cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 926 Documents
Best Programming Creator Content Selection with K-Means Clustering Algorithm and MAUT Method Aryunani, Witari; Setiani, Yeni; Purnama, Indra
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7310

Abstract

Selecting quality programming content creators on platforms such as YouTube is becoming a complex challenge as digital educational content expands. This research designs a systematic approach by combining K-Means algorithm and MAUT method to objectively evaluate and rank creators. Data from 100 programming channels was analysed using K-Means, resulting in three main clusters based on audience views and interactions. The leading cluster was identified with an average of 335,461 views per video and an engagement rate of 0.31%. The MAUT method then ranked the creators in this cluster, revealing Brackeys as the best programming contentcreator with an optimal balance between audience reach and participation with a final score of 0.624. The results show that the integration of these two methods is effective in providing a data-driven solution for educational content selection, as well as a reference for creators in improving the quality of the material. The combination of K-Means and MAUT not only answers the need for objectivity in content curation, but also enriches the literacy of multidimensional evaluation methods in the era of online learning.
Prediction of Student Work Readiness using Artificial Neural Network and Decision Tree Andini, Bilqiis Shahieza; Lhaksmana, Kemas Muslim
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7316

Abstract

The readiness of students for the workforce is a critical metric in evaluating the quality of higher education. Forecasting students' work readiness before their entrance into the industry calls for a data-driven approach since they often lack the necessary skills and experience until graduation. Using two machine learning techniques—Artificial Neural Network (ANN) and Decision Tree (DT)—this research aims to create a classification model to predict students' employment readiness. Among the several aspects the data covers are academic knowledge, professional attitude, soft skills, hard skills, and socio-economic background. Data preparation, data cleansing, feature selection, model training, and performance evaluation make up the study approach. The ANN model comprised four hidden layers, while the DT was refined with RandomizedSearchCV. The test results showed that DT had an accuracy of 90.80%, and ANN had 90.69%, indicating that both performed very well and can be selected based on what the user needs most. This research contributes a predictive model for educational institutions to assess students' employment preparedness in a more objective and systematic way.
Studi Perbandingan Metode Dempster-Shafer dan Teorema Bayes dalam Sistem Pakar Diagnosa Penyakit Sistem Pernapasan Kusmanto, Kusmanto; Esabella, Shinta; Karim, Abdul; Bobbi Kurniawan Nasution, Muhammad; Hidayatullah, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7317

Abstract

Respiratory system disease diagnosis often faces challenges in ensuring the accuracy of results due to the complexity of overlapping symptoms. In particular, a method is needed that is able to handle data uncertainty and utilize existing evidence optimally. This study aims to compare two methods, namely Bayes' Theorem and Dempster-Shafer, in diagnosing three types of respiratory diseases: Asthma, Tuberculosis, and Bronchitis. The solution is done by analyzing the percentage of confidence produced by each method based on symptom data. The results show that Bayes' Theorem produces the highest confidence for Tuberculosis (74.92%), while Dempster-Shafer provides the highest confidence for Bronchitis (80%). This comparison indicates that the selection of methods must be adjusted to the characteristics of the data and the needs of the analysis. This study contributes to providing insight into the advantages and disadvantages of each method, which can be used as a reference in developing a more accurate disease diagnosis decision support system.
Penerapan Data Mining Untuk Analisis Sentimen Masyarakat Terhadap Ibu Kota Nusantara Pada Media Sosial X Rayean, Rival Valentino; Afdal, M; Permana, Inggih; Rozanda, Nesdi Evrilyan
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7318

Abstract

The policy of relocating the National Capital City to Nusantara (IKN) has become a viral and hotly debated issue in Indonesia, triggering diverse public reactions ranging from support to opposition. To understand the dynamics of this public sentiment, this research analyzed user responses from the social media platform X. A total of 1000 tweet data were collected, equally divided into 500 tweets before and 500 tweets after Indonesia's 2024 Independence Day ceremony. These tweet data were then manually labeled and classified for sentiment analysis using Naive Bayes and Random Forest data mining algorithms, with the SMOTE technique applied to address data class imbalance. The analysis results showed that before the Independence Day ceremony, sentiment towards the National Capital City to Nusantara (IKN) was dominated by 44% negative tweets (219 data points), followed by 30% positive (151 data points), and 26% neutral (130 data points). Post-ceremony, negative sentiment significantly increased to 50% (252 data points), while positive sentiment slightly rose to 33% (165 data points), and neutral sentiment decreased to 17% (83 data points). In model performance evaluation, the Random Forest algorithm demonstrated higher classification accuracy compared to Naive Bayes. Nevertheless, the accuracy difference between the two algorithms was relatively small, indicating that both were quite effective for sentiment analysis on this research dataset. This study successfully presents a comprehensive overview of the dynamics and polarity of public opinion on social media X regarding the ongoing policy of relocating the National Capital City to Nusantara.
Clustering the Economic Conditions of Various Countries From 2010-2023 by Conducting A Comparative Analysis of the K-Means and K-Medoids Algorithms Yunita, Yunita; Ekawati, Hanifah; Yusnita, Amelia
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7330

Abstract

Understanding the similarities and differences in economic conditions across countries is crucial for various stakeholders. This research investigates the global economic landscape by clustering countries based on their economic indicators, including GDP, inflation rate, unemployment rate, and economic growth, spanning the period of 2010 to 2023. This timeframe encompasses significant global economic events, making it pertinent for analysis. The study employs and compares two prominent clustering algorithms: K-Means and K-Medoids, to identify groups of countries exhibiting similar economic patterns. Utilizing secondary data from Kaggle encompassing 19 countries, the research assesses the ability of each algorithm to delineate meaningful economic clusters. The K-Means algorithm, with a determined optimal number of four clusters, demonstrated a reasonably good cluster separation and moderate internal cohesion, evidenced by a Silhouette Coefficient of 0.58 and a Davies-Bouldin Index of 0.63. In contrast, the K-Medoids algorithm yielded a distinct clustering structure with a lower Silhouette Coefficient (0.26) and a higher Davies-Bouldin Index (1.16), suggesting less distinct cluster separation and potential sensitivity to data characteristics. This comparative analysis provides insights into the applicability and performance of K-Means and K-Medoids in discerning global economic structures, contributing to a deeper understanding of the world economic map and the utility of clustering techniques in economic data analysis.
Sistem Deteksi Gas Pintar Berbasis IoT dan Terintegrasi Fuzzy-Logic untuk Keamanan Distribusi Gas secara Realtime Azizah, Putri Nur; Taqwa, Ahmad; Salamah, Irma
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7331

Abstract

Abstract−LPG gas is a widely used fuel for daily needs in households, industry, and commercial sectors. Although easy to use and affordable, LPG contains highly flammable compounds that can cause fires and explosions, especially if leaks go undetected. Field surveys show that most gas agents or depots still use manual methods relying on the sense of smell to detect gas leaks. This approach does not provide optimal or accurate results, making it ineffective and potentially harmful to health when excessive gas is inhaled. Therefore, this research aims to design a gas leak detection system based on the Internet of Things (IoT) using the Fuzzy Tsukamoto algorithm integrated with the Blynk application. The method involves the design of hardware and software using three sensors as input parameters: MQ-6 (gas), DHT22 (temperature), and Flame Sensor (fire), which are processed by the ESP32 microcontroller through fuzzy logic rules. The system outputs include a visual LED indicator, buzzer activation, status display on the LCD, notifications via Blynk, and automatic fan response to neutralize the gas. Based on results simulation and testing under three environmental condition scenarios, the system is able to detect gas leaks with average error of 0.315% and accuracy of 90.55%. This study demonstrates a reliable, effective, and responsive gas leak detection system. It is expected that the system can minimize the potential dangers of gas leaks and enhance gas storage safety.
Analisis Sentimen Ulasan Mobile JKN pada Playstore dengan Perbandingan Akurasi Algoritma Naïve Bayes dan SVM Pranata, Eka Arya; Budiman, Fikri; Kurniawan, Defri
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7334

Abstract

The facilities provided by BPJS Health by releasing the Mobile JKN application, with this application the administrative process that previously had to be done directly can be done online and more flexibly. This research aims to see the sentiment of the community towards the JKN Mobile application review by comparing the SVM and Naïve Bayes algorithms. As well as optimizing the Naïve Bayes algorithm by using grid search. Reviews are taken from Google play with the help of Google Play Scraper API, the dataset taken amounted to 7,000 reviews. The results of using Naïve Bayes with an accuracy value of 86%, after tuning optimization using Grid Search significantly increases the accuracy value of the Naïve Bayes algorithm to 91% and for the SVM algorithm has an accuracy value of 92%. From the trial, it was found that the SVM algorithm is still better than the Naïve Bayes algorithm even though it has been optimized, but by optimizing the accuracy value Naïve Bayes is closer to SVM performance. This research can provide insight into the comparison of the two algorithms in identifying JKN Mobile reviews and the need for optimization to improve the performance of algorithms in sentiment analysis, besides that this research also contributes to the improvement and development of the JKN Mobile application so that it is useful for the community.
Analisis Perbandingan Akurasi Model EfficientNetB0 dan Vision Transformer Dalam Klasifikasi Citra Motif Batik Giriloyo Sari, Ratna Puspita; Chandra, Albert Yakobus
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7343

Abstract

Batik is a cultural heritage owned by Indonesia and has been inaugurated by UNESCO on October 2, 2009. In this digital era, the variety of batik motifs must be preserved, especially in Giriloyo Batik Village located in Karang Kulon, Wukirsari, Imogiri Sub-district, Bantul. The complexity and diversity of batik motifs in the area require a modern technological approach to assist the accurate classification process. This study aims to compare the performance of the two current models, EfficientNetB0 and Vision Transformer, in classifying five classic batik motifs in Kampung Batik Giriloyo. This research method combines deep learning approach based on Convolutional Neural Network (CNN) and Transformer with training process from zero without transfer learning. The research stages used include dataset collection, prepocessing, augmentation, model building and training, evaluation and visualization of result comparison. Evaluation is done using accuracy, precision, recall, F1-score and inference time efficiency metrics. The final dataset amounted to 13,128 sliced batik images. The dataset is then divided into 3 main parts, namely training data by 80%, validation data by 10% and testing data by 10% of the total dataset. The final results showed that Vision Transformer achieved the best performance with testing accuracy reaching 99.85 and the EfficientNetB0 model gave an accuracy of 98.78% with stable efficiency. This research confirms that the Vision Transformer model is superior in extracting global patterns in complex batik motifs. This research also makes a real contribution to the utilization of artificial intelligence in cultural preservation through the classification of digital batik motifs and the development of a classic batik motif classification system in Giriloyo Batik Village.
Determining the Country with the Best Economic Conditions 2025 using the MCDM Method Harpad, Bartolomius; Azahari, Azahari; Salmon, Salmon
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7346

Abstract

In the midst of increasingly complex global challenges in 2025, evaluating a country's economic condition is an important element in supporting strategic decision-making, whether at the government, corporate or individual level. The diversity of economic indicators such as Gross Domestic Product (GDP), inflation, unemployment, and human development index often makes it difficult to make an objective and comprehensive assessment. Reliance on a single indicator tends to produce a biased and unrepresentative picture. To address these issues, this research adopts a Multi-Criteria Decision Making (MCDM) approach that is able to consider various economic aspects simultaneously and systematically. The three MCDM methods used in this study are TOPSIS, VIKOR, and COCOSO. The analysis was conducted on 19 countries using four main indicators, namely GDP in billion USD, inflation rate, unemployment rate, and economic growth rate. Based on the results of data processing, the USA occupies the top position as the country with the best economic performance, followed by China. The three methods show consistency in ranking some countries, but there are also striking differences for some alternatives due to different approaches in normalisation and weighting. These findings emphasise the importance of choosing the right method in multicriteria evaluation. Therefore, a combined approach such as ensemble decision-making is recommended to strengthen the validity of the results. For further development, the use of additional indicators and the integration of artificial intelligence-based technology are suggested to improve accuracy and flexibility in analysing economic conditions between countries.
Analisis Kinerja Algoritma Machine Learning Untuk Klasifikasi Potensi FRAUD Klaim Layanan Kesehatan Rumah Sakit Ubed, Imanullah Ali; Syarif, Iwan; Saputra, Ferry Astika
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7349

Abstract

Fraud in healthcare claims represents a critical challenge that undermines the efficiency and sustainability of Indonesia's National Health Insurance (JKN) system. This study contributes a large-scale comparative evaluation of five machine learning algorithms for classifying potential fraud in BPJS Kesehatan claims, namely Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), XGBoost + SMOTE, and Logistic Regression (LR). A novelty of this study lies in applying the SMOTE technique in conjunction with XGBoost to address class imbalance in fraud datasets. The dataset consists of over 200,000 claim entries, which have undergone data cleaning, normalization, and feature selection. Performance was assessed using precision, recall on fraud class (positive), f1-score, accuracy, and confusion matrix visualizations to capture classification error distribution. Results demonstrate that ANN and XGBoost + SMOTE are superior in detecting fraudulent claims with high recall, while SVM achieves the most balanced performance in terms of precision and sensitivity. Random Forest and Logistic Regression serve as moderate baselines but are less effective in identifying complex fraud patterns. This study contributes to the development of a more adaptive and efficient fraud detection system based on machine learning, with practical implications for strengthening the automatic verification system used by BPJS Kesehatan.