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 181 Documents
 15   16   17   18   19 
Binary Classification of Asthma for the CAPS Pediatric Dataset in Malawi Using Machine Learning Sodiq, Jaffarus; Syarifah Diana Permai
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.v7i3.14108

Abstract

Childhood asthma poses a significant public health challenge, especially in low- and middle-income countries. An early intervention is essential for effective management and improved prevention of Childhood asthma. This study aims to develop a predictive model for childhood asthma by applying machine learning (ML) techniques. The dataset includes self-reported information on respiratory symptoms, anthropometric measurements, spirometry data, and personal carbon monoxide (CO) exposure among children aged 6–8 years in rural Malawi. We employed a supervised ML approach, focusing on classification algorithms and handling imbalanced outcomes, including Random Forest, Logistic Regression, and XGBoost. Additionally, this study applied the Synthetic Minority Over-sampling Technique (SMOTE), creating synthetic samples of the minority class to balance the distribution of the outcome variable in the training data. Data preprocessing involved handling missing values, feature selection, and normalization to ensure data quality and model performance. Model evaluation was conducted using cross-validation and performance metrics, including precision, recall, and F1-score. Among the evaluated models, Logistic Regression emerged as the most balanced approach, offering strong precision and the highest F1-score while maintaining a reasonable recall rate. This balance reduces the likelihood of overdiagnosis while still capturing a significant proportion of true positives, making it suitable for early screening applications. Moreover, Logistic regression, with its simple mathematical structure, provides more transparency and explainability, which are vital for clinical adoption and gaining practitioner trust.
Web-Based Quality Control Dashboard Design for Data Validation and Monitoring: A Case Study of BMKG Instruments Purwandari, Kartika; Aufauzan, Brian Tirafi; Sigalingging, Join Wan Chanlyn
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.13532

Abstract

Accurate meteorological data are vital for the operational activities of the Agency for Meteorology, Climatology, and Geophysics (BMKG), specifically for weather forecasting and disaster mitigation. However, Automatic Weather Station (AWS) instruments frequently encounter sensor degradation and technical malfunctions, which compromise data validity. Traditional manual validation is inefficient and prone to human error. This study addresses these gaps by designing a web-based Quality Control (QC) dashboard for real-time AWS data monitoring. Developed using the Laravel framework and PostgreSQL, the system integrates Leaflet.js and Chart.js for interactive spatial and analytical visualization. Using the Agile Scrum methodology, the development process was iteratively refined across eight sprints. Implementation results show a significant improvement in data validation accuracy and a reduction in potential human error. User Acceptance Testing (UAT) with fifteen BMKG specialists confirms high usability, with the system receiving "Strongly Agree" ratings for its efficiency in real-time monitoring and reporting. The practical implications include enhanced data credibility for national climate modeling. This paper concludes that while the dashboard streamlines workflows, future iterations should incorporate automated anomaly detection algorithms. Limitations include a current reliance on static validation thresholds, suggesting a need for machine learning integration in future research.
Measuring Student Satisfaction with Academic Applications at BINUS University Through the Customer Satisfaction Score (CSAT) Framework Fransisco, Mario
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.14540

Abstract

This study examines student satisfaction with four key academic applications used at BINUS University: BinusMaya, Neksus Semester Plan, Thesis App, and the Library App which play a central role in supporting learning activities, academic administration, and access to academic resources. The study applies the Customer Satisfaction Score (CSAT) framework, a widely used approach for evaluating user satisfaction with system quality, usability, and performance. The CSAT evaluation is adapted to the functional characteristics of each application. Thesis App, BinusMaya, and Neksus Semester Plan, which directly support core academic processes, are assessed using four dimensions: fulfilment, efficiency, system availability, and accuracy. Meanwhile, the Library App, which functions as a supporting academic resource platform, is evaluated using ease of use, features and functionality, and system performance. A quantitative descriptive approach was employed, with data collected through an online survey conducted between July and September 2025. A four-point Likert scale was used to encourage clear evaluative responses, and the sample size was determined using Slovin’s formula. The findings indicate that students generally report positive satisfaction across all applications. Thesis App performs strongly in terms of efficiency and accuracy, while the BinusMaya shows high satisfaction in fulfilment. Neksus Semester Plan receives favourable evaluations in efficiency but faces responsiveness challenges during peak usage periods. Library app is positively rated for its features, although improvements are needed in system performance and interface consistency. Overall, the results suggest that BINUS University’s academic applications effectively support student activities, while also highlighting the importance of continuous system improvement.
Machine Learning Approach: A Comparative Analysis of Classifiers in Predicting Obesity Type Tedjasulaksana, Jeffrey; Dinata, Ferry Jaya; Krisnadi, Rafael; Reksosamudro, Matthew S.W.; Wen, Wilbert; Hidayat, Muhammad Fadlan
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.15268

Abstract

Obesity is a growing global public health concern that increases the risk of chronic diseases and significantly affects quality of life. Traditional diagnostic methods such as Body Mass Index (BMI) have limitations in accurately representing body fat distribution and individual health conditions. This study aims to comparatively evaluate the performance of various machine learning and neural network models in predicting obesity levels using a multiclass classification approach. The dataset consists of 2,111 observations with 12 predictor variables and seven obesity categories, obtained from a publicly available source. Data preprocessing included duplicate removal, outlier handling using the interquartile range method, feature scaling, and categorical encoding, followed by a 60:20:20 train–validation–test split. Several classifiers were implemented, including Logistic Regression, Support Vector Classifier, Random Forest, Extra Trees, Gradient Boosting-based models (XGBoost and LightGBM), Multilayer Perceptron, K-Nearest Neighbors, and TabNet. Model performance was evaluated using macro-average F1-score and confusion matrix analysis. The results indicate that LightGBM achieved the highest predictive performance with an F1-score of 0.96, demonstrating strong generalization across obesity categories. XGBoost and Random Forest also showed strong performance, while Support Vector Classifier exhibited consistent results across training, validation, and cross-validation. These findings suggest that ensemble-based models are highly effective for obesity classification, while model selection should consider accuracy, interpretability, and computational constraints.
Integrating Geospatial Big Data and Machine Learning for Village Level Rural Urban Classification: Evidence From Toba Regency Br. Saragih, Meilani Thereza; Hartojo, Nurlatifah
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.14159

Abstract

This study aims to develop a data-driven framework for classifying rural and urban areas at the village level in Toba Regency by integrating official statistical data, geospatial big data, and machine learning techniques. The current regional classification still relies on the 2020 baseline and may not adequately reflect recent socio-spatial transformations occurring at finer administrative levels. To address this limitation, this study integrates Village Potential Statistics (PODES) data with spatial indicators derived from big data sources, including population density from WorldPop and the Built-Up Index (BUI) extracted from satellite imagery. The integration of these datasets enables a more comprehensive representation of settlement patterns, spatial development intensity, and demographic distribution across villages. Three supervised machine learning algorithms were implemented to this study: Support Vector Machine (SVM), Naïve Bayes, and Random Forest, with model evaluation using accuracy, precision, recall, and F1-score. The analysis results show that the Random Forest algorithm provides the best performance. Based on the best model, of the 244 villages analyzed, 156 areas were classified as rural and 88 areas as urban. These results indicate a change in status in 47 villages compared to the previous classification. These findings indicate that integrating official statistical data with big data and machine learning methods can capture the dynamics of regional development more adaptively, potentially serving as a complementary approach for compiling regional classifications and formulating more targeted development policies.
Classification of Severe Weather Conditions in Nigeria: An Integrated Weather Database with Machine Learning Approach Olasunkanmi, B.O.; Adekunle, J.D; Oyelakin, S. O.; Obaude, A. M.; Afolabi, C.O.; Oyeniran, M. I.; Ideh, G. E.; Ayanlowo, E. J.; Ogu, C. K.; Robert, C. O.; Sule, H. S.; Anifowoshe, T. J.
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.14302

Abstract

Severe weather events pose significant risks to human safety, infrastructure, and economic activities, particularly in developing regions such as Nigeria, where reliable weather data management and analytical systems remain limited. This study presents an integrated weather data management database and a machine learning–based framework for classifying severe weather conditions using meteorological data from Nigeria. Secondary weather data was obtained from the OpenWeather platform covering the period from February 21st to 27th, 2024. A structured database was designed to store and manage the weather variables, followed by data preprocessing and exploratory statistical analysis. Supervised machine learning models were trained to classify weather conditions into severity categories based on predefined thresholds. Model performance was evaluated using training and testing datasets. Among the evaluated models, the random forest and neural network achieved the highest classification accuracy, while logistic regression showed comparatively lower but stable performance. Although high accuracy values were observed, these results may be influenced by rule-based severity labeling and potential class imbalance. This study demonstrates the feasibility of integrating weather data management systems with machine learning techniques for automated severe weather classification in Nigeria. Future research should incorporate expert-validated severity labels, longer temporal datasets, and external validation to improve generalizability and reduce overfitting risks.
Variable Selection in Clustering for Sanitation Access Analysis in East Java Supporting SDG 6 Purnama, Mohammad Dian
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.14729

Abstract

To have sanitation we need to think about a few things to make people healthy and help the world be a better place. This study is trying to figure out how people in East Java get to use sanitation. We are looking at an important things that help us understand how people use sanitation. We used a method called clustering to see how different cities and districts in East Java are doing. This study utilized a set of six variables, encompassing the five pillars of community-based total sanitation (STBM). The variables employed following the selection process include awareness of open defecation (SBS), awareness of hand washing with soap (CPTM), and drinking water and food management (PAMMRT). The resulting in this study has three distinct clusters, each reflecting different levels of sanitation across cities and districts in East Java. However, the clustering is important to recognize that the excluded variables maintain considerable value as indicators established by the government. Furthermore, to its capacity to implement the variable selection method in the context of clustering, it is anticipated that this research will serve as a valuable resource for policymakers, providing them with a framework to prioritize specific areas in their efforts to enhance sanitation access for the purpose of achieving sustainable development.
Mapping the Evolution of AI Chatbots in Indonesia (2021-2025): A PRISMA-Based Systematic Literature Review on Applications, Technologies, and Impacts Felix, Antonius; Sundjaja, Arta Moro; Sutrisno, Julius; Suryadi, Nanang
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.14942

Abstract

The rapid development of artificial intelligence has accelerated the adoption of chatbots in organizations in Indonesia. But there is no systematic synthesis of the development of this technology in Indonesian context. This research provides a systematic review of the development and implementation of AI chatbots in Indonesia in 2021–2025, with the aim of filling the research gap related to sectoral applications, technological trajectories, and contextual challenges. A systematic literature review was conducted following the PRISMA 2020 guidelines on the Scopus, Google Scholar and arXiv databases to collect 257 initial records. After duplicate removal and a multi-step screening process, 16 high-quality studies were included in the final synthesis. Thematic analysis identified four main findings: (1) AI Chatbots are found in higher education, healthcare, banking, public services, fintech, e-commerce, and SMEs; (2) The technology has evolved from rule-based approaches (AIML, TF-IDF) to machine learning (Seq2Seq LSTM, Rasa+IndoBERT) and the latest large language model integration (GPT-3.5, Vertex AI); (3) Reported impacts include improved user satisfaction (SUS scores 80.1), operational efficiency, and 24/7 service availability; and (4) Existing challenges include accuracy in Indonesian language processing, complexities in system integration, data privacy issues, and varied levels of digital literacy. This review is the first systematic mapping of Indonesia’s AI chatbot landscape and makes evidence-based recommendations for the development of locally-adapted, culturally-sensitive models. Results show that future chatbot development should emphasize Indonesian language datasets and hybrid architectures that combine automation and human oversight.
A Comparative Study of Machine Learning and Stacking Ensemble Models for Diabetes Prediction Jabar, Bakti Amirul; Januario, Albertus; Sanjaya, Davin Miguel; Tanuwijaya, James
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.15332

Abstract

Diabetes is a chronic metabolic disease and increasingly widespread disease around the world and early diagnosis is crucial. Methodology In this study, the performance of three machine learning models (Logistic- Regression, K-Nearest Neighbour (KNN) and Naive Bayes) is reviewed under the task of diabetes classification using Pima Indians Diabetes Dataset. To tackle the class imbalance, we applied imputation, SMOTE for the data pre-processing, and Min-Max Scaling to enhance the prediction performance. Further, we have applied the ensemble learning and stacking, where all the three models have been used as meta classifiers. The results indicate that KNN had the best individual model performance (accuracy 77.27%, AUC 0.8444%) but the stacking ensemble with meta-model being Logistic Regression is superior to any model (accuracy 80.52%, AUC 0.8604%). This suggests that ensemble learning can also improve the accuracy of diabetes diagnosis. These findings demonstrate that combining multiple classification approaches may provide more stable predictions across different patient conditions and clinical attributes In addition the preprocessing stages contributed to reducing noise and improving data consistency before model training The study also highlights the potential use of ensemble-based systems in supporting healthcare professionals during preliminary diabetes screening particularly in environments with limited medical resources and increasing numbers of diabetes cases requiring rapid assessment.
Sentiment and Topic Analysis of Public Opinion on Indonesia’s Minister of Finance Using IndoBERTweet, TF-IDF, and Latent Dirichlet Allocation Sujarwo, Surya; Harefa, Jeklin; Alexander, Alexander
Engineering, MAthematics and Computer Science Journal (EMACS) Vol. 8 No. 1 (2026): EMACS (In Press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/emacsjournal.v8i1.15346

Abstract

In today’s technology-based society, people share their opinions on online social media platforms, which can be used as data for sentiment analysis. One of the most popular platforms for obtaining publicly accessible data is X. This study analyzes public views of the Ministry of Finance (MoF) by examining 9,543 tweets gathered from February to September 2025. The data collected was preprocessed through cleaning, name entities grouping, and keywords filtering, then evaluated using IndoBERTweet, and keywords were extracted using the Term Frequency-Inverse Document Frequency (TF-IDF). For topic modelling, Latent Dirichlet Allocation (LDA) was used, and sentiment distributions were tracked over time through temporal aggregation. To obtain more specific public opinion sentiment analysis, a neutral classification was added to differentiate from the previous studies that used only positive and negative classifications. To support this approach, a pre-trained model with three sentiment classifications was used. The results show that neutral sentiment dominated the tweets followed by negative sentiment then positive sentiment, especially during the transition to the new Ministry of Finance, showing the relevance of real-world events to online public opinion on X. Based on topic trends, public opinion shows the trend change from fiscal policy and leadership to criticism and leadership change.

Page 18 of 19 | Total Record : 181

 15   16   17   18   19 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 8 No. 1 (2026): EMACS (In Press) 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