show that LSTM achieved the lowest RMSE of 0.0222 ± 0.0030, MAE of 0.0172 ± 0.0015, and the highest R² of 0.889 ± 0.068. The Hybrid model delivered intermediate performance, improving upon CNN but not surpassing LSTM. These findings confirm that LSTM networks are particularly effective for stock price forecasting in the Indonesian market, while hybrid CNN–LSTM architectures can provide complementary strengths by balancing short-term feature learning with long-term temporal dependencies.
Integration of Multi-Architecture Deep Learning Models for Pneumonia Detection Based on Chest X-Ray Imaging Edbert, Ivan Sebastian; Oktovianus, Louis; Tanriwan, Robert; Aulia, Alvina
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.14336

Abstract

Pneumonia remains a leading cause of child mortality worldwide, particularly in resource-limited settings where diagnostic tools and expertise are scarce. Recent advances in deep learning offer an opportunity to enhance pneumonia detection through automated analysis of chest X-ray images. This study evaluates the performance of ten state-of-the-art deep learning architectures, including VGG16, ResNet50, DenseNet121, and MobileNetV2, for pneumonia detection using the widely recognized "Chest X-Ray Images (Pneumonia)" dataset. The dataset underwent rigorous preprocessing, including image resizing, data augmentation, and class balancing, to optimize model training and improve generalization. Performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC were utilized to assess model effectiveness. Among the evaluated architectures, MobileNetV2 demonstrated the best performance with an accuracy of 97.51% and an AUC of 0.9941, highlighting its potential for reliable diagnostic applications. The results also emphasize the trade-offs between sensitivity and specificity across models, offering useful insights for real-world deployment. This study underscores the importance of leveraging deep learning models in clinical diagnostics, particularly in environments with limited healthcare resources. Beyond evaluating models, the findings provide evidence-based recommendations for selecting efficient architectures that balance accuracy and computational efficiency. Future work will focus on integrating multimodal datasets, improving explainability, and validating these models in diverse clinical environments to ensure scalability, trust, and generalizability for global health applications.
Comparison of IndoBERT and SVM Algorithm to Perform Aspect Based Sentiment Analysis using Hierarchical Dirichlet Process Octarini, Sheila Prima; Zakiyyah, Alfi Yusrotis; Purwandari, Kartika
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.13493

Abstract

Analyzing the performance of SVM and IndoBERT models for aspect-based sentiment analysis on fashion reviews in Tokopedia E-Commerce. This study employs the SMOTE technique due to the imbalance in the original data. Aspect determination using the Hierarchical Dirichlet Process (HDP) model yields satisfactory results with an adequate coherence score. The comparison between SVM and IndoBERT methods for aspect-based sentiment analysis shows that SVM is superior. IndoBERT achieved an accuracy of 87%, precision of 91%, recall of 93%, and F1-Score of 92%, while SVM attained an accuracy of 96%, precision of 100%, recall of 92%, and F1- Score of 96%. Therefore, the SVM model was chosen for implementation on a website that allows users to view aspect-based sentiment analysis on products in E-Commerce. The HDP model effectively grouped related terms into aspects such as “Material,” “Shipping,” and “Colour,” enhancing interpretability in sentiment classification. The resulting website enables users to analyze product sentiments interactively, providing actionable insights for both sellers and customers to assess product quality and service satisfaction more efficiently.
Low-Resolution Face Recognition: A Review of Methods and Data Utomo, Yesun; Kelvin
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 7 No. 3 (2025): EMACS
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v7i3.14082

Abstract

This paper provides a review of previous studies in Low-Resolution Face Recognition (LRFR), specifically focusing on cross-resolution Face Recognition (FR) methods. While state-of-the-art deep learning FR systems achieve high accuracy on high-resolution (HR) images, they are generally unsuitable for low-resolution (LR) images frequently encountered in applications like surveillance systems, where faces often have low pixel counts due to capture conditions. Cross-resolution FR, which compares an HR image with an LR image, presents a significant challenge due to the distinct visual properties of images at different resolutions. The paper discusses two primary approaches to address this problem: super-resolution (SR), which is a transformative method that aims to construct HR images from LR ones, and unified feature space (UFS), a non-transformative method that maps facial features from varying resolutions into a shared feature space. This work summarizes both SR and UFS methods. Based on the review, the paper concludes that non-transformative (UFS) methods are more suitable for future directions. This recommendation is driven by their lower computational power requirements, proven effectiveness in real-world implementations such as mobile devices and drones, and alignment with current technological trends. The paper also emphasizes the need for further research using real or natural LR face images to identify degradation patterns and compare results between real and artificially generated LR images.

Page 1 of 2 | Total Record : 14

 1   2 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 7 No. 3 (2025): EMACS Vol. 7 No. 2 (2025): EMACS Vol. 7 No. 1 (2025): EMACS Vol. 6 No. 3 (2024): EMACS Vol. 6 No. 2 (2024): EMACS Vol. 6 No. 1 (2024): EMACS Vol. 5 No. 3 (2023): EMACS Vol. 5 No. 2 (2023): EMACS Vol. 5 No. 1 (2023): EMACS Vol. 4 No. 3 (2022): EMACS Vol. 4 No. 2 (2022): EMACS Vol. 4 No. 1 (2022): EMACS Vol. 3 No. 3 (2021): EMACS Vol. 3 No. 2 (2021): EMACS Vol. 3 No. 1 (2021): EMACS Vol. 2 No. 3 (2020): EMACS Vol. 2 No. 2 (2020): EMACS Vol. 2 No. 1 (2020): EMACS Vol. 1 No. 1 (2019): EMACS More Issue