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
+6282370070808
Journal Mail Official
jurnal.bulletincsr@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Computer Science Research
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 27743659     DOI : -
Core Subject : Science,
Computer Science & IT
Bulletin of Computer Science Research covers the whole spectrum of Computer Science, which includes, but is not limited to : • Artificial Immune Systems, Ant Colonies, and Swarm Intelligence • Bayesian Networks and Probabilistic Reasoning • Biologically Inspired Intelligence • Brain-Computer Interfacing • Business Intelligence • Chaos theory and intelligent control systems • Clustering and Data Analysis • Complex Systems and Applications • Computational Intelligence and Soft Computing • Distributed Intelligent Systems • Database Management and Information Retrieval • Evolutionary computation and DNA/cellular/molecular computing • Expert Systems • Fault detection, Fault analysis, and Diagnostics • Fusion of Neural Networks and Fuzzy Systems • Green and Renewable Energy Systems • Human Interface, Human-Computer Interaction, Human Information Processing • Hybrid and Distributed Algorithms • High-Performance Computing • Information storage, security, integrity, privacy, and trust • Image and Speech Signal Processing • Knowledge-Based Systems, Knowledge Networks • Knowledge discovery and ontology engineering • Machine Learning, Reinforcement Learning • Networked Control Systems • Neural Networks and Applications • Natural Language Processing • Optimization and Decision Making • Pattern Classification, Recognition, speech recognition, and synthesis • Robotic Intelligence • Rough sets and granular computing • Robustness Analysis • Self-Organizing Systems • Social Intelligence • Soft computing in P2P, Grid, Cloud and Internet Computing Technologies • Support Vector Machines • Ubiquitous, grid and high-performance computing • Virtual Reality in Engineering Applications • Web and mobile Intelligence, and Big Data • Cryptography • Model and Simulation • Image Processing
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 462 Documents
 35   36   37   38   39 
Penerapan Support Vector Machine Dengan Smote Untuk Klasifikasi Sentimen Pada Data Ulasan Aplikasi Trading View Muhammad Badri; Elin Haerani; Fadhilah Syafria; Okfalisa Okfalisa; Lola Oktavia
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.793

Abstract

In the digital era, user feedback on mobile applications serves as highly valuable information for developers to evaluate app performance. One popular application in the field of finance and investment is TradingView, widely used for technical analysis by traders. User feedback on this application reflects various user sentiments, including positive, negative, and neutral. However, the large volume of reviews and the unstructured nature of text data make manual analysis inefficient and prone to high subjective bias. Therefore, the use of automatic classification methods capable of processing text data with reasonable accuracy is required. This study aims to implement the “Support Vector Machine (SVM)” technique to classify user feedback on the TradingView application. To address the issue of imbalanced sentiment class distribution, the study also employs the “Synthetic Minority Over-sampling Technique (SMOTE)”. The study utilizes 10,000 reviews obtained via web scraping from the Google Play Store. The study workflow consists of text preprocessing, feature extraction using “Term Frequency-Inverse Document Frequency (TF-IDF)”, data balancing, SVM model training, and model evaluation. The evaluation results show that the application of SVM with SMOTE achieves an accuracy of approximately ±85.56% across data splits (70:30, 80:20, 90:10). In each scenario, the highest F1-score was achieved for the positive sentiment class, while the performance of minority classes (negative and neutral) improved after data balancing with SMOTE, with an average F1-score increase of 1.67% for the negative class and 10.67% for the neutral class. Without SMOTE, the average negative F1-score was ±57%, and the neutral class was undetected (0.00%). Furthermore, validation using K-Fold Cross Validation yielded an average accuracy of 89.20%, which increased to 95.10% after applying SMOTE. This improvement was consistent across all data proportions (70:30, 80:20, 90:10), with an average increase of 5.44%. These findings confirm that integrating SVM with SMOTE not only enhances classification performance on imbalanced data but also maintains model stability. Therefore, this study contributes to the advancement of automated sentiment classification systems, particularly for financial mobile app reviews, and can serve as a reference for future research in user review analysis on similar applications.
Identifikasi Penyakit Padi Berdasarkan Citra Daun Menggunakan Arsitektur Convolutional Neural Network Kustom Andre Gunawan Polontalo; Mohamad Ilyas Abas; Widya Eka Pranata
Bulletin of Computer Science Research Vol. 5 No. 6 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i6.809

Abstract

Rice production in Indonesia often declines due to leaf diseases that are difficult to detect early using conventional methods. This study aims to identify rice leaf diseases based on leaf images using a Convolutional Neural Network (CNN). The dataset was obtained from an online repository (Kaggle) containing labeled images of rice leaves across several disease categories. A custom CNN model was designed and trained after applying image preprocessing (resizing to 224×224 pixels), normalization, and data augmentation to reduce overfitting. The training was conducted in the Google Colab environment using TensorFlow with train–test splits of 70:30, 80:20, and 90:10 to analyze model performance. The best result achieved a training accuracy of 83.02% and a testing accuracy of 77.33%. Furthermore, the model was compared with several widely used architectures in the literature, including ResNet50, VGG16, and EfficientNetB0. The findings indicate that the proposed custom CNN model provides competitive classification performance for early detection of rice leaf diseases and has the potential to serve as a decision-support system for farmers in rapid and efficient disease management.
Pengembangan Sistem Transformasi dan Konversi Data Berbasis Web Menggunakan Arsitektur RESTful API Deborah Kurniawati; Adi Kusjani; Robby Cokro Buwono; Muhammad Aldo Ridhoni
Bulletin of Computer Science Research Vol. 5 No. 6 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i6.818

Abstract

Heterogeneous data management often faces challenges such as format inconsistency, high latency, and lack of automation, leading to inefficiencies and errors in data transformation. This research aims to develop a web-based system to automate data transformation and conversion across formats using a Representational State Transfer (RESTful) Application Programming Interface (API) architecture, with a Mithril.js frontend and Go backend. An experimental and system development approach was employed, comprising three stages: client-server architecture design, implementation, and testing. The system provides 11 primary API endpoints, such as /api/tasks and /api/transformations, to manage tasks and data transformations. The Single Page Application frontend offers intuitive navigation with menus for task management, data sources, and activity logs. Functional testing on Comma-Separated Values, JavaScript Object Notation, and SQLite formats yielded accurate transformations, including text prepending, data type conversion, and lowercase normalization. Performance evaluation using Google Lighthouse recorded a median score of 85, indicating high performance. The system enhances efficiency and accuracy compared to manual methods, supporting cross-platform interoperability. However, limitations include support for only simple tabular formats and lack of security features. This research offers a lightweight solution for data transformation, with potential applications in organizational data integration and business analytics.
Peningkatan Transparansi Tata Kelola Keuangan Desa melalui Pengembangan Sistem Berbasis Web dengan Menerapkan Model Agile Septiano Cepeda Da Costa; Galet Guntoro Setiaji; Ahmad Rifa'i
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.821

Abstract

This research discusses village financial management as a primary aspect in supporting village progress and community welfare. Transparent and effective budget management is crucial for ensuring that village funds are utilized optimally for development programs. However, several obstacles persist, including delays in financial reporting and limited access to information for residents. The purpose of this research is to design and develop a web-based village financial information system using the Laravel framework and an Agile methodology to improve transparency, data accessibility, and the effectiveness of real-time financial reporting. The Agile method was selected for its iterative and collaborative development process, which is responsive to user needs. This approach allows both residents and village officials to participate actively in the development process, ensuring the resulting system serves as a viable solution to existing problems. Functional testing results using the Black Box method indicate that the system facilitates easier financial reporting, provides accurate data presentation, and supports accountability in village fund management. This system is expected to increase community participation in budget oversight and serve as a technological solution for the digitalization of village financial management. Ultimately, this system aims to make village budget management transparent, fast, and accessible to all residents at any time, thereby fostering community trust and engagement in village development.
Analisis Sentimen Keluhan Pelanggan ISP menggunakan Support Vector Machine (SVM) dan TF-IDF Dini Fakta Sari; Deborah Kurniawati; Endang Wahyuningsih; Tediyan Rahmat Wibowo
Bulletin of Computer Science Research Vol. 5 No. 6 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i6.822

Abstract

This study aims to analyze the sentiment of customer complaints regarding Internet Service Provider (ISP) services in Indonesia, where the primary issues frequently reported include connection disruptions, slow internet speeds, weak signals, and unresponsive or uninformative complaint handling, as reflected in various consumer reports on social media. These issues contribute to customer dissatisfaction and necessitate data analysis solutions to deeply understand public opinions. Data was collected via API from a social media platform using keywords related to internet services, such as "internet disruption" and "internet complaints." The data underwent text preprocessing stages, including cleaning, case folding, tokenization, stopword removal, and stemming to produce consistent text. Text features were extracted using Term Frequency–Inverse Document Frequency (TF-IDF), which were then classified using the Support Vector Machine (SVM) algorithm. Model evaluation using 10-Fold Cross Validation yielded an average accuracy of 91.47%, precision of 94.27%, recall of 99.20%, and F1-score of 96.67%. Word frequency analysis revealed dominant words such as “slow,” “disruption,” and “signal” as the main issues in customer complaints. The combination of SVM and TF-IDF proved effective for sentiment analysis in Indonesian, providing academic and practical contributions for ISPs to monitor customer opinions and improve service quality. Future research is recommended to employ deep learning models like BERT and more diverse data.
Sistem Pakar Diagnosa Awal Cacar Monyet Menggunakan Logika Fuzzy Metode Tsukamoto dan Mesin Inferensi Forward Chaining Berbasis Android Surtikanti Surtikanti; Khilmy Safirul Iman
Bulletin of Computer Science Research Vol. 6 No. 2 (2026): February 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i2.823

Abstract

Rising monkeypox cases in Indonesia require accessible early detection systems given conventional diagnosis limitations and lack of public understanding about disease symptoms. This research develops an early diagnosis expert system for monkeypox by integrating Fuzzy Tsukamoto and Forward Chaining methods based on responsive web. Iterative and Incremental Development approach was applied through three development iterations. Forward Chaining traces 7 discrete symptoms (G01-G07) producing qualitative diagnosis which is then reinforced by Fuzzy Tsukamoto through fuzzification of 3 continuous variables (body temperature, rash count, lymph node swelling) with 27 inference rules and weighted average defuzzification to quantify risk level. Integration mechanism works in layers where Forward Chaining verifies binary symptom completeness as initial diagnosis, subsequently the qualitative output is reinforced with quantitative certainty value (Z) from Tsukamoto as risk stratification, producing comprehensive diagnosis that overcomes single-method system limitations. Testing on 20 cases showed clear separation between low-risk (Z: 0.331-0.463) and high-risk (Z: 0.814-0.990) categories. Validation using medical expert diagnosis as gold standard yielded 95% accuracy, 90% sensitivity, 100% specificity, 100% precision, and 94.7% F1-score, proving system capability in accurate diagnosis. Black Box testing validated all system functionalities running error-free. Layered integration of both methods proved effective in producing objective diagnosis with high accuracy, although further research is needed for multi-disease base expansion and validation using actual clinical data from healthcare facilities.
Penerapan Algoritma K-Means dalam Segmentasi Anggota Koperasi Berdasarkan Pola Simpanan dengan Analisis RFMP untuk Meningkatkan Loyalitas Abdul Razak Naufal; Turkhamun Adi Kurniawan; M Al’Amin
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.843

Abstract

Cooperatives as member-based financial institutions have an important role in supporting the welfare of their members. However, the diversity of member characteristics, both in terms of length of membership and the amount of monthly savings, poses challenges in formulating effective management strategies. This study aims to group cooperative members based on financial transaction data patterns using a data mining approach. The method used is the K-Means Clustering algorithm, with the main variables using RFMP analysis (Recency, Frequency, Monetary and Payment), namely length of membership (Recency), frequency of savings in a year (Frequency), amount of monthly savings (Monetary) and timely loan payments (Payment). Data is processed through a pre-processing stage, the data is normalized using the Min–Max Scaling method to equalize unit differences between variables, Determination of the optimal number of clusters is done using the Elbow Method, which shows that the best number of clusters is three groups. The results of the study with a total of 50 transaction data resulted in cooperative members being divided into three clusters. The first cluster is at-risk members at 36%, the second cluster is potential members at 40%, and the third cluster is loyal or exclusive members at 24%. These findings provide practical solutions for cooperatives in developing member management strategies. Existing members need to be motivated to increase savings, new members need coaching to foster loyalty, and premium members need special services to maintain their satisfaction. Thus, clustering results can form the basis for data-driven decision-making in cooperative management.
Komparasi Model ResNet50 dan EfficientNetV2M dengan Penerapan Transfer Learning dan Fine Tuning pada Klasifikasi Penyakit Bercak Daun Tanaman Pisang Muhammad Gimmas Manggara; Anna Dina Kalifia
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.855

Abstract

Bananas are an important commodity to support the Indonesian economy, but the frequent occurrence of banana spot disease in tropical countries can cause problems for this industry. The purpose of this study is to build and compare two models, namely ResNet50, which is often used as the main comparison, with EfficientNetV2M as a newer model. The dataset was obtained from two sources on the Mendeley data platform. The combined dataset consists of 1938 data labeled with 5 classes: cordana, pestalotiopsis, black sigatoka, yellow sigatoka, and healthy. The preprocessing process was carried out by dividing the data into training, validation, and testing with a ratio of 70:20:10, then resizing and assigning weights to each class. Two models were trained with the same parameters and evaluation metrics such as accuracy, precision, recall, f1-score, and loss. The test evaluation results show the results of the EfficientNetV2M model test with an accuracy metric value of 94,92%, precision of 95,49%, recall of 92,23%, f1-score of 93,70% and loss of 17,96%. While ResNet50 with an accuracy value of 91,88%, precision of 90,97%, recall of 87,59%, f1-score of 89,14%, and Loss of 20,87%. Based on these evaluation results, EfficientNetV2M is a model with superior performance for the classification of banana leaf spot disease. This research is expected to be a reference for determining an effective model and developing a classification system for banana leaf spot disease.
Penggunaan Model Inceptionv3 Berbasis Transfer Learning untuk Mendeteksi Masker Wajah Secara Real-Time Muhammad Chaska Putra Sofyan; Joko Aryanto
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.865

Abstract

The use of face masks has become an essential health protocol to prevent the spread of infectious diseases. However, public compliance remains low due to the absence of effective automated monitoring systems. This study aims to develop a real-time face mask detection system using transfer learning with the InceptionV3 architecture. The model was trained on facial image datasets classified into two categories: mask and no mask. By leveraging the ability of InceptionV3 to extract complex visual features, the training process becomes more efficient without training the model from scratch. The system is integrated with a webcam to perform real-time detection in real environments. The testing results indicate that the model achieved an accuracy of 98.7%, with stable detection performance and real-time responsiveness. These findings highlight the strong potential of deep learning approaches to support automated and effective monitoring of public health protocol compliance.
Pemodelan Topik pada Komunitas Ekspresi Emosi Negatif di Media Sosial X Menggunakan LDA Rizal Muhammad Ramli; Chanifah Indah Ratnasari
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.877

Abstract

This study aims to map the thematic structure of conversations within a community of negative emotional expression on platform X, commonly referred to as the “Komunitas MARAH MARAH.” The primary problem explored in this study is how collective anger is formed and which issues dominate the discourse within this community. To address this, the study employs a text mining approach through several stages of textual data processing, including data scraping, preprocessing, dictionary-based normalization, Term Frequency–Inverse Document Frequency (TF-IDF) weighting, and topic modeling using Latent Dirichlet Allocation (LDA). A total of 75,032 tweets were collected and subsequently cleaned, resulting in 38,956 unique entries for further analysis. Topic modeling was conducted by evaluating several topic configurations, with the highest coherence score of 0.5367 achieved using a three-topic model. Further analysis revealed three dominant themes along with their proportional distributions: personal complaints and everyday emotional expression (50.5%), direct anger or generalized expressions toward particular groups (35.8%), and issues related to fraud and digital security (13.7%). These findings illustrate how collective anger is constructed, disseminated, and interpreted within online conversational spaces. This study is expected to serve as a foundation for further research on digital emotion, online community dynamics, and social issue mapping through public discourse.

Page 37 of 47 | Total Record : 462

 35   36   37   38   39 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 5 (2026): August 2026 Vol. 6 No. 4 (2026): June 2026 Vol. 6 No. 3 (2026): April 2026 Vol. 6 No. 2 (2026): February 2026 Vol. 6 No. 1 (2025): December 2025 Vol. 5 No. 6 (2025): October 2025 Vol. 5 No. 5 (2025): August 2025 Vol. 5 No. 4 (2025): June 2025 Vol. 5 No. 3 (2025): April 2025 Vol. 5 No. 2 (2025): February 2025 Vol. 5 No. 1 (2024): December 2024 Vol. 4 No. 6 (2024): Oktober 2024 Vol. 4 No. 5 (2024): August 2024 Vol. 4 No. 4 (2024): June 2024 Vol. 4 No. 3 (2024): April 2024 Vol. 4 No. 2 (2024): Februari 2024 Vol. 4 No. 1 (2023): December 2023 Vol. 3 No. 6 (2023): October 2023 Vol. 3 No. 5 (2023): Agustus 2023 Vol. 3 No. 4 (2023): June 2023 Vol. 3 No. 3 (2023): April 2023 Vol. 3 No. 2 (2023): Februari 2023 Vol. 3 No. 1 (2022): Desember 2022 Vol. 2 No. 3 (2022): Agustus 2022 Vol. 2 No. 2 (2022): April 2022 Vol. 2 No. 1 (2021): Desember 2021 Vol. 1 No. 3 (2021): Agustus 2021 Vol. 1 No. 2 (2021): April 2021 Vol. 1 No. 1 (2020): Desember 2020 More Issue