Garuda - Garba Rujukan Digital

Pembangkitan Kode Sampa MBROLA untuk Lirik Pupuh Pucung Berdasarkan Padalingsa dan Diftong I Putu Eka Giri Gunawan; I Gusti Agung Indrawan
Techno.Com Vol 19, No 2 (2020): Mei 2020
Publisher : LPPM Universitas Dian Nuswantoro

Kurangnya minat masyarakat untuk belajar tembang bali akan mengakibatkan semakin hilangnya budaya bali. Salah satu faktor peyebab kurang tertarik nya masyarakat untuk belajar tembang bali adalah media pembelajaran tembang bali yang kurang menarik dan tidak interaktif. Pupuh pucung merupakan salah satu bagian dari sekar alit yang merupakan bagian tembang bali. Sekar alit/pupuh memiliki aturan dalam penulisan liriknya yang disebut dengan padalingsa yang terdiri dari guru wilangan yaitu jumlah suku kata dalam setiap barisnya, guru dingdong yaitu huruf vokal pada kata terakhir setiap barisnya dan guru gatra yaitu jumlah baris dalam satu baitnya. Penelitian ini akan menciptakan suatu aplikasi yang interaktif yang bisa digunakan untuk mencoba lirik dari pupuh pucung sesuai dengan aturan padalingsa pupuh pucung. Penelitian ini membahas bagaimana analisis dan konversi lirik pupuh pucung ke kode sampa yang digunakan di program sintesis suara MBROLA. Hasil dari penelitian ini adalah kode sampa MBROLA yang dibangkitkan berdasarkan aturan padalingsa dan diftong bahasa bali.

Prosodic Analysis of Pupuh Pucung using Mbrola Speech Synthesis Application I Gusti Agung Indrawan; I Putu Eka Giri Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 5, No 5 (2022): February
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v5i5.187

Pupuh Pucung is one part of the sekar alit which is part of the Balinese song. Sekar alit/pupuh has a rule in writing lyrics called padalingsa, which consists of guru wilangan, namely the number of syllables in each line, guru dingdong, which is the vowel in the last word of each line and guru gatra, which is the number of lines in one stanza. This study discusses how the text-to-speech application can help in developing pupuh pucung. Text to speech is an application that converts text into sound. In this research, an application design that can sing Pupuh Pucung's lyrics was developed with the concept of text to sing. This study uses the mbrola application as a text-to-speech converter. The analysis results, namely the frequency of the fundamental tone, aim to determine each phoneme's initial frequency in Pupuh Pucung. With the initial frequency, it will shorten the range of subsequent prosodic observations. The use of pupuh pucung's fundamental tone as a guide for the formation of prosody can be used as an initial guide in forming pupuh pucung's prosody.

Peramalan Jumlah Kunjungan Wisatawan Menggunakan Triple Exponential Smoothing I Wayan Agus Surya Darma; I Putu Eka Giri Gunawan; Ni Putu Sutramiani
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol. 8, No. 3, December 2020
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2020.v08.i03.p06

Bali merupakan salah satu destinasi pariwisata terbaik di dunia. Berdasarkan berita resmi statistik yang dipublikasikan oleh Badan Pusat Statistik Bali, jumlah kunjungan wisatawan mancanegara ke Bali pada bulan Juni 2019 mencapai 549.751 kunjungan. Peramalan kunjungan wisatawan merupakan faktor yang sangat penting untuk menentukan kebijakan tempat tujuan wisata, meminimalkan ketidakpastian dan resiko investasi. Hal ini merupakan hal yang sangat penting karena sektor pariwisata merupakan tulang punggung ekonomi di Bali. Penelitian ini mengangkat topik bagaimana mengimplementasikan metode Triple Exponential Smoothing pada proses peralaman jumlah wisatawan. Kami menggunakan data historis kunjungan wisatawan ke Bali yang diperoleh dari Badan Pusat Statistik Provinsi Bali. Hasil peramalan dievaluasi menggunakan mean absolute error untuk menunjukan rata-rata kesalahan dalam perhitungan peramalan. Rata-rata Mean Absolute Error yang dihasilkan pada peramalan ini adalah 18 dengan hasil evaluasi terbaik dengan menggunakan Alpha 0.9, Beta 0 dan Gamma 0.8.

Prosodic Analysis of Pupuh Pucung using Mbrola Speech Synthesis Application I Gusti Agung Indrawan; I Putu Eka Giri Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 5, No 5 (2022): February
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Pupuh Pucung is one part of the sekar alit which is part of the Balinese song. Sekar alit/pupuh has a rule in writing lyrics called padalingsa, which consists of guru wilangan, namely the number of syllables in each line, guru dingdong, which is the vowel in the last word of each line and guru gatra, which is the number of lines in one stanza. This study discusses how the text-to-speech application can help in developing pupuh pucung. Text to speech is an application that converts text into sound. In this research, an application design that can sing Pupuh Pucung's lyrics was developed with the concept of text to sing. This study uses the mbrola application as a text-to-speech converter. The analysis results, namely the frequency of the fundamental tone, aim to determine each phoneme's initial frequency in Pupuh Pucung. With the initial frequency, it will shorten the range of subsequent prosodic observations. The use of pupuh pucung's fundamental tone as a guide for the formation of prosody can be used as an initial guide in forming pupuh pucung's prosody.

PIECES ANALYSIS IN THE INFLUENCE OF THE DESIGNING DIGITAL SIGNATURE CERTIFICATE SYSTEM Ida Bagus Gede Sarasvananda; I Putu Eka Giri Gunawan; I Komang Arya Ganda Wiguna; Made Suci Ariantini; I Gede Iwan Sudipa
Jurnal Mantik Vol. 6 No. 1 (2022): May: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Correspondence is an inseparable part of an agency, both private and government. The administration of correspondence has often utilized information system technology in assisting business processes carried out by parties within the organization itself. For example, the Institute for Innovation and Creativity Development (LPIK) of the Indonesian Institute of Business and Technology (INSTIKI) has implemented a correspondence information system, but there is a weakness in the system, namely that there is no digital signature process so that it is not optimal in facilitating the management of correspondence. This study aims to analyze the business processes of the system that is already running using the PIECES (Performance, Information, Economy, Control, Efficiency, Service) method. The benefits of the research are obtained from the analysis of the problems based on the previously running system seen from the use case diagram design, activity diagrams and system interfaces. This results in an analysis of the proposed system to complete system features and system functionality based on the results of the analysis of 6 aspects of PIECES which can assist LPIK institutions in facilitating the mailing business process.

Optimization Strategy on Deep Learning Model to Improve Fruit Freshness Recognition I Gusti Agung Indrawan; Putu Andy Novit Pranartha; I Wayan Agus Surya Darma; I Putu Eka Giri Gunawan
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol 14 No 1 (2023): Vol. 14, No. 1 April 2023
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2023.v14.i01.p01

The high fruit production during the harvest season is a challenge in the process of sorting fresh fruit and rotten fruit in plantations. Automatic fruit freshness classification based on deep learning can speed up the sorting process. However, building a model with high accuracy requires the right strategy based on the dataset's characteristics. This research aims to apply optimization strategies to deep learning models to improve model performance. The optimization strategy is implemented by optimizing the model using fine-tuning strategy by selecting the best parameters based on learning rate, optimizers, transfer learning, and data augmentation. The transfer learning process is applied based on the dataset's characteristics by training some parameters with a size of 30% and 60%, which were tested in four scenarios. The fine-tuning strategy is applied to three Deep Learning models, i.e., MobileNetv2, ResNet50, and InceptionResNetV2, which have various parameter sizes. Based on test results, fine-tuning strategy produces the best performance up to 100% with a learning rate of 0.01, the SGD optimizers on the InceptionResNetV2 model are trained on 60% of the parameters.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search