Garuda - Garba Rujukan Digital

Comparison of the DBSCAN Algorithm and Affinity Propagation on Business Incubator Tenant Customer Segmentation Agustino, Dedy Panji; Budaya, I Gede Bintang Arya; Harsemadi, I Gede; Dharmendra, I Komang; Pande, I Made Suandana Astika
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 12, No 2 (2023): JULI
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v12i2.1682

The increasingly complex business environment necessitates businesses to design more effective and efficient strategies for company development, including market expansion. To understand customer behaviors, customer data analysis becomes crucial. One common approach used to group customers is segmentation based on RFM analysis (Recency, Frequency, and Monetary). This study aims to compare the performance of two clustering algorithms, namely DBSCAN and Affinity Propagation (AP), in providing customer profile segment recommendations using RFM analysis. DBSCAN algorithm is employed due to its ability to identify arbitrarily shaped clusters and handle data noise. On the other hand, Affinity Propagation (AP) algorithm is chosen for its capability to discover cluster centers without requiring a pre-defined number of clusters. The transaction dataset used in this research is obtained from one of the business incubator tenants at STIKOM Bali. The dataset undergoes preprocessing steps before being segmented using both DBSCAN and AP algorithms. Performance evaluation of the algorithms is conducted using the Silhouette Scores and Davies-Bouldin Index (DBI) matrices. The research findings indicate that the AP algorithm outperforms DBSCAN in this customer segmentation case. The AP algorithm yields Silhouette Scores of 0.699 and DBI of 0.429, along with recommendations for 4 customer segments. Furthermore, further analysis is performed on the AP results using a statistical approach based on the mean values of each segment for the RFM variables. The four customer segments generated by the AP algorithm, based on the mean values of the RFM variables, can be associated with the concept of customer relationship management.

WebGL 3D Virtual Exhibition as a Media to Increase the Visibility of Digital Artwork Pande, I Made Suandana Astika; Budaya, I Gede Bintang Arya; Crisnapati, Padma Nyoman
JTIM : Jurnal Teknologi Informasi dan Multimedia Vol 5 No 3 (2023): November
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v5i3.376

The ongoing digital transformation continues to shape various domains, including the realm of art, which adopts social media to digitally promote artworks. Nonetheless, physical art exhibitions maintain their allure as they provide a direct experiential interaction for visitors. Consequently, the development of exhibition platforms that amalgamate user experience with accessibility becomes imperative. One emerging solution involves leveraging information technology and multimedia for virtualization, such as utilizing WebGL for creating a 3D Virtual Exhibition (3DVE). Employing the ADDIE methodology and evaluating it through the Technology Acceptance Model (TAM), the assessments affirm the robust performance and positive responses of 30 participants towards WebGL 3DVE. This development yields practical benefits, particularly for artists seeking to enhance the visibility of their creations. Furthermore, the inherent ease of use and broad accessibility can expand the potential audience for enjoying artworks. The percentage acceptance rates according to TAM validate favorable responses across usability (88%), ease of use (74%), satisfaction (90.6%), and technological acceptance (84.6%). Thus, the deployment of WebGL 3DVE in art exhibition development showcases strong potential in delivering a deeper and more inclusive experiential journey.

Performance Comparison of KNN and CNN in Classifying Balinese Gangsa Instrument Tones Yusadara, I Gede Putra Mas; Dewi, Ni Made Rai Masita; Budaya, I Gede Bintang Arya
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 4 (2024): Article Research Volume 8 Issue 4, October 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.14019

Balinese traditional music, particularly the Gamelan Gangsa, represents a unique aspect of Indonesia’s cultural heritage. Despite its cultural significance, the study and teaching of this instrument face challenges, particularly in tone standardization and the availability of effective learning tools. This research addresses these challenges by exploring the application of Artificial Intelligence (AI) technologies specifically K-Nearest Neighbors (KNN) and Convolutional Neural Networks (CNN) in the identification and classification of Gamelan Gangsa tones. The study involved the creation of a dataset comprising audio recordings of the instrument, followed by the development and evaluation of KNN and CNN models. The results indicate that KNN, with an accuracy of 90%, outperformed CNN, which achieved an accuracy of 85%. The findings suggest that KNN is particularly effective in distinguishing subtle tonal differences, making it a valuable tool for supporting traditional music education. This research not only contributes to the technical understanding of Gamelan Gangsa’s acoustic characteristics but also underscores the potential of AI in cultural preservation. The development of AI-based tone identification systems can facilitate the teaching and learning of traditional music, ensuring its transmission to future generations. The study serves as a foundation for further exploration into the integration of AI technologies with cultural heritage, demonstrating how modern innovations can enhance the appreciation and understanding of traditional arts.

Comparison of Sentiment Analysis Algorithms with SMOTE Oversampling and TF-IDF Implementation on Google Reviews for Public Health Centers Budaya, I Gede Bintang Arya; Suniantara, I Ketut Putu
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 3 (2024): MALCOM July 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i3.1459

Sentiment analysis, or opinion mining, is a key area of natural language processing that identifies sentiments in free text. As digital business services grow and user-generated content increases, analyzing sentiments in online reviews is vital for enhancing business operations and customer satisfaction. This study focuses on sentiment analysis of user reviews from Google Reviews for Public Health Centers (PHCs) in Bali, Indonesia, using five machine learning models: Logistic Regression, Support Vector Machine (SVM), XGBoost, Naive Bayes, and Random Forest. These models classified sentiments into positive and negative categories using a dataset balanced with SMOTE to improve accuracy. We divided a total of 1.834 reviews, using 20% for testing and 80% for training, to ensure a thorough evaluation under real-world conditions. Logistic Regression and Naive Bayes performed best, both achieving an accuracy of 0.89, with Logistic Regression providing a balanced precision and recall. The study enhances academic understanding of sentiment analysis in healthcare and offers insights for business administrators on handling online customer feedback. The findings stress the importance of choosing suitable machine learning techniques based on specific data characteristics and project requirements to optimize both technological and business outcomes.

Pendampingan Proyek Videografi dalam Pengembangan Video Profil Sekolah di Sekolah Luar Biasa Negeri 1 Badung Agustino, Dedy Panji; Mahendra, I Nyoman Dwi Arysna; Budaya, I Gede Bintang Arya
Panrannuangku Jurnal Pengabdian Masyarakat Vol. 4 No. 3 (2024)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/panrannuangku2752

SLB Negeri 1 Badung adalah sekolah yang memfasilitasi pendidikan anak-anak berkebutuhan khusus, dengan tujuan mengembangkan pendidikan inklusif, dimana peran mitra luar sekolah mutlak diperlukan. Namun untuk mendapatkan mitra kolaborasi yang sesuai, sekolah memerlukan sebuah media informasi untuk menyampaikan program dan komiten sekolah secara efektif dan menarik. Video profil merupakan salah satu media informasi yang dapat digunakan. Oleh karena itu dalam kegiatan pengabdian kepada masyarakat ini dilaksanakan pendampingan proyek videografi untuk pengembangan video profil sekolah dengan metode pelaksanaan kegiatan dimulai dari perencanaan, pelatihan, produksi, evaluasi, dan publikasi. Kegiatan ini berhasil menghasilkan video profil hasil kolaborasi pihak sekolah dengan tim pengabdian masyarakat yang dapat menggambarkan komitmen dan program sekolah terhadap pendidikan inklusif dan pengembangan keterampilan siswa berkebutuhan khusus. Kegiatan ini menunjukkan pentingnya media visual dalam meningkatkan visibilitas dan daya tarik institusi pendidikan, serta memberikan inspirasi bagi sekolah lain dalam strategi promosi dan pengembangan keterampilan siswa serta membuka peluang kolaborasi bagi sekolah.

Application of Formal Concept Analysis and Clustering Algorithms to Analyze Customer Segments Budaya, I Gede Bintang Arya; Dharmendra, I Komang; Triandini, Evi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 2 (2025): April 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i2.6184

Business development cannot be separated from relationships with customers. Understanding customer characteristics is important both for maintaining sales and even for targeting new customers with appropriate strategies. The complexity of customer data makes manual analysis of the customer segments difficult, so applying machine learning to segment the customer can be the solution. This research implements K-Means and GMM algorithms for performing clustering based on the Transaction data transformed to the Recency, Frequency, and Monetary (RFM) data model, then implements Formal Concept Analysis (FCA) as an approach to analyzing the customer segment after the class labeling. Both K-Means and GMM algorithms recommended the optimal number of clusters as the customer segment is four. The FCA implementation in this study further analyzes customer segment characteristics by constructing a concept lattice that categorizes segments using combinations of High and Low values across the RFM attributes based on the median values, which are High Recency (HR), Low Recency (LR), High Frequency (HF), Low Frequency (LF), High Monetary (HM), and Low Monetary (LM). This characteristic can determine the customer category; for example, a customer that has HM and HR can be considered a loyal customer and can be the target for a specific marketing program. Overall, this study demonstrates that using the RFM data model, combined with clustering algorithms and FCA, is a potential approach for understanding MSME customer segment behavior. However, special consideration is necessary when determining the FCA concept lattice, as it forms the foundation of the core analytical insights.

Comparison of the DBSCAN Algorithm and Affinity Propagation on Business Incubator Tenant Customer Segmentation Agustino, Dedy Panji; Budaya, I Gede Bintang Arya; Harsemadi, I Gede; Dharmendra, I Komang; Pande, I Made Suandana Astika
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 12 No. 2 (2023): JULI
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v12i2.1682

The increasingly complex business environment necessitates businesses to design more effective and efficient strategies for company development, including market expansion. To understand customer behaviors, customer data analysis becomes crucial. One common approach used to group customers is segmentation based on RFM analysis (Recency, Frequency, and Monetary). This study aims to compare the performance of two clustering algorithms, namely DBSCAN and Affinity Propagation (AP), in providing customer profile segment recommendations using RFM analysis. DBSCAN algorithm is employed due to its ability to identify arbitrarily shaped clusters and handle data noise. On the other hand, Affinity Propagation (AP) algorithm is chosen for its capability to discover cluster centers without requiring a pre-defined number of clusters. The transaction dataset used in this research is obtained from one of the business incubator tenants at STIKOM Bali. The dataset undergoes preprocessing steps before being segmented using both DBSCAN and AP algorithms. Performance evaluation of the algorithms is conducted using the Silhouette Scores and Davies-Bouldin Index (DBI) matrices. The research findings indicate that the AP algorithm outperforms DBSCAN in this customer segmentation case. The AP algorithm yields Silhouette Scores of 0.699 and DBI of 0.429, along with recommendations for 4 customer segments. Furthermore, further analysis is performed on the AP results using a statistical approach based on the mean values of each segment for the RFM variables. The four customer segments generated by the AP algorithm, based on the mean values of the RFM variables, can be associated with the concept of customer relationship management.

Operational Optimization through the Development of a Digital Financial Transaction Recording Website in Village Owned Enterprise Sarwada Amerta, Taro Village: Optimalisasi Operasional melalui Pengembangan Website Pencatatan Transaksi Keuangan Digital di BUMDesa Sarwada Amerta Desa Taro Kusuma, Tubagus Mahendra; Budaya, I Gede Bintang Arya; Pande, I Made Suandana Astika; Dharmendra, I Komang
Mattawang: Jurnal Pengabdian Masyarakat Vol. 4 No. 2 (2023)
Publisher : Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.mattawang1821

In this community services activity, mentoring and implementation of a digital financial transaction recording system were conducted in village owned enterprise (VOE) Sarwada Amerta, Taro Village. The findings of this study demonstrate that the utilization of financial transaction information systems can optimize the financial operational processes of VOE. The efficiency and accuracy of financial data processing have improved, and the accessibility of financial information has become easier. However, it was found that the adaptation to the new information system still requires time for the human resources to consistently utilize the system. Strong support and commitment from relevant stakeholders, along with continuous educational efforts, are crucial factors in ensuring the successful implementation of the information system. This community services activity is expected to contribute to the economic development of the village through financial management education for VOE and by encouraging the utilization of information technology in local business financial management. Abstrak Pada kegiatan pengabdian masyarakat ini, dilakukan pendampingan dan implementasi sistem pencatatan keuangan digital di BUMDesa Sarwada Amerta, Desa Wisata Taro. Berdasarkan hasil dari kegiatan ini menunjukkan bahwa penggunaan sistem informasi pencatatan transaksi keuangan dapat mengoptimalkan proses operasional BUMDesa, khususnya dalam bidang keuangan. Efisiensi dan akurasi dalam pengolahan data keuangan meningkat, serta aksesibilitas informasi keuangan menjadi lebih mudah. Namun, ditemukan bahwa adaptasi terhadap sistem informasi yang baru masih memerlukan waktu bagi sumber daya manusia BUMDesa agar dapat menggunakan sistem dengan konsisten. Dukungan dan komitmen yang kuat dari pihak terkait, serta upaya edukasi yang berkelanjutan, menjadi faktor penting dalam memastikan keberhasilan implementasi sistem informasi ini. Kegiatan pengabdian ini diharapkan memberikan kontribusi dalam pengembangan ekonomi desa dengan edukasi manajemen keuangan BUMDesa serta mendorong pemanfaatan teknologi informasi dalam pengelolaan keuangan usaha di tingkat lokal.

A Comparative Analysis of Character and Word-Based Tokenization for Kawi-Indonesian Neural Machine Translation Budaya, I Gede Bintang Arya; Yusadara, I Gede Putra Mas
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11283

Preserving regional languages is a strategic step in preserving cultural heritage while expanding access to knowledge across generations. One approach that can support this effort is the application of automatic translation technology to digitize and learn local language texts. This study compares two tokenization strategies, word-based and character-based on a Kawi–Indonesian translation model using the FLAN-T5-Small Transformer architecture. The dataset used consists of 4,987 preprocessed sentence pairs, trained for 10 epochs with a batch size of 8. Statistical analysis shows that Kawi texts have an average length of 39.6 characters (5.4 words) per sentence, while Indonesian texts have an average length of 54.9 characters (7.5 words). These findings suggest that Kawi sentences tend to be lexically dense, with low word repetition and high morphological variation, which can increase the learning complexity of the model. Evaluation using BLEU and METEOR metrics shows that the model with word-based tokenization achieved a BLEU score of 0.45 and a METEOR score of 0.05, while the character-based model achieved a BLEU score of 0.24 and a METEOR score of 0.04. Although the dataset size has increased compared to previous studies, these results indicate that the additional data is not sufficient to overcome the limitations of the semantic representation of the Kawi language. Therefore, this study serves as an initial baseline that can be further developed through subword tokenization approaches, dataset expansion, and training strategy optimization to improve the quality of local language translations in the future.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search