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 329 Documents
 19   20   21   22   23 
Penerapan Information Gain Untuk Seleksi Fitur Pada Klasifikasi Jenis Kelamin Tulang Tengkorak Menggunakan Backpropagation Khair, Nada Tsawaabul; Afrianty, Iis; Syafria, Fadhilah; Budianita, Elvia; Gusti, Siska Kurnia
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.637

Abstract

Forensic anthropology and skull analysis play a crucial role in the biological identification of individuals, including sex determination. This study aims to improve the accuracy of gender classification based on skull structure by combining the Information Gain feature selection method with the Backpropagation algorithm. The dataset used is the craniometric data compiled by William W. Howells, consisting of 2,524 samples with 85 measurement features. The preprocessing stage includes data selection, data cleaning, and normalization. Feature selection was conducted using the Information Gain method with three threshold values: 0.01, 0.05, and 0.1, resulting in 79, 46, and 38 selected features, respectively. The model was evaluated using the K-Fold Cross Validation method with K=10 and K=20. The highest accuracy of 93.91% was achieved at the 0.01 threshold using the Backpropagation architecture [79:119:1], a learning rate of 0.01, and K=20. These results demonstrate that feature selection using Information Gain enhances the performance of the Backpropagation model by eliminating irrelevant features and minimizing the risk of overfitting.
Klasifikasi Citra Sampah Botol Plastik Jenis HDPE dan PET Menggunakan Algoritma YOLOv7 Purwasih, Opita; Widhiarso, Wijang; Muhammad Rizky Pribadi
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.654

Abstract

The classification of plastic bottle waste, particularly High Density Polyethylene (HDPE) and Polyethylene Terephthalate (PET), remains a challenge in recycling processes due to their similar visual characteristics. Misclassification can lead to a decline in recycled material quality and economic losses in the waste management industry. This research aims to develop an automated image-based classification system to distinguish between HDPE and PET plastic waste using the You Only Look Once version 7 (YOLOv7) object detection algorithm. The dataset consists of plastic bottle images in various physical conditions, annotated with bounding boxes to support model training. The data were split into 70% for training, 20% for validation, and 10% for testing. The best performance was achieved with a batch size of 16 and 100 training epochs, resulting in a precision of 93.9%, recall of 91.6%, and a mean Average Precision (mAP@0.5) of 96.5%. The model demonstrated the ability to accurately classify both types of plastic bottles, even when objects were deformed. These results suggest that the YOLOv7 algorithm is highly capable for implementation in image-based waste classification systems, enhancing sorting efficiency and supporting more sustainable plastic waste management practices.
Analisis Kinerja Random Forest Dalam Deteksi Gejala Alergi Rongga Mulut Berbasis Warna Gusi Gea, Juli Hartati; Agustinus Rudatyo Himamunanto; Haeny Budiati
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.657

Abstract

Early detection of allergies in the oral cavity remains challenging due to the subjective nature of visual assessment and limited access to diagnostic facilities. This study proposes a novel approach using the Random Forest algorithm to classify the severity of allergic symptoms based on gum color analysis from digital images. A total of 2,742 gum images were clinically categorized using the Modified Gingival Index (MGI) into mild, moderate, and severe conditions. Preprocessing included conversion to HSV color space and adaptive segmentation using red thresholds on the hue channel (0–10 and 160–180), saturation > 50, and value > 40. Statistical features, including mean, standard deviation, skewness, kurtosis, and entropy, were extracted and normalized using Z-Score. Six parameter combinations were tested with an 80:20 train-test split. The optimal configuration with n_estimators=80, max_depth=9, and min_samples_leaf=2 achieved an accuracy of 95.81%. The highest performance was achieved in the mild class with precision and recall of 98.91%, and stable results in the moderate (93.80%) and severe (94.74%) classes, with only a 0.94% difference. Cross-validation evaluation demonstrated excellent model stability, with an average accuracy of 95.30% and a standard deviation of 0.67%, indicating consistent performance across data subsets. Feature importance analysis showed the dominance of the hue and saturation channels, particularly kurtosis and mean saturation. This study demonstrates that a Random Forest-based allergy detection system using gum color is highly accurate and effective as a non-invasive screening tool in dental and oral health, especially in resource-limited settings, with the potential to improve early screening access in primary healthcare facilities.
Deteksi Penyakit Tanaman Padi (Oryza Sativa L.) Menggunakan Support Vector Machine (SVM) Dan Random Forest Pada Citra Daun Gulo, Bintang Karmila; Agustinus Rudatyo Himamunanto; Jatmika
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.660

Abstract

Rice (Oryza sativa L.) is a major food crop that is susceptible to disease attacks, which can reduce farmers' productivity and yields. This study aims to develop a digital image-based rice leaf disease classification system using the Support Vector Machine (SVM) and Random Forest algorithms. The dataset consists of three disease classes (Blast, Blight, and Tungro), which are processed through pre-processing stages such as resizing, normalization, and augmentation. Feature extraction is performed using HSV histograms, RGB average values, and Gray Level Co-occurrence Matrix (GLCM) to obtain color and texture characteristics. The data is then divided with a ratio of 80:20 for model training and testing. The evaluation results show that Random Forest provides the best performance with an accuracy of 97.73%, precision and recall values ??above 0.94, and an average F1 score of 0.98. This study shows that a machine learning-based image classification approach can be an effective solution for early detection of diseases in rice plants.
Penggunaan Convolutional Neural Network NASNetLarge Dalam Klasifikasi Citra Daging Babi dan Sapi Aqilah, M Alfandri; Jasril; Sanjaya, Suwanto; Insani, Fitri
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.666

Abstract

The adulteration of beef with pork is a serious issue in Indonesia, particularly for Muslim consumers who are required to consume halal products. According to a Kompas (2020) report, a case of meat adulteration involving 100 kilograms of mixed meat sold as beef was discovered in Tangerang City. This practice not only violates religious laws but also poses threats to public health and consumer trust. To address this challenge, this study adopts a deep learning approach using NASNetLarge for the classification of pork, beef, and mixed meat images. Unlike previous research that utilized EfficientNet-B2 and achieved an accuracy of 98.23%, this study’s NASNetLarge approach produced a comparably competitive accuracy of 98.03%. The dataset used consists of 1,932 images sourced from the Kaggle platform, which were processed through preprocessing and augmentation stages. The data were then split into two distribution scenarios: the entire dataset and a balanced class dataset with 90:10 and 80:20 ratios. Evaluation results show that the best parameter combination was achieved in the first scenario with a 90:10 ratio using augmented images, a learning rate of 0.001, 128 dense units, and the Adam optimizer. The model achieved the highest accuracy of 98.03%, with a precision of 98.63%, recall of 98.40%, and an F1-score of 98.50%. These results indicate that NASNetLarge is effective in accurately and consistently classifying meat images. Image augmentation significantly improved model performance, and the 90:10 data ratio yielded more optimal results compared to 80:20. These findings have the potential to support food surveillance efforts by enabling rapid and accurate detection of meat adulteration.
Perbandingan Akurasi Arsitektur EfficientNet-B0, VGG16, dan Inception V3 Dalam Deteksi Tumor Ginjal Pada Citra CT-Scan Muhammad Fahri; Yanto, Febi; Syafria, Fadhilah; Abdillah, Rahmad
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.670

Abstract

Kidney dysfunction can trigger the development of various diseases, including kidney tumors. Early detection of kidney tumors is very important to increase the effectiveness of treatment and the chances of patient recovery. The use of deep learning technology in medical image classification has become a promising approach, especially in detecting abnormalities in the kidney organ through CT-Scan images. This study compares the performance of three Convolutional Neural Network (CNN) architectures, namely EfficientNet-B0, Inception-V3, and VGG16, in detecting kidney tumors. The dataset used was obtained from the kaggle website, namely CT-scan images with normal and tumor classes and divided by a ratio of training  data and test data of 80:20. The hyperparameter used is Stochastic Gradient Descent (SGD) with a learning rate of 0.001 and 0.0001. The evaluation was carried out using a confusion matrix with metrics of accuracy, precision, recall, and F1-score . According to the test outcomes, the VGG16 model configured with a 0.001 learning rate achieved the highest classification performance, recording 99.46% accuracy, precision, recall, and F1-score.
Optimalisasi Akurasi Prediksi Curah Hujan Bulanan Menggunakan Deep Learning Yafik, Muhammad Ikrom; Chairani, Chairani
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.735

Abstract

The Province of Lampung exhibits high rainfall variability influenced by various atmospheric dynamics such as the Asian Monsoon, Australian Monsoon, El Niño–Southern Oscillation (ENSO), and the Indian Ocean Dipole (IOD). Accurate rainfall prediction is crucial across multiple sectors, including agriculture, water resource management, and hydrometeorological disaster mitigation. However, prediction methods commonly used in the region are still dominated by statistical approaches or conventional machine learning techniques, which often struggle to capture long-term temporal patterns in rainfall data. On the other hand, deep learning technologies such as the Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) offer better capabilities in modeling time series data, yet no specific comparative evaluation has been conducted for rainfall prediction in the Lampung Province. Comparing these two methods is important because the architectural characteristics of RNN and GRU differ in handling long-term dependencies, and selecting the right model can directly impact prediction accuracy and the effectiveness of decision-making in affected sectors. This study aims to implement and compare the performance of RNN and GRU in predicting monthly rainfall in Lampung Province using data from 80 rain gauges distributed across 15 districts/cities over the period from January 1991 to February 2025. The results show that the RNN model outperforms the GRU model, with lower RMSE (115.61 vs. 119.50), smaller MAE (86.94 vs. 91.28), and higher R² (0.35 vs. 0.30). Predictions for the period from March 2025 to February 2026 reveal a clear seasonal pattern, with minimum rainfall occurring in August 2025 (peak dry season) and maximum rainfall in January 2026 (peak rainy season). This study demonstrates that RNN is more effective than GRU in capturing the temporal patterns of rainfall, making it more recommended for long-term prediction applications.
Implementasi Animasi 2D menggunakan Motion Graphic sebagai Media Informasi Palang Merah Indonesia Wulandari, Irma; Fananda, Ibrohim Yofid; Hasim, Jauari Akhmad Nur; Pramulen, Aji Sapta; Damastuti, Fardani Annisa; Zukhaha, Ashiliya Atsmara
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.739

Abstract

The Indonesian Red Cross (PMI) has a significant responsibility in conveying humanitarian information to the public. However, the challenges of effectively communicating information to the broader community remain a primary concern, as conventional media often lack appeal and are difficult to comprehend fully. To address this issue, this study implements 2D animation based on motion graphics as a communication medium for PMI. The animation production process includes creating storyboards, developing visual illustrations, graphic processing, adding motion elements, voice narration, and audio-visual synchronization, resulting in a communicative and engaging medium. 2D animation was chosen because it can present messages with simple yet clear visuals, while motion graphics provide engaging motion dynamics that make information easier to understand and remember. The integration of both allows for the delivery of messages that are concise, interactive, and in line with the characteristics of digital media that are widely accessed by the public. Evaluation results show a significant increase in the level of understanding among respondents after watching the video, with post-test scores reaching 94.8% in the PMI member group and 91.2% in the general public group. These findings affirm that 2D animation media based on motion graphics is effective in enhancing the appeal, understanding, and effectiveness of PMI communication, thus it can be an innovative alternative strategy to expand the reach of humanitarian information.
Analisis Klasifikasi Kesiapan Digital Desa Menggunakan Decision Tree dan Pemetaan Spasial Fatimah Ahmad, Hafidlotul; Firdawanti, Aulia Rizki; Agustiani, Nur
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.741

Abstract

Digital transformation at the village level is a strategic element in promoting equitable development and improving public service delivery. However, the level of digital readiness across regions remains uneven. This study aims to classify the digital readiness of villages in West Java Province by utilizing data from Open Data Jabar (opendata.jabarprov.go.id) related to the number of digital villages, internet access, and village development strata. A Decision Tree classification algorithm was employed to categorize regions into two readiness classes: high and low. The modeling results indicate that the number of self-reliant (mandiri) villages and the percentage of villages with internet access are the most influential variables in the classification. Although internet infrastructure is available in most areas, it does not always correspond to the level of village digitalization. Districts with high internet access but a low number of self-reliant villages are still classified as having low readiness. The model achieved an accuracy of 83%, although its performance in identifying the high readiness class was limited due to class imbalance in the dataset. Spatial visualization was also used to highlight regional disparities in digital readiness. This study provides an early contribution to digital readiness mapping of villages using a machine learning approach in Indonesia.
Penerapan Algoritma BM25 dalam Pencarian Lowongan Pekerjaan pada Website Job Portal Kheng, Tek; Asri, Jefry Sunupurwa; Wahyu, Sawali; Yulhendri, Yulhendri
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.760

Abstract

The development of the digital era has grown rapidly all the time which has significantly changed the job search process for job applicants, making Online Job Portals one of the main places in human resource recruitment activities, however, the effectiveness of Job Portals Job search still has fundamental weaknesses such as the job search technology used still uses simple string matching which can cause less relevant search results and reduce the quality of user experience in applying for jobs. This study was conducted to improve the quality of job vacancy search results on Job Portal A Career by applying the Okapi BM25 algorithm. This research method uses a Rapid Application Development (RAD) development approach, such as designing a client server architecture with Next.js as the frontend, ASP.NET Core as the backend and PostgreSQL as the main database. The BM25 algorithm is integrated directly into the database using the VectorChord BM25 extension to calculate the search relevance score with the user inputted query. In testing with the query “accelist the quality support career IT need”, the system displays 800 of 1,011 documents (79.13%) with a non-zero relevance score. Furthermore, evaluation through User Acceptance Testing (UAT) showed a user satisfaction rate of 91.2%, confirming that BM25 is capable of displaying the most relevant results at the top of the rankings and supporting the effectiveness of the search system. The results of this study can be concluded that the BM25 algorithm is a more effective and efficient search solution with high scalability potential for application to other web-based job search systems.

Page 21 of 33 | Total Record : 329

 19   20   21   22   23 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue 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