cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Nelly Khairani Daulay
Contact Email
nellykhairanilestari@gmail.com
Phone
+6282370070808
Journal Mail Official
mesran.skom.mkom@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Artificial Intelligence
Published by CV. Graha Mitra Edukasi
ISSN : -     EISSN : 29623944     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
The field of study of the Bulletin of Artificial Intelligence journal, in the field of Artificial Intelligence, includes: 1) Decision Support Systems, 2) Data Mining, 3) Expert Systems, 4) Big Data, 5) Text Mining, and 6) Natural Language Processing. But does not rule out the possibility of publishing manuscripts in the field of Computer Science.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 37 Documents
 1   2   3   4 
Persepsi Pengguna terhadap Penggunaan AI dalam Kehidupan Sehari-hari Pendekatan Technology Acceptance Model (TAM) Sutrita Br Situmeang; Amelia Khairani; Rizkah Fadillah
Bulletin of Artificial Intelligence Vol 4 No 2 (2025): October 2025
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v4i2.235

Abstract

The development of Artificial Intelligence (AI) technology has brought significant changes to various aspects of daily life, including information search, digital services, education, and social interaction. The presence of AI provides convenience, speed, and efficiency in completing various activities. However, the level of acceptance and utilization of AI within society still varies, influenced by users’ perceptions of ease of use, perceived benefits, and trust in the accuracy of information generated by AI. This study aims to analyze users’ perceptions and levels of acceptance of AI usage in everyday life in Indonesia using the Technology Acceptance Model (TAM) approach. The research method employed is descriptive quantitative, with data collected through a five-point Likert scale questionnaire. The questionnaire was distributed online to 35 respondents who had experience using AI technology. The variables analyzed include Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Attitude Toward Using (ATU), Behavioral Intention to Use (BI), and Actual Use (AU). The results of the validity test indicate that all questionnaire items are valid, with calculated r-values greater than the r-table value of 0.334, while the reliability test produced a Cronbach’s Alpha value of 1.03, indicating that the research instrument has a very high level of internal consistency. Descriptive analysis shows that the PEOU variable achieved a percentage of 65%, PU 78%, ATU 72%, AU 75%, and BI 68%. These results indicate that respondents generally have positive perceptions toward the use of AI, particularly in terms of perceived usefulness and ease of use. These positive perceptions influence users’ attitudes, intentions to use, and actual use of AI in daily activities. Therefore, this study demonstrates that AI is well accepted by users and has strong potential to effectively support everyday activities.
Prediksi Magnitudo Gempa Indonesia Menggunakan Machine Learning Berbasis Data Seismik Farizi Ilham; Halili Maar; Dimas Lendesi
Bulletin of Artificial Intelligence Vol 5 No 1 (2026): April 2026
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v5i1.226

Abstract

Indonesia is one of the world's most seismically active regions, making earthquake magnitude prediction an important component of disaster mitigation. This study compares several machine learning regression algorithms for predicting earthquake magnitude using Indonesian seismic data collected from the United States Geological Survey (USGS) during 2016–2023. The dataset contains 17,331 earthquake records consisting of spatial, measurement-quality, and temporal attributes. The research process included data preprocessing, feature engineering, model training, and evaluation using the Coefficient of Determination (R²), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Four regression algorithms were evaluated: Linear Regression, Support Vector Regression, Random Forest Regression, and Gradient Boosting Regression. Experimental results show that Random Forest Regression achieved the best performance with an R² of 0.767, MAE of 0.123, and RMSE of 0.179, followed by Gradient Boosting Regression with an R² of 0.746. Feature importance analysis indicates that magError, depthError, depth, and gap are the most influential variables in earthquake magnitude prediction. These findings demonstrate that ensemble learning provides accurate prediction performance while offering meaningful interpretation of influential seismic parameters for disaster mitigation systems
Klasifikasi Penyakit Ginjal Kronis pada Data Tidak Seimbang Menggunakan K-Nearest Neighbor Berbasis Seleksi Fitur Mutual Information dan GridSearchCV Mirza Afif Pradivta; Solikhun Solikhun; Timbo Faritcan P Siallagan
Bulletin of Artificial Intelligence Vol 5 No 1 (2026): April 2026
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v5i1.227

Abstract

Chronic Kidney Disease (CKD) is a progressive disease characterized by a gradual decline in kidney function and requires early detection to reduce the risk of severe complications. Machine learning has been widely applied to support CKD classification based on clinical attributes; however, medical datasets often contain missing values, a combination of numerical and categorical features, and class imbalance. This study aims to evaluate the performance of the K-Nearest Neighbor (KNN) algorithm for CKD classification using Mutual Information feature selection and GridSearchCV. The dataset consisted of 400 samples, including 250 CKD cases and 150 non-CKD cases. The proposed methodology included data cleaning, missing value imputation, categorical feature encoding, numerical feature normalization using MinMaxScaler, feature selection using SelectKBest with Mutual Information, and hyperparameter tuning using GridSearchCV. Model performance was evaluated using hold-out testing and 10-fold cross-validation. The hold-out evaluation showed that the KNN model with GridSearchCV achieved 100.00% accuracy, precision, recall, F1-score, and AUC on the test set. To ensure that this result was not dependent on a single train-test split, additional evaluation was conducted using 10-fold cross-validation. The cross-validation results yielded an average accuracy of 99.25% for the KNN model with GridSearchCV, indicating consistent performance across different data partitions. Meanwhile, the KNN model with Mutual Information feature selection and GridSearchCV achieved 98.75% accuracy, 100.00% recall, and a 99.01% F1-score, demonstrating competitive performance while using a more compact feature subset. The findings indicate that the application of GridSearchCV improved the performance of the KNN model on the dataset used, while Mutual Information contributed to selecting relevant features, enabling the model to maintain strong classification performance with a reduced number of features
Penerapan Algoritma Sattolo Shuffle dalam Sistem Pengacakan Denah Tempat Duduk Peserta Ujian untuk Mencegah Kecurangan Akademik Surya Darma Nasution; Guidio Leonarde Ginting
Bulletin of Artificial Intelligence Vol 4 No 2 (2025): October 2025
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v4i2.236

Abstract

Academic cheating during examinations remains a serious problem in educational institutions. One contributing factor is the use of fixed and predictable seating arrangements, which allow exam participants to plan cheating strategies with nearby peers. This study aims to implement the Sattolo Shuffle algorithm in a seating arrangement randomization system for exam participants as a measure to prevent academic dishonesty. The Sattolo Shuffle algorithm was chosen because of its ability to generate cyclic permutations that guarantee every element moves from its original position, ensuring no exam participant occupies the same seat as in a previous exam. The study was conducted using an experimental approach involving 30 exam participants randomized using the Sattolo Shuffle algorithm. The shuffling process requires 29 iterations (n-1 iterations for n=30 elements), and the verification results show that no participant remains in their original position (0 fixed points), proving the algorithm successfully produces a perfect cyclic permutation. All 30 participants form a single cycle, confirming the derangement property of the Sattolo Shuffle algorithm
Mapping the Evolution of Multi-Criteria Decision-Making and Simple Additive Weighting Research: A Comprehensive Bibliometric and Science Mapping Analysis from 2000 to 2025 Alfry Aristo Jansen Sinlae; Zulfikar Zulfikar; Juni Ismail; Yanto Saputra; Raja Anan Nasution; Elsy Rahajeng; Mesran Mesran
Bulletin of Artificial Intelligence Vol 4 No 2 (2025): October 2025
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v4i2.204

Abstract

The increasing complexity of decision-making environments driven by digital transformation, sustainability challenges, and technological advancements has significantly accelerated the adoption of Multi-Criteria Decision-Making (MCDM) methods across diverse scientific and practical domains. Among these approaches, the Simple Additive Weighting (SAW) method has gained substantial attention due to its simplicity, transparency, and effectiveness in evaluating alternatives based on multiple criteria. Despite the rapid growth of MCDM-SAW studies, the existing body of knowledge remains fragmented across disciplines, institutions, and application areas, creating a need for a comprehensive assessment of its intellectual and thematic development. Therefore, this study aims to systematically map the evolution, intellectual structure, and emerging research trends of MCDM and SAW research from 2000 to 2025. A bibliometric research design combined with science mapping techniques was employed using data retrieved from the Scopus database. A total of 381 English-language publications were selected through a PRISMA-based screening process. Data analysis was conducted using the Scopus Analysis Tool for performance analysis and VOSviewer for network visualization, including publication trend analysis, subject area distribution, co-citation analysis, and keyword co-occurrence mapping. The findings reveal a substantial increase in scientific production, particularly after 2015, indicating the growing relevance of MCDM and SAW in contemporary decision-support research. Engineering and Computer Science emerged as the most dominant subject areas, while leading publication sources included Expert Systems with Applications, Mathematics, Sustainability, and IEEE Access. Co-citation analysis identified influential scholars and foundational theories that shape the field, whereas keyword co-occurrence analysis highlighted the growing integration of sustainability, optimization, artificial intelligence, and hybrid MCDM frameworks. The novelty of this study lies in its integrated examination of publication performance, intellectual structure, and thematic evolution within the MCDM-SAW domain. The study contributes by providing a comprehensive knowledge map that supports future theoretical development, interdisciplinary collaboration, and methodological innovation in decision-support research
Analisis Sentimen Pengaruh Media Sosial Terhadap Keputusan Pembelian Konsumen Menggunakan Metode K-Nearest Neighbors (K-NN) Adinda Febiola; Ratih Manalu; Retno Ajeng Kartika Said; Putrama Alkhairi
Bulletin of Artificial Intelligence Vol 5 No 1 (2026): April 2026
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v5i1.238

Abstract

Perkembangan media sosial telah mengubah cara konsumen berinteraksi dan mengambil keputusan pembelian. Media sosial menjadi platform utama bagi konsumen untuk berbagi pengalaman, memberikan ulasan, dan mendiskusikan produk atau layanan. Penelitian ini bertujuan untuk menganalisis sentimen konsumen terhadap ulasan produk dimedia sosial serta dampaknya pada keputusan pembelian menggunakan metode K-NN. Data yang digunakan berupa ulasan konsumen yang dikumpulkaan pada platform media sosial. Data tersebut diproses melalui tahapan preprocessing, seperti tokenisasi, penghapusan kata tidak penting, dan stemming, sebelum diklasifikasikan menjadi sentimen positif dan negatif. K-NN dipilih karena keandalannya dalam klasifikasi berbasis jarak dan kemampuannya menangani datasetdengan pola distribusi yang kompleks. Hasil penelitian menunjukkan bahwa metode K-NN mampu mengklasifikasikan sentimen konsumen dengan akurasi 100%. Hasil analisis menunjukkan bahwa sentimen positif berkonstribusi signifikan dalam mempengaruhi keputusan keputusan pembelian, sedangkan sentimen negatif cenderung mengurangi minat konsumen. Hasil yang diperoleh dari tahap modelling dengan menggunakan metode K-NN dan perbandingan 80:20 untuk data training dan testing, maka nilai akurasi yang dihasilkan sebesar 90%, precision 90%, recall 100%. Evaluasi model dilakukan menggunakan matrik akurasi, presisi dan recall, dengan hasil yang menunjukkan kinerja K-NN cukup baik dalam mengklasifikasikan sentimen konsumen. Penelitian ini memberikan wawasan tentang pentingnya memahami sentimen konsumen di media sosial untuk strategi pemasaran yang lebih efektif, serta menunjukkan potensi penerapan machine learning, khususnya K-NN dalam menganalisis data tekstual untuk mendukung pengambilan keputusan bisnis.
Pengambilan Keputusan Dalam Pemilihan Penerima Bantuan Sosial Dengan Metode Multi-Factor Evaluation Process Muhammad Azhari; Ahmad Iqbal; Sindy Khairi Purba; Putrama Alkhairi
Bulletin of Artificial Intelligence Vol 4 No 2 (2025): October 2025
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v4i2.239

Abstract

Social assistance program is one of the government initiatives to reduce poverty level in Indonesia. In Simalungun Regency, Karang Anyar Village, the large amount of recipient data that needs to be processed can slow down the distribution of aid to people in need. This study aims to develop a system that can support social assistance facilitators in determining the right recipients quickly and accurately. The method used in this study is the Multi-Factor Evaluation Process (MFEP), which is expected to be able to identify recipients more efficiently. The data analyzed in this study consists of 25 prospective social assistance recipients obtained from social assistance facilitators in Karang Anyar Village. The assessment criteria for aid recipients include the presence of family members of Early Childhood, Pregnant Women, Elderly, People with Disabilities, High School Children (SMA), Middle School Children (SMP), and Elementary School Children (SD). The MFEP stages include determining the weight for each criterion, assigning a value to each factor, calculating the evaluation weight, and summing all evaluation weights to obtain the final value as a basis for decision making. Data processing on 25 potential aid recipients revealed that 24 were eligible and 6 were ineligible. The results of this data processing using the MFEP method, compared with manual data from social assistance facilitators in Simalungun, Karang Anyar Village, showed a 100% accuracy rate for decision-making. With this level of accuracy, the MFEP method has been proven to assist the decision-making process in selecting appropriate social assistance recipients in Simalungun Regency, Karang Anyar Village.

Page 4 of 4 | Total Record : 37

 1   2   3   4 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol 5 No 1 (2026): April 2026 Vol 4 No 2 (2025): October 2025 Vol 4 No 1 (2025): April 2025 Vol 3 No 2 (2024): October 2024 Vol 3 No 1 (2024): April 2024 Vol 2 No 2 (2023): October 2023 Vol 2 No 1 (2023): April 2023 Vol 1 No 2 (2022): October 2022 Vol 1 No 1 (2022): April 2022