cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
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
 88   89   90   91   92 
Klasifikasi Text Dokumen Web Berbasis Supervised Learning Sebagai Pemodelan Aplikasi Pembelajaran Kebudayaan Melayu di Indonesia Mustakim, Mustakim; Salisah, Febi Nur; Suryani, Suryani
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8499

Abstract

Indonesia, as the largest archipelagic country, is home to diverse cultures, including Malay culture in Riau Province. The website features numerous text documents, including articles, news, and personal documents, uploaded by members of the cultural community. This study aims to support the preservation of Malay culture through technology by implementing a digital learning system based on Machine Learning. Previous research has identified weaknesses in the application of intelligent systems and machine learning algorithms. This study tests five classification algorithms Random Forest, SVM, Naïve Bayes, KNN, and PNN to improve the system's accuracy and performance. The results show that Random Forest achieved the highest accuracy of 91.17%, followed by KNN at 88.23%, SVM and NBC at 82.35%, and PNN at 76.47%. The developed Digital Learning System (DLS) received positive feedback, with a User Acceptance Test (UAT) score of 86% and a 100% success rate in Blackbox testing, demonstrating stable performance across various devices. This research introduces a new innovation in Malay cultural preservation applications, utilizing Machine Learning algorithms to enhance both accuracy and functionality.
Credit Card Fraud Detection Using Support Vector Machine: A Study on Data Balancing Strategies Hasibuan, Lailan Sahrina
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8514

Abstract

The rise in credit card transactions has been accompanied by an increase in fraudulent activities. One of the key challenges in detecting fraud is the distribution of the dataset, where fraudulent transactions are significantly outnumbered by normal ones. Despite their low occurrence, fraudulent transactions have a significant impact on the banking sector. Therefore, an effective model is needed to identify and estimate fraudulent transactions. This study aims to generate optimal training dataset from an imbalanced one using Adaptive Synthetic Sampling (ADASYN) to enhance the training process of Support Vector Machine (SVM) model. The dataset used consists of anonymized credit card transactions and labeled as either fraudulent or normal, sourced from the Kaggle dataset. It contains transactions made by European cardholders in September 2013, covering a two-day period with 492 fraud cases out of 284,807 transactions. Three datasets were derived from the original: raw, balanced, and support vector-based balanced. The SVM model training on these datasets resulted in sensitivities of 0.39, 0.64, and 0.70, respectively, while the precision values were 0.92, 0.72, and 0.01. The corresponding f-measure values were 0.55, 0.68, and 0.02. The best performance based on the f-measure was achieved using the balanced version of the raw dataset.
Analisis Perbandingan Metode Teorema Bayes, Case-Based Reasoning, dan Dempster-Shafer untuk Mendiagnosis Penyakit Lambung Sudarsono, Bernadus Gunawan; Lestari, Dwi
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8524

Abstract

Gastric diseases, such as gastritis, GERD, and peptic ulcers, are significant health problems with high prevalence in the community. The process of diagnosing these diseases is often hampered by symptoms that overlap with other health disorders, limited experience of medical personnel, and incomplete patient symptom data. This condition can lead to misdiagnosis and ineffective treatment. Therefore, a system is needed that can support the diagnosis process more accurately and efficiently. This study compares three intelligent system-based diagnostic methods, namely Bayes' Theorem, Case-Based Reasoning (CBR), and Dempster-Shafer Theory. Bayes' Theorem analyzes the probability of the relationship between symptoms and diseases, CBR compares new cases with previous cases, while Dempster-Shafer Theory handles data uncertainty to produce a level of diagnostic confidence. The analysis was carried out using gastric disease symptom data that has been collected from the literature and medical surveys. This study contributes by presenting a comparative analysis of the advantages and disadvantages of each method in diagnosing gastric disease. The aim is to determine the most effective method in improving diagnostic accuracy and the efficiency of the medical decision-making process. The preliminary results show a comparison between Bayes' Theorem, Case-Based Reasoning, and Dempster Shafer showing that Gastroesophageal Reflux Disease has the highest confidence level, followed by Gastritis, while Gastric Ulcer has the lowest confidence level in all methods.
Comparison of MOOSRA and MOORA Methods in the Decision Support System for the Selection of Outstanding Students Rahayu, Eka Fitri; Lestari, Octarina Budi; Syafrudin, Syarifah Azharina; Wahyuni, Indah; Setyasih, Dwi
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8572

Abstract

Outstanding student is a student activity in every achievement of high performance in the form of curricular, co-curricular or extracurricular to choose and give an award. In both public and private universities, they select outstanding students using a decision support system. A decision support system is a computer-based system that produces information in solving a problem to support or encourage a decision-making process in a semi-structured and unstructured situation. To solve the problem in this case, the decision support system applies the MOOSRA (Multi-objective Optimization on the Basis of Simple Ratio Analysis) and MOORA (Multi-objective Optimization on the Basis of Ratio Analysis) methods. The author has prepared seven alternative data and seven criteria data along with the weighting using the ROC (Rank Order Centroid) method. From the calculation of the two methods, the highest alternative results are different. From the calculation of the MOOSRA method, the highest alternative was obtained, namely Rohan (A6) with a final preference value of 66.7937, while for the calculation of the MOORA method, the highest alternative was obtained, namely Khairunisa (A4) with a final preference value of 0.3955.
Student Class Grouping in Junior High Schools Based on Academic Performance Using the Fuzzy C-Means Method Bustomi, Tommy; Hasiholan, Jundro Daud; Harianto, Kusno
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8585

Abstract

Abstrak−Differences in academic abilities among junior high school students often pose a challenge for schools in conducting class groupings objectively and efficiently. Many educational institutions, including SMP Negeri Y, still rely on manual grouping methods that are subjective and do not accurately reflect the actual conditions of students. Inaccurate grouping may lead to imbalanced learning processes, where students with high and low academic abilities are placed in the same group without considering their performance variations. Therefore, a data-driven approach is needed to represent student characteristics comprehensively and flexibly. This study aims to apply the Fuzzy C-Means (FCM) method to cluster students of SMP Negeri Y based on four main attributes: Academic Average, Attitude Score, Activeness Score, and Attendance. The FCM method was chosen for its ability to handle data uncertainty and assign multiple membership degrees to each student across different clusters. Prior to clustering, the data underwent a preprocessing stage involving data cleaning, normalization using StandardScaler, and scale adjustment across attributes to improve the accuracy of Euclidean distance calculations. The analysis results revealed the formation of two main clusters representing student academic performance levels. Cluster 0 has an average academic score of 78.37 with moderate attitude and activeness levels, while Cluster 1 shows a higher academic average of 82.18 accompanied by better attitude, activeness, and attendance scores. Based on the highest membership degree, 38 students were assigned to Cluster 0 and 26 students to Cluster 1. Model evaluation using Fuzzy Partition Coefficient (FPC), Modified Partition Coefficient (MPC), and Silhouette Score indicated the optimal configuration at a fuzziness level of m = 2, yielding FPC = 0.680, MPC = 0.359, and Silhouette Score = 0.334. These findings demonstrate that FCM is effective in representing variations in student abilities more realistically, while also providing an objective foundation for schools to design adaptive learning strategies and implement data-driven academic policies.
Comparative Performance Analysis of Long Short-Term Memory (LSTM) and Support Vector Regression (SVR) Algorithms in Gold Price Prediction Lailiyah, Siti; Yunita, Yunita; Ekawati, Hanifah
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8605

Abstract

Gold is one of the most important investment commodities in the global financial system, widely recognized for its role as a safe-haven asset and its ability to preserve value during periods of inflation, economic instability, and geopolitical uncertainty. Despite its relative stability compared to other financial instruments, gold prices exhibit significant volatility driven by various macroeconomic factors, including exchange rate movements, inflation dynamics, global monetary policy decisions, and market sentiment. As a result, accurate gold price prediction remains a critical challenge for investors, financial analysts, and policymakers. This study aims to conduct a comparative performance analysis of two machine learning algorithms, namely Long Short-Term Memory (LSTM) and Support Vector Regression (SVR), in predicting gold prices represented by the XAU/USD currency pair. The research utilizes daily historical gold price data from 2004 to 2025 obtained from the Kaggle platform. The dataset includes key financial attributes such as Open, High, Low, Close prices, and trading Volume. Data preprocessing steps involve data cleaning, chronological sorting, handling missing values through linear interpolation, feature selection, and normalization using the Min-Max scaling technique. The dataset is then divided sequentially into training and testing sets with an 80:20 ratio to preserve temporal dependencies. The LSTM model is designed to capture long-term temporal patterns using the closing price as a time series input, while the SVR model leverages multiple input features to model non-linear relationships through kernel-based regression. Model performance is evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The experimental results demonstrate that the LSTM model outperforms the SVR model across all evaluation metrics. The LSTM achieved an RMSE of 0.0082, an MAE of 0.0060, and an R² value of 0.9969, indicating a very high level of predictive accuracy and strong generalization capability. In contrast, the SVR model recorded an RMSE of 0.0289, an MAE of 0.0143, and an R² of 0.9611, reflecting lower precision, particularly during periods of high price volatility. These findings confirm that LSTM is more effective in capturing complex temporal dependencies and non-linear dynamics inherent in gold price time series data. Consequently, LSTM is recommended as a superior approach for long-term gold price forecasting, while SVR may serve as a complementary or baseline predictive model in financial time series analysis.
Perbandingan Metode Certainty Factor dan Dempster-Shafer dalam Sistem Pakar Diagnosa Penyakit THT Subekthi, Errysa
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8623

Abstract

The diagnosis of Ear, Nose, and Throat (ENT) diseases often encounters difficulties in determining the level of certainty of a disease based on the symptoms experienced by the patient. The main issue in this study is how to compare the accuracy levels between the Certainty Factor and Dempster-Shafer methods in expert systems for diagnosing ENT diseases. As a solution, this research applies both methods and analyzes their computational results based on various symptoms entered by patients. The objective of this study is to identify which method is more effective in providing diagnostic certainty. The findings indicate that the Certainty Factor method produces a higher level of certainty compared to the Dempster-Shafer method — for instance, in the case of tonsillitis, achieving 94.68% compared to only 0.02% with Dempster-Shafer. Therefore, the Certainty Factor method is recommended for use in expert systems for ENT disease diagnosis. This study contributes to enhancing understanding of the application of artificial intelligence methods in the medical field, particularly in improving the accuracy of expert systems to assist healthcare professionals in diagnostic decision-making processes.
Investment Decision-Making for High-Potential Startups in the Digital Economy Using AHP and VIKOR Salmon, Salmon; Rahmadani, Rizki Galang; Harpad, Bartolomius
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8633

Abstract

The rapid growth of the digital economy has driven the emergence of numerous startup companies that play a vital role as catalysts for innovation and business transformation in the modern era. However, the increasing number of startups poses a major challenge for investors in selecting the most potential and profitable investment opportunities. The main problem lies in the multi-criteria evaluation process, which involves various aspects such as market potential, product innovation, business model, team performance, and financial stability. To address this complexity, this study applies a combination of the Analytical Hierarchy Process (AHP) and VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) methods as an objective and measurable multi-criteria decision-making approach. The AHP method is utilized to determine the priority weights of each criterion through a pairwise comparison process. The results show that market potential (C1) is the most dominant criterion with a weight of 0.458, followed by product innovation (C2) with a weight of 0.247, and business model (C3) with a weight of 0.144. Meanwhile, team performance (C4) and financial stability (C5) have relatively lower weights of 0.105 and 0.046, respectively. These findings indicate that market and innovation aspects are the primary factors influencing startup investment feasibility. Furthermore, the VIKOR method is employed to rank the alternatives based on compromise solutions toward the ideal outcome. The results reveal that startup A17 has the lowest compromise value (Q = 0.0000), making it the most optimal investment alternative, followed by A4 (Q = 0.0303) and A19 (Q = 0.0586). This study demonstrates that the combination of AHP and VIKOR methods provides a comprehensive, objective, and consistent analysis in the decision-making process for digital startup investments. The proposed approach assists investors in evaluating startups more systematically and accurately based on the priority of relevant criteria in the context of the dynamic digital economy. Therefore, a decision support system based on the AHP-VIKOR method can serve as an effective solution for decision-makers to identify and select the most promising startups for future development.
Naïve Bayes Optimization for Visual Ergonomics Prediction in Smartphone Display Mode Pambudi, Rizkha Tegar; Wibowo, Agung
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8665

Abstract

Smartphone display modes (dark mode and light mode) play an important role in visual comfort, especially in relation to the risk of digital eye strain due to intensity of use and lighting conditions. This study aims to optimize the Naïve Bayes algorithm to predict display mode preferences based on users' visual ergonomics factors. Data were collected through an online survey of 283 smartphone users using purposive and convenience sampling. Seven variables were used as features, namely age, gender, duration of use, dominant time of use, purpose of use, screen type, and lighting conditions, with display mode preference as the target label. The study built two models, namely the baseline Naïve Bayes and the optimal model. Optimization was carried out by balancing the data with the Synthetic Minority Oversampling Technique for Nominal (SMOTEN) and adjusting the alpha hyperparameter using GridSearchCV. The evaluation results showed that the baseline model achieved an accuracy of 68.42% with a light mode class recall of 0.57. After optimization, the accuracy increased to 70.18% and the light mode recall rose to 0.71, indicating an improvement in the model's ability to recognize minority classes and reduce prediction bias. This study shows that SMOTEN optimization and hyperparameter tuning effectively improve the model's sensitivity to user preferences and have the potential to support the development of adaptive interfaces that automatically adjust the display mode to improve user visual comfort.
Comprehensive Benchmark of Yolov11n, SSD MobileNet, CenterFace, Yunet, FastMtCnn, HaarCascade, and LBP for Face Detection in Video Based Driver Drowsiness Go, Agnestia Agustine Djoenaidi; Alzami, Farrikh; Naufal, Muhammad; Azies, Harun Al; Winarno, Sri; Pramunendar, Ricardus Anggi; Megantara, Rama Aria; Maulana, Isa Iant; Arif, Mohammad
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8678

Abstract

Face detection is a critical foundation of video-based drowsiness monitoring systems because all downstream tasks such as eye-closure estimation, yawning detection, and head movement analysis depend entirely on correctly identifying the face region. Many previous studies rely on detector-generated outputs as ground truth, which can introduce bias and inflate model performance . To avoid this limitation, I manually constructed a ground truth dataset using 1,229 frames extracted from 129 yawning and microsleep videos in the NITYMED dataset. Ten representative frames were sampled from each video using a face-guided extraction script, and all frames were manually annotated in Roboflow following the COCO format to ensure accurate bounding box labeling under varying lighting, head poses, and facial deformation. Using this manually annotated dataset, I conducted a comprehensive benchmark of seven face-detection algorithms: YOLOv11n, SSD MobileNet, CenterFace, YuNet, FastMtCnn, HaarCascade, and LBP. The evaluation focused on localization quality using Intersection over Union (IoU ≥ 0.5) and Dice Similarity, allowing each algorithm’s predicted bounding box to be directly compared against human defined ground truth. The results show that HaarCascade achieved the highest IoU and Dice scores, particularly in frontal and well-lit frames. FastMtCnn also produced strong alignment with a high number of correctly matched frames. CenterFace and SSD MobileNet demonstrated smooth bounding box fitting with competitive Dice scores, while YOLOv11n and YuNet delivered moderate but stable performance across most samples. LBP showed the weakest results, mainly due to its sensitivity to lighting variations and soft-texture regions. Overall, this benchmark provides an unbiased and comprehensive comparison of modern and classical face-detection algorithms for video-based driver-drowsiness applications.

Page 90 of 93 | Total Record : 926

 88   89   90   91   92 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue