Article Per Year (5 Year)
p-Index From 2021 - 2026
0.92
P-Index
This Author published in this journals
All Journal Jurnal Media Infotama Indonesian Journal of Data and Science Tematik : Jurnal Teknologi Informasi Komunikasi Journal Transformation of Mandalika Journal of Social Work and Empowerment
Wayan Gede Suka Parwita
Politeknik Negeri Bali
Aerospace Engineering Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Medicine & Pharmacology Physics Social Sciences Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Perancangan Desain Kemasan Produk UMKM Desa Jatiluwih Wayan Gede Suka Parwita; Eldian Rinaldi; Luh Kemala Putri Widhiari; Ni Putu Ritra Trees Ari Kartika Hadi Saraswati; Ketut Vini Elfarosa
Journal of Social Work and Empowerment Vol 4 No 3 (2025): Vol 4 No 3 (2025): Journal of Social Work and Empowerment - (Mei- Juli 2025)
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/jswe.v4i3.860

Abstract

Desa Jatiluwih, yang tersohor dengan keindahan sawah teraseringnya, merupakan destinasi wisata unggulan yang telah ditetapkan sebagai Warisan Budaya Dunia oleh UNESCO. Desa ini memiliki berbagai produk unggulan bernilai ekonomi tinggi seperti beras organik, kopi dan teh lokal, serta kerajinan tangan berbahan bambu yang sangat potensial untuk dikembangkan di pasar ekowisata dan produk ramah lingkungan. Namun, potensi tersebut belum sepenuhnya dimanfaatkan, khususnya dalam aspek pengemasan produk. Tanpa dukungan desain kemasan yang profesional, informatif, dan menarik, produk-produk lokal akan sulit bersaing di pasar global, meskipun memiliki kualitas yang tinggi. Menyikapi hal tersebut, kegiatan pengabdian kepada masyarakat ini berfokus pada perancangan desain kemasan sebagai strategi peningkatan daya saing UMKM Desa Jatiluwih. Hasil kegiatan menunjukkan kontribusi dalam memperkuat identitas visual dan meningkatkan nilai jual produk lokal. Lima mitra UMKM dari sektor pertanian dan pengolahan makanan mendapatkan rancangan desain kemasan produk yang lengkap (primer, sekunder, dan tersier), yang dirancang sesuai dengan karakteristik unik masing-masing produk.
Analisis implementasi triple bottom line pada program corporate social responsibility di the patra bali resort & villas I Komang Arif Cahya Pradana; I Komang Mahayana Putra; Wayan Gede Suka Parwita
Journal Transformation of Mandalika, e-ISSN: 2745-5882, p-ISSN: 2962-2956 Vol. 7 No. 6 (2026)
Publisher : Institut Penelitian dan Pengembangan Mandalika Indonesia (IP2MI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/jtm.v7i6.6557

Abstract

This study aims to analyze the implementation of the Triple Bottom Line concept (People, Planet, Profit) in Corporate Social Responsibility (CSR) programs at The Patra Bali Resort & Villas and to identify the challenges faced in its implementation. This research employs a qualitative method with a descriptive approach. The data sources used in this study consist of primary and secondary data. Data collection techniques were conducted through observation, interviews, and documentation involving parties directly engaged in CSR program implementation. Interviews were conducted with the Training Manager, HCBP Hospitality, and CSR program beneficiaries to obtain comprehensive information regarding program implementation.The results indicate that The Patra Bali Resort & Villas has implemented CSR programs that reflect the three dimensions of the Triple Bottom Line. In the People dimension, the company carries out social empowerment programs such as employing persons with disabilities and organizing blood donation activities. In the Planet dimension, the company implements environmental sustainability initiatives, including eco-enzyme waste management and the empowerment of local salt farmer groups. Meanwhile, in the Profit dimension, the company conducts training and certification programs for local tour guides, contributing to long-term economic sustainability.However, several challenges remain, including the absence of structured impact measurement indicators and limitations in continuous monitoring and evaluation of CSR programs.
Analisis Algoritma Machine Learning untuk Gagal Jantung dengan Interpretability SHAP dan LIME I Gede Sugita Aryandana; Leni Anggraini Susanti; Putu Eka Suryadana; Wayan Gede Suka Parwita
TEMATIK Vol. 12 No. 2 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i2.2627

Abstract

Kesehatan adalah keadaan sejahtera secara fisik, mental, dan sosial yang memungkinkan setiap individu dapat menjalani kehidupan secara produktif. Di antara berbagai dimensi kesehatan, kesehatan fisik menjadi aspek yang paling fundamental karena berperan penting dalam menjaga kualitas hidup manusia. Salah satu indikator utama dari kesehatan fisik adalah fungsi jantung, yang memiliki peran vital dalam mendukung aktivitas dan kinerja tubuh. Gangguan pada fungsi jantung tidak hanya berdampak pada kondisi fisik, tetapi juga dapat memengaruhi kesejahteraan mental dan sosial individu sehingga menyebabkan gagal jantung. Untuk mendeteksi gagal jantung secara dini, diperlukan penelitian dalam penerapan algoritma Machine Learning sebagai metode analisis yang dapat mendukung ketepatan serta efisiensi dalam proses diagnosis. Instrumen yang digunakan dalam algoritma Machine Learning adalah SHAP dan LIME, dengan memanfaatkan dataset medis pasien penderita gagal jantung sebagai objek analisis. Hasil penelitian ini bahwa algoritma random forest merupakan algoritma terbaik dalam memprediksi resikok gagal jantung. Hasil accuracy dari algoritma random forest menunjukkan nilai sebesar 0.8334 secara keseluruhan diikuti dengan nilai rata-rata precission sebesar 0,8125, nilai rata-rata recall sebesar 0,793, nilai rata-rata f1-scorenya sebesar 0,8015 dan nilai UACnya sebesar 0.90. Berdasarkan hasil klasifikasi selanjutnya dilakukan interpretability metode SHAP dan LIME. Hasil metode SHAP memberikan gambaran mendalam mengenai pengaruh variabel utama seperti time, serum creatinine, ejection fraction, dan age terhadap risiko gagal jantung. Hasil metode LIME memberikan hasil secara lokal yang artinya dalam kasus ini, metode LIME menyoroti serum creatinine sebagai variabel utama yang meningkatkan prediksi kematian.
Hybrid Deep Learning Models For Gold Price Prediction: Enhancing Forecast In Volatile Financial Markets Ni Luh Wiwik Sri Rahayu Ginantra; Ni Wayan Yeni Pratiwi; Christina Purnama Yanti; Wayan Gede Suka Parwita
Indonesian Journal of Data and Science Vol. 7 No. 2 (2026): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v7i2.394

Abstract

Introduction: Gold is widely regarded as a long-term store of value and a hedge against inflation, yet its short-term price volatility creates significant challenges for investment decision-making and requires accurate forecasting methods. This study evaluates a hybrid deep learning approach combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to capture both short-term fluctuations and long-term temporal dependencies in gold price movements. Method: Historical daily gold closing-price data comprising 2,735 observations from 2015 to 2025 were collected and normalized using Min-Max Scaling. The data were divided chronologically into 80% training and 20% testing sets. A hybrid CNN–LSTM model was trained using the Adam optimizer with a learning rate of 0.0001, dropout of 0.2, a timestep of 30, and batch sizes of 16, 32, and 64. Model performance was evaluated using Root Mean Square Error (RMSE). Results and Discussion: The batch size of 16 achieved the best performance, producing the lowest validation RMSE of 0.0929 and an RMSE of 11.518535% after denormalization, outperforming batch sizes of 32 and 64. The model also followed actual gold-price trends more closely, while the inclusion of Dense and Dropout layers improved generalization. Conclusion: The CNN–LSTM hybrid model, particularly with a batch size of 16, provides an effective approach for forecasting volatile gold prices by integrating local pattern extraction with long-term temporal modeling.
Analisis Pemanfaatan E-Learning dalam Proses Pengajaran: Studi Kasus Dosen CPNS Politeknik Negeri Bali Putu Eka Suryadana; Ni Putu Ritra Trees Ari Kartika Hadi Saraswati; Wayan Gede Suka Parwita; I Gede Sugita Aryandana
Jurnal Media Infotama Vol 21 No 1 (2025): April 2025
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v21i1.7935

Abstract

New lecturers at the Bali State Polytechnic can utilize a learning management system (LMS) to improve online teaching. This system supports various academic functions, such as providing access to resources, sending assignments, and creating interactive learning experiences. However, E-learning has the potential for over-reliance on technology, which can reduce traditional teaching methods and personal interaction in the classroom. This research aims to analyze the use of e-learning in the teaching process for CPNS 2024 lecturers at the Bali State Polytechnic. The research used a questionnaire with a Likert scale with a sample of 30 CPNS 2024 lecturers who had no experience as lecturers. The results of the questionnaire responses were tested for validity and reliability to ensure that the data processed was valid data. The validity test results show that all the questions tested are valid and the reliability results show a Cronbach alpha value of 0.736 and is included in the high category. Meanwhile, the results of processing the USE questionnaire by calculating the average percentage score for each factor include: usability 96%, convenience 89.5% and satisfaction 94%. A questionnaire designed to measure the usefulness of e-learning for new lecturers has proven to be valid and reliable. The results of the questionnaire show that e-learning really helps CPNS 2024 lecturers in delivering material and managing lecture assignments effectively.
Co-Authors Christina Purnama Yanti Eldian Rinaldi I Gede Sugita Aryandana I Komang Arif Cahya Pradana I Komang Mahayana Putra Ketut Vini Elfarosa Leni Anggraini Susanti Luh Kemala Putri Widhiari Ni Luh Wiwik Sri Rahayu Ginantra Ni Putu Ritra Trees Ari Kartika Hadi Saraswati Ni Wayan Yeni Pratiwi Putu Eka Suryadana