Claim Missing Document
Check
Articles

Found 31 Documents
Search

Kombinasi Metode SVM Dengan Optimasi SMOTE Terhadap Ulasan Pengguna Layanan Streaming Ni Putu Anik Juniantini; Yanti, Christina Purnama; Nilawati, Ni Ketut Utami
TEMATIK Vol 11 No 2 (2024): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2024
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v11i2.2068

Abstract

The development of digital technology has changed media consumption patterns in Indonesia, with streaming services like Disney+ Hotstar becoming increasingly popular. Since its launch in 2020, Disney+ Hotstar has offered exclusive content from Marvel, Pixar, Disney, National Geographic and others, quickly capturing the market in Indonesia. However, this service is not without controversy, particularly regarding certain content deemed to conflict with social values in Indonesia. Additionally, service quality, subscription prices, and content availability are also concerns for users. The difference in ratings on the Play Store (1.7) and the App Store (4.8) indicates a disparity in user satisfaction between the two platforms. This study aims to analyze user sentiment towards Disney+ Hotstar, particularly regarding reviews on the Play Store and App Store. Using a classification model with Support Vector Machine (SVM), optimized with the Synthetic Minority Over-Sampling Technique (SMOTE) to address data imbalance. Based on the analysis of 1,650 datasets, user sentiment tends to be neutral, as measured using the Vader Lexicon. The method testing results show that SMOTE optimization can improve the performance of the SVM model, with an accuracy increase of +0.7 on Play Store reviews from 0.67 to 0.74, and an accuracy increase of +0.11 on App Store reviews from 0.72 to 0.83 In conclusion, the SVM method optimized with SMOTE has proven effective in improving the accuracy of sentiment classification in user reviews of Disney+ Hotstar.
Sistem Pendukung Keputusan Penerimaan Tenaga Unit Medis di RS Ari Canti dengan Metode Topsis Wiwik Sri Rahayu Ginantra, Ni Luh; Yanti, Christina Purnama; Toraja, Dewa Gede
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 2 (2020): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v4i2.257

Abstract

Ari Canti Hospital selectively conducts selection in the company environment that is by selecting one by one application then do some test on applicants with several criteria. With a large number of applicants making the selection process takes a lot of time and effort, as well as applicant data and the outcomes of the applicants are not well archived. Based on the above problems, need a solution to problem-solving by making a Decision Support System to determine the appropriate applicants to become new employees by facilitating the selection of employees by predetermined criteria. The TOPSIS method is chosen because this method is a form of decision support method based on the concept that the best alternative not only has the shortest distance from the ideal solution but also has the longest distance Of the ideal solution. The result of the design of this Decision Support System is the system has been able to generate reports from the applicant rank calculation by the values that have been obtained on the criteria that have been determined. The calculation results of the Decision Support System is already by the calculations performed manually.
Sistem Pendukung Keputusan Penerimaan Tenaga Unit Medis di RS Ari Canti dengan Metode Topsis Wiwik Sri Rahayu Ginantra, Ni Luh; Yanti, Christina Purnama; Toraja, Dewa Gede
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 2 (2020): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v4i2.257

Abstract

Ari Canti Hospital selectively conducts selection in the company environment that is by selecting one by one application then do some test on applicants with several criteria. With a large number of applicants making the selection process takes a lot of time and effort, as well as applicant data and the outcomes of the applicants are not well archived. Based on the above problems, need a solution to problem-solving by making a Decision Support System to determine the appropriate applicants to become new employees by facilitating the selection of employees by predetermined criteria. The TOPSIS method is chosen because this method is a form of decision support method based on the concept that the best alternative not only has the shortest distance from the ideal solution but also has the longest distance Of the ideal solution. The result of the design of this Decision Support System is the system has been able to generate reports from the applicant rank calculation by the values that have been obtained on the criteria that have been determined. The calculation results of the Decision Support System is already by the calculations performed manually.
Optimizing convolutional neural networks-based ensemble learning for effective herbal leaf disease detection Ginantra, Ni Luh Wiwik Sri Rahayu; Yanti, Christina Purnama; Ariantini, Made Suci
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i2.pp2416-2426

Abstract

This study aims to optimize convolutional neural networks (CNN)-based ensemble learning models to enhance accuracy and stability in detecting herbal leaf diseases. The dataset used in this study is sourced from the “Lontar Taru Pramana” collection, which includes various images of herbal leaves affected by different diseases such as Ancak Bacterial Spot, Dapdap Mosaic Virus, and Kelor Powdery Mildew. Several CNN models, including VGG16, AlexNet, ResNet50, DenseNet121, MobileNetV2, and InceptionV2, were evaluated. Among these, the ensemble models combining VGG16, DenseNet121, and MobileNetV2 were selected due to their superior performance. The ensemble model achieved precision scores of 0.81 for class 1, 0.76 for class 2, and 0.78 for class 3, with corresponding recall scores of 0.8167, 0.74, and 0.7633, and F1-scores of 0.8133, 0.75, and 0.7717 respectively. These results indicate significant improvements in model performance and robustness.
Mengenal Aksara Bali: Balinese Script game education based on mobile application I Gede Andika; Daniel Eka Saputra; Christina Purnama Yanti; Gede Indrawan
Journal of Games, Game Art, and Gamification Vol. 4 No. 1 (2019): Special Issue: International Conference of Games, Game Art and Gamification (IC
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/jggag.v4i1.7240

Abstract

Balinese Scriptwriting, as one of Balinese cultural richness, is going to extinct because of its decreasing use. Governor of Bali, I Wayan Koster, expressed concern about the increasingly diminishing interest of the community, especially among the younger generation using it. This research focused on the development of a Balinese Script game education based on a mobile application called Mengenal Aksara Bali. In this research area, Mengenal Aksara Bali offered a solution as an application that is not only for playing,but also provided features for learning Balinese Script glyphs (Aksara Wresastraand numbers). Mengenal Aksara Bali was implemented by using Construct2(a powerful game creator designed especially for 2D games). Through Black Box testing, its functions in the application wasrunning as expected
Implementasi Aplikasi Buku Kas Untuk Menunjang Kompetensi Siswa Jurusan Akuntansi Ni Luh Wiwik Sri Rahayu Ginantra; Christina Purnama Yanti; Theresia Hendrawati
Darma Abdi Karya Vol. 3 No. 2 (2024): Darma Abdi Karya: Jurnal Pengabdian Kepada Masyarakat
Publisher : LPPM POLITEKNIK LP3I

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/darmaabdikarya.v3i2.2167

Abstract

At this time, people are more directed towards consumptive behavior in living their daily lives. The same is true for teenagers, the majority of whom follow a lifestyle in accordance with current trends. By following this trend, it is certain that adolescents will spend more money and not commensurate with existing income. Similarly, students at SMK Dwijendra Denpasar majoring in Accounting have problems where students are difficult to manage their personal finances. With our community service activities, it is hoped that it can help students in terms of a good financial management system and can improve skills and knowledge about how to manage personal finances so that later in the world of work it is expected to be able to manage company finances. The output of this research is that students are able to identify and prioritize the main priorities for allocating their personal funds. In addition, students can feel financial security in meeting sudden needs, because they have sufficient savings in the future.
Blockchain Technology Model on Virtual Museum as an Effort to Enchance Balinese Cultural Metaverse Sudipa, I Gede Iwan; Aditama, Putu Wirayudi; Yanti, Christina Purnama
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.972

Abstract

The preservation of cultural heritage in the digital era faces numerous challenges, particularly in securing authenticity, ownership, and preventing damage or loss of digital assets. This study explores the implementation of blockchain technology within a virtual museum dedicated to Balinese culture as part of the broader metaverse environment. Blockchain provides a decentralized and immutable system to record and manage digital cultural assets, ensuring transparency and security in their provenance and ownership. This paper presents a blockchain model for a virtual museum that includes features such as digital tokens and smart contracts, enabling automated processes such as the lending, licensing, and sale of digital artifacts. The integration of this model with metaverse technology creates an interactive and immersive environment for users to explore Balinese culture virtually, while simultaneously ensuring the preservation of its digital representations. The model is developed using the Rapid Application Development (RAD) methodology, enabling quick prototyping and system adjustments based on user requirements. Testing results demonstrate the system's functional success in terms of blockchain transactions and user interaction in the virtual environment. Despite challenges such as regulatory and infrastructural constraints, the findings indicate that the blockchain model has strong potential for application in digital heritage preservation. This study concludes by highlighting the benefits of blockchain in securing cultural assets and its role in promoting the Balinese digital economy through cultural tourism and virtual experiences.
Classification of Cavendish Banana Ripeness With CNN Method Tjokorda Istri Agung Pandu Yuni Maharani; I Gusti Agung Indrawan; Gede Dana Pramitha; Christina Purnama Yanti; I Made Marthana Yusa
Indonesian Journal of Data and Science Vol. 6 No. 2 (2025): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v6i2.259

Abstract

Cavendish bananas are one of the most widely consumed tropical fruits in Indonesia due to their sweet taste and high nutritional content. However, as they ripen, the sugar content in bananas increases, which can be a problem for diabetics. To help diabetics choose bananas with the right level of ripeness, this study developed a Cavendish banana ripeness classification model using artificial intelligence technology, namely the ResNet50 Convolutional Neural Network (CNN) architecture. The banana data is divided into five ripeness categories: green, yellowish green, yellow, spotted yellow, and spotted brownish yellow. The model was trained with two approaches, with and without data augmentation, using two types of training algorithms (optimizers), namely Adam and SGD, as well as a k-fold cross-validation method to ensure accurate results. The results showed that the ResNet50 model produced the highest accuracy of 98% when trained using data augmentation and the Adam optimizer with a learning rate setting of 0.0001.
MARKERLESS AUGMENTED REALITY UNTUK PEMBELAJARAN SISTEM SARAF PUSAT Yanti, Christina Purnama; Wulandari, Dewa Ayu Putri; Putra S., I Ketut Yama Cahyana
JEIS: Jurnal Elektro dan Informatika Swadharma Vol 5, No 2 (2025): JEIS EDISI JULI 2025
Publisher : Institut Teknologi dan Bisnis Swadharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56486/jeis.vol5no2.777

Abstract

The research aims to design and build a learning media application for the Human Central Nervous System at SMA Negeri 1 Pupuan, utilizing Augmented reality technology. This Augmented reality provides students with a new experience that seems practical and effective in supporting learning activities. The Augmented reality method used in the research is Markerless (i.e., without markers). After designing the application, Black Box Testing was carried out, material expert testing with results of 96% in the strongly agree category, as well as UEQ testing with the Attractiveness value (allure) of 1.88 in the outstanding category, Perspicuity (Clarity/Readability) of 1.81 in the good category, Efficiency of 1.85 in the good category, Dependability (Reliability) of 1.91 in the outstanding category, and Stimulation of 1.98 in the exceptional category. Good and structured system design, careful testing of the application, and positive user responses show that the application has the potential to become a learning medium that can support learning activities in the Central Nervous System material.Penelitian ini bertujuan untuk merancang dan membangun aplikasi media pembelajaran Sistem Saraf Pusat Manusia pada SMA Negeri 1 Pupuan, dengan memanfaatkan teknologi Augmented Reality. Hal ini memberikan pengalaman yang baru pada siswa yang terkesan praktis dan efektif untuk mendukung kegiatan pembelajaran. Metode yang digunakan dalam penelitian adalah MDLC (Multimedia Development Life Cycle). Setelah perancangan aplikasi, dilakukan pengujian Black Box Testing, pengujian ahli materi dengan hasil 96% dalam kategori sangat setuju, serta pengujian UEQ dengan nilai Attractiveness (Daya Tarik) sebesar 1,88 dengan kategori sangat baik, Perspicuity (Kejelasan/Keterbacaan) sebesar 1.81 dengan kategori baik, Efficiency (Efisiensi) sebesar 1,85 dengan kategori baik, Dependability (Keandalan) sebesar 1,91 dengan kategori sangat baik, dan Stimulation (Stimulasi) sebesar 1,98 dengan kategori sangat baik. Hasil pengujian diatas menunjukan bahwa aplikasi berpotensi dalam menjadi sebuah media pembelajaran yang bisa mendukung kegiatan pembelajaran dalam materi Sistem Saraf Pusat.
PKM DESCRIPTIVE ANALYSIS PADA ELY’S CAFE ADIWANA UNAGI SUITE Saraswati, Ni Wayan Sumartini; Muku, I Dewa Made Krishna; Suryawan, I Wayan Dharma; Martarini, Ni Made Lisma; Novitasari, Dwi; Nirwana, Ni Kade Ayu; Agetania, Ni Luh Putu; Yanti, Christina Purnama; Waas, Devi Valentino; Marlinda, Ni Luh Putu Mery; Juniartini, Ni Komang Tri
Jurnal Widya Laksmi: Jurnal Pengabdian Kepada Masyarakat Vol. 3 No. 2 (2023): Jurnal WIDYA LAKSMI (Jurnal Pengabdian Kepada Masyarakat)
Publisher : Yayasan Lavandaia Dharma Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59458/jwl.v3i2.61

Abstract

Di tengah persaingan yang makin ketat, Business Intelligence (BI) menjadi solusi dalam tantangan bisnis perusahaan yang lebih solutif. BI dalam prosesnya memanfaatkan data historis yang selalu bertumbuh semakin banyak. Dengan BI perusahaan dapat memiliki strategi yang lebih kuat dan pengambilan keputusan yang lebih matang. Penelitian ini membangun BI pada Adiwana Unagi Suites yang menghasilkan visualisasi data untuk mengambil keputusan yang tepat. Adapun tool yang digunakan adalah Tableau, software BI dan visualisasi data yang cepat, powerful, dan efektif digunakan. Dari penelitian ini, dihasilkan tujuh visualisasi data berdasarkan pertanyaan yang telah dikemukakan terlebih dahulu untuk membantu strategi bisnis. Adapun hasilnya berupa visualisasi data dengan berbagai bentuk grafik, seperti butterfly bar chart, vertical bar chat, line chart, tabel pivoting, serta box plot.