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
 69   70   71   72   73 
Pendekatan Machine Learning dengan Teknik Stacking untuk Memprediksi Kualitas Air MinumPendekatan Machine Learning dengan Teknik Stacking untuk Memprediksi Kualitas Air Minum D, Ishak Bintang; Andono, Pulung Nurtantio; Pramunendar, Ricardus Anggi; Winarno, Agus; Darmawan, Aditya Aqil
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.7014

Abstract

Safe drinking water quality is essential for public health, yet environmental pollution has significantly degraded its quality. Manual methods such as WQI and STORET are inefficient, prompting this study to propose a machine learning-based classification system for more accurate water potability assessment. The Water Potability dataset from Kaggle is used, consisting of 3,276 samples with nine key parameters. The preprocessing stage includes data imputation, normalization, feature engineering, and oversampling with SMOTE. The applied models include LGBM, Random Forest, GBM, and XGBoost, optimized using Bayesian techniques and stacking ensemble to enhance accuracy. Results show that the stacking ensemble achieves an accuracy of 85.38%, precision of 88.02%, recall of 85.38%, and F1-score of 85.23%, outperforming individual models. This system enables real-time water quality monitoring with faster and more accurate results, supporting decision-making in sanitation policies and clean water availability.
Perbandingan Kinerja Algoritma K-Nearest Neighbors dan Decision Tree untuk Klasifikasi Diabetes Yunianto, Amar Haris; Subhiyakto, Egia Rosi
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6550

Abstract

Diabetes is a chronic metabolic disease that is a major concern in global health due to its increasing prevalence, including in Indonesia, with significant impacts on individual health and health systems. This study aims to compare the performance of K-Nearest Neighbors (KNN) and Decision Tree (DT) algorithms in diabetes classification using the Pima Indians Diabetes Database (PIDD) dataset. Research methods include data collection, pre-processing, missing value handling, outlier detection and handling, and data balancing techniques using Synthetic Minority Oversampling Technique (SMOTE) to overcome class imbalance in the dataset. Model implementation is done by optimizing parameters using GridSearchCV, while performance evaluation is done based on accuracy, precision, recall, and F1 score matrices. The results show that the DT algorithm has superior performance compared to KNN, both without SMOTE and with SMOTE. In the model without SMOTE, DT achieved 85.71% accuracy, while KNN only reached 83.12%. After applying SMOTE, the performance of both algorithms improved significantly, with DT achieving 92% accuracy, 94% precision, 90.38% recall, and 92.16% F1 score, while KNN achieved 91% accuracy, 96.59% recall, and 90.43% F1 score. This study revealed that the use of SMOTE effectively improved the model's performance in handling data imbalance, while the DT algorithm showed better performance stability. These findings are expected to make a significant contribution to the development of more accurate prediction models for diabetes diagnosis, while enriching insights into the application of machine learning in the healthcare field.
Data-Driven Hospitality: Advanced Forecasting Models for Hotel Occupancy Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6611

Abstract

Accurate forecasting of hotel booking demand is essential for resource optimization, revenue maximization, and enhanced customer experience in the hospitality industry. This study evaluates the performance of three forecasting models, ARIMA, Prophet, and LSTM, using historical booking data to identify the most effective approach for predicting demand. The evaluation employed four key metrics: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and R-squared (R²), providing a comprehensive comparison. The results indicate that the LSTM model outperformed the others in prediction accuracy, achieving the lowest MAE (2.71) and MAPE (21.33%), demonstrating its strength in capturing complex patterns. However, its negative R-squared value (-0.20) suggests limitations in explaining overall data variance compared to ARIMA (0.51) and Prophet (0.50). The Prophet model excelled in seasonal decomposition but showed the highest MAPE (71.86%), while ARIMA delivered robust residual diagnostics, adhering well to model assumptions with consistent variance and randomness in residuals. The findings suggest that while LSTM is most effective for short-term forecasting, ARIMA and Prophet provide better interpretability and reliability for long-term trend analysis. A hybrid approach combining the strengths of all three models is recommended to enhance predictive accuracy and robustness. This study provides actionable insights for industry stakeholders seeking to improve decision-making processes and operational efficiency through advanced forecasting techniques.
Implementation Naive Bayes Algorithm in Sentiment Analysis for Netflix Reviews on Google Playstore Mahendra, Aldy; Wijaya, Anugerah Bagus; Arifudin, Dani
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6646

Abstract

Developing technology has had an impact in many ways such as watching a movie, in the past watching a movie had to be through television or cinema media. This resulted in difficulties due to inefficient broadcast schedules, as well as the inability to replay. But unlike the current era, watching movies can be done anywhere and anytime by utilizing a streaming application. One of the existing applications is Netflix, in this application there are many types of movies from all walks of life, not only that the monthly subscription system in this application is relatively cheap. The existing streaming applications are not only Netflix but there are still many other applications, therefore Netflix needs to pay attention to the reviews given by users so that this application continues to grow and is not defeated by other applications. Reviews given by users can be used as evaluation material, to see reviews cannot be seen at a glance but must be detailed. Because there are quite a lot of reviews that manual processes cannot be applied, it is necessary to use a sentiment analysis process and utilize existing algorithms such as data mining. This study aims to conduct sentiment analysis based on user reviews of the Netflix application on the google playstore. The review data of 1,000 was taken by the author and then obtained the results of the research that the reviews given by users tended to be negative and the naïve bayes algorithm got an accuracy level of 82%.
Analisis Sentimen Terhadap Kualitas Pelayanan Aplikasi In-Drive Menggunakan Metode Naive Bayes Classifier Prakoso, Muhammad Sidiq Bagus; Hanif, Isa Faqihuddin
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6682

Abstract

This research analyzes user sentiment towards the service quality of the In-Drive application using the Naive Bayes Classifier method. A total of 15,000 reviews from the Google Play Store were collected using web scraping techniques from the results of sentiment analysis of the data, 9,665 negative sentiments and 5,335 positive sentiments were found. The data went through a pre-processing stage including cleaning, case folding, stopword removal, tokenizing, and stemming. Naive Bayes algorithm was used to classify the reviews into positive and negative sentiments. Evaluation using the confusion matrix resulted in 76.56% accuracy, 78.26% precision, 87.69% recall, and 82.71% F1 score. These results indicate that most reviews are negative. This research is expected to help In-Drive app developers understand user experience and improve service quality based on automatically available reviews.
Perbandingan Performa Arsitektur CNN Terhadap Klasifikasi Tumor Otak Menggunakan Data MRI Saputri, Sekar Dewi Harnum; Lukman, Achmad; Irsan, Muhamad
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6710

Abstract

This study discusses the performance comparison of four Convolutional Neural Network (CNN) architectures in brain tumor classification using histopathology images. CNN has proven its effectiveness in improving the accuracy and efficiency of image-based medical diagnosis. This study compares four popular architectures, namely ResNet, AlexNet, InceptionNet, and VGG12, using a histopathology image dataset with a total of 2,145 images divided into training (70%), validation (15%), and testing (15%) subsets. The results show that the VGG12 model achieves the best accuracy of 98.0%, followed by InceptionNet with an accuracy of 97.3%. The ResNet model achieves an accuracy of 94.3%, while AlexNet has an accuracy of 93.2%. In addition, the VGG12 model shows consistent performance with high precision, recall, and F1-Score values, making it a superior choice for medical applications. This study provides in-depth insights into the advantages and limitations of each CNN architecture, as well as implementation guidelines to support the development of image-based medical diagnosis applications efficiently and accurately.
Penerapan PSO–RU Dalam Algoritma Naive Bayes Untuk Mengatasi Class Imbalance Data Bencana Tanah Longsor Akbar, Zakaria Ihza; Siswa, Taghfirul Azhima Yoga
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6888

Abstract

Abstract−Landslides are one of the most significant natural disasters in Indonesia, often causing substantial economic losses and threats to human safety. A key challenge in processing landslide data is the issue of class imbalance, where the number of disaster occurrence data is significantly smaller compared to non-disaster data. This study aims to improve landslide prediction accuracy by integrating the Naive Bayes algorithm and Particle Swarm Optimization (PSO) while employing the Random Undersampling (RU) technique to address data imbalance. The dataset used in this study includes landslide data from Samarinda City for the period 2022-2023, obtained from the Regional Disaster Management Agency (BPBD) and the Meteorology, Climatology, and Geophysics Agency (BMKG). The research process involved data preprocessing, balancing data using RU, implementing the Naive Bayes algorithm, and optimizing it with PSO. Model performance was evaluated using the 10-Fold Cross Validation technique and a confusion matrix. The results show that applying the Naive Bayes algorithm with PSO optimization without RU achieved the highest average accuracy of 89.49%, compared to Naive Bayes without optimization, which only reached 87.59%. Meanwhile, the application of RU showed varied effects, with the combination of Naive Bayes + PSO with RU achieving an average accuracy of 50%, slightly better than Naive Bayes with RU, which only reached 45%. This study demonstrates that PSO optimization can improve the performance of the Naive Bayes model in handling complex landslide datasets, although balancing techniques such as RU must be applied cautiously to avoid the loss of important information. The results of this study are expected to support disaster mitigation efforts through more accurate predictions, aiding stakeholders in decision-making, such as early evacuation planning and infrastructure development in landslide-prone areas.
A Prediksi Rekomendasi Pemilihan Kejuruan pada Sekolah Menengah Kejuruan Menggunakan Perbandingan Metode Decision Tree C4.5 dan Naïve Bayes Windari, Ratih; Nugroho, Handoyo Widi
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6928

Abstract

SMK Negeri 4 Bandar Lampung faces challenges in assisting students in selecting a major that aligns with their potential, interests, and abilities. The decision-making process for choosing a major is often influenced by subjective factors that lack transparency and may not be entirely accurate. Therefore, a system is needed to provide more accurate and objective recommendations. This study develops a predictive system for major selection at SMK Negeri 4 Bandar Lampung using two methods: the Decision Tree C4.5 algorithm and the Naïve Bayes algorithm. The system utilizes seven key attributes as predictive variables, including mathematics scores, English scores, science (IPA) scores, Indonesian language scores, academic achievements, participation in extracurricular activities, and color blindness condition. The study findings indicate that the C4.5 algorithm achieves an accuracy of 84.46%, whereas the Naïve Bayes algorithm outperforms it with an accuracy of 92.23%. This suggests that the Naïve Bayes algorithm is more effective for this application. Nevertheless, both methods still have limitations that can be improved through parameter optimization and more in-depth data processing. The implementation of this data-driven system is expected to enhance the efficiency of providing more relevant major recommendations at SMK Negeri 4 Bandar Lampung and serve as an inspiration for other schools to adopt similar approaches to improve education quality.
Penerapan CNN dan RNN untuk Pembuatan Deskripsi Konten Visual Menggunakan Deep Learning Hermanto, Aldy Agil; Karyono, Giat; Tahyudin, Imam
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6958

Abstract

The development of technology in the field of image and sound processing has had a significant impact on increasing the accessibility of information for various groups, especially for individuals with visual impairments. One of the innovations that emerged was the image to speech system, which allows the conversion of images into sounds that can be understood by its users. The main problem lies in the low accuracy of object recognition in images with high variability, such as poor lighting or complex backgrounds, as well as the challenge of producing suitable text descriptions to be converted into audio. The method used involves extracting image features using InceptionV3-based CNN and forming a sequence of descriptive texts through RNN with an attention mechanism. The dataset consists of 40,455 captions and 8,091 images, processed using text and image pre-processing techniques before being trained using the teacher forcing technique. The evaluation results show a very low BLEU score (5.154827976372712e-153), indicating the model's inability to replicate the original caption well. However, the audio from the text-to-speech conversion using Google Text-to-Speech is quite clear. Future solutions include increasing the dataset, applying regularization, and adjusting the model architecture to improve the accuracy of caption prediction and audio relevance to the image. With these improvements, it is hoped that the system can provide more inclusive visual information accessibility for individuals with visual impairments.
Verifikasi Kesesuaian Materi Pembelajaran Menggunakan Model Bidirectional Encoder Representations from Transformers (BERT) dan Semantic Textual Similarity Abadi, Riani Saputri
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6967

Abstract

The challenge in the education domain is ensuring that learning can be evaluated effectively and in a structured manner to improve and strengthen the quality of education standards in achieving optimal learning. In this study, an implementation was carried out to evaluate learning outcomes based on Natural Language Processing using BERT (IndoBERT) and Cosine similarity to assess the consistency and accuracy of learning materials with BAKP and RPS. IndoBERT is used to extract embedding vectors as contextual semantic representations from documents, and the similarity level is calculated using Cosine Similarity between the contents of BAKP and RPS to ensure the achievement of learning objectives. The research methodology consists of data collection, pre-processing, tokenization, and sentence embedding using IndoBERT, calculating the similarity level, and evaluating model performance. The results showed that implementing the IndoBERT model produced a good level of similarity with a value above the threshold, which was 0.50, with a Cosine Similarity result of 0.674 and a performance evaluation of 100%. This approach can provide the potential for automation of the higher education quality assurance process for academic evaluation based on BAKP and RPS so that learning materials are always relevant and updated with industry needs.

Page 71 of 93 | Total Record : 926

 69   70   71   72   73 

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