Article Per Year (5 Year)
p-Index From 2021 - 2026
2.509
P-Index
This Author published in this journals
All Journal Jurnal SPEKTRUM Vidyottama Sanatana: International Journal of Hindu Science and Religious Studies JUTIK : Jurnal Teknologi Informasi dan Komputer JURNAL PENDIDIKAN TAMBUSAI Jurnal Pelayanan dan Pengabdian Masyarakat (Pamas) Progresif: Jurnal Ilmiah Komputer International Journal of Engineering and Emerging Technology Indonesian Journal of Social and Environmental Issues (IJSEI) Jurnal Penelitian Agama Hindu Buletin Poltanesa Journal of Community Development Jurnal Teknik Gradien Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Jurnal Locus Penelitian dan Pengabdian Jurnal Abdi Daya Jurnal Bangkit Indonesia Scientica Education Journal (SEJ)
Wikan Pradnya Dana, Gde
Universitas Warmadewa
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Nursing Public Health Social Sciences

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Analisis Komparatif Unjuk Kerja Model Vision Transformers Dengan ConvNeXt Dalam Rekognisi Citra Warangka Keris Bali Ni Putu Widya Yuniari; Gde Wikan Pradnya Dana; I Gede Wira Darma
Progresif: Jurnal Ilmiah Komputer Vol 21, No 2 (2025): Agustus
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v21i2.2987

Abstract

The application of attention mechanisms in image recognition has emerged as a new paradigm in computer vision, serving as a foundational approach in generative AI. Two state-of-the-art models frequently referenced in recent studies are Vision Transformers (ViT), introduced by Google, and ConvNeXt, developed by Meta (Facebook) AI Research. However, their application in recognizing local cultural imagery, such as the warangka (sheath) of the Balinese keris, remains highly limited. The urgency of this study lies in evaluating the effectiveness of AI models in supporting technology-based cultural preservation. This study aims to compare the unjuk kerjance of these two models in handling the classification and recognition of warangka keris (Balinese kris sheaths). The methodology involves data augmentation, feature extraction, patch processing (for ViT), model construction, evaluation, and image recognition analysis using Grad-CAM. The dataset comprises a combination of primary and secondary sources. Primary data were collected through field visits to kris-making workshops in Bali, while secondary data were obtained from previous studies. The kris sheath image classes used in this study include: 'Sesrengatan', 'Kojongan', 'Batun Poh', 'Kekandikan', and 'Beblatungan'. The study successfully developed image classification models, achieving an accuracy of 82% with the ViT model and 97% with the ConvNeXt model. The recognition process effectively highlighted the most significant regions of each image, providing valuable insight for future generative AI research.Keywords: Attention, ConvNeXt, Keris Bali, Vision Transformers AbstrakPenerapan attention dalam rekognisi citra menjadi pendekatan baru dalam pengenalan gambar dan berpotensi menjadi benchmark dalam pengembangan kecerdasan buatan generatif. Dua model terkini yang banyak diteliti adalah Vision Transformers (ViT) dari Google dan ConvNeXt dari Meta AI. Namun, penerapan keduanya dalam pengenalan citra budaya lokal seperti warangka keris Bali masih sangat terbatas. Urgensi penelitian ini terletak pada upaya mengevaluasi efektivitas model kecerdasan buatan dalam mendukung pelestarian budaya berbasis teknologi. Penelitian ini bertujuan untuk membandingkan performa ViT dan ConvNeXt dalam klasifikasi serta rekognisi citra warangka keris Bali. Metode yang digunakan meliputi augmentasi data, ekstraksi fitur, proses patching (untuk ViT), pembuatan model, pengujian, serta analisis grad cam. Data yang digunakan merupakan gabungan data primer (hasil kunjungan ke workshop pembuatan keris Bali) dan data sekunder dari berbagai sumber. Citra keris yang digunakan antara lain: ‘Sesrengatan’, ‘Kojongan’, ‘Batun Poh’, ‘Kekandikan’, dan ‘Beblatungan’. Hasil menunjukkan akurasi 82% (ViT) dan 97% (ConvNeXt), serta bagian penting citra berhasil dikenali sebagai benchmark generatif.Kata kunci: Attention; ConvNeXt; Keris Bali; Vision Transformers
Analisis Unjuk Kerja Klasifikasi Citra Motif Kain Bali Menggunakan Model Inception Dan EfficientNet Ni Putu Widya Yuniari; I Made Surya Kumara; I Kadek Agus Wahyu Raharja; Gde Wikan Pradnya Dana; I Gede Wira Darma; I Made Adi Bhaskara
Progresif: Jurnal Ilmiah Komputer Vol 21, No 1 (2025): Februari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v21i1.2568

Abstract

Bali, with its rich culture and diverse symbolism reflected in the traditional fabric motifs. However, the manual recognition of Balinese fabric motifs faces challenges such as pattern complexity, similarity between motifs, and limited public knowledge. This study aims to address these challenges by using Artificial Intelligence (AI) to automate the process of accurately and efficiently identifying Bali fabric motifs. The research develops a motif recognition model for Bali fabrics using Inception V3 and EfficientNet B1 algorithms in image classification analysis. The research methodology used is experimental, starting with dataset collection, data augmentation, feature extraction, modeling, and testing. The results show that the EfficientNet model achieved an accuracy of 99% on the 25th iteration, much higher than Inception V3, which only achieved 62% accuracy. These results indicate that the EfficientNet model is more effective in recognizing and classifying Bali fabric motifs and strengthen the potential of artificial intelligence in cultural preservation.Keywords: Bali; Classification; EfficientNet; Inception; Pattern AbstrakBali, dengan kekayaan budaya yang kompleks serta beragam simbolisme. Salah satunya tercermin dalam rupa motif kain tradisional Bali. Namun, pengenalan manual motif kain Bali sering terhambat oleh tantangan seperti kerumitan pola, kesamaan antara motif, dan keterbatasan pengetahuan masyarakat. Penelitian ini bertujuan untuk mengatasi tantangan tersebut dengan menggunakan kecerdasan buatan (AI) untuk mengotomatisasi proses identifikasi motif kain Bali secara akurat dan efisien. Penelitian ini mengembangkan model pengenalan motif kain Bali dengan menggunakan algoritma Inception V3 dan EfficientNet B1 dalam analisis klasifikasi citra. Metode penelitian yang digunakan adalah eksperimen, dimulai dengan pengumpulan dataset, augmentasi data, ekstraksi fitur, pemodelan, dan pengujian. Hasil penelitian menunjukkan bahwa model EfficientNet B1 mencapai akurasi 99% pada iterasi ke-25, jauh lebih tinggi dibandingkan dengan Inception V3 yang hanya memperoleh akurasi 62%. Hasil ini menunjukkan bahwa model EfficientNet lebih efektif dalam mengenali dan mengklasifikasikan motif kain Bali serta memperkuat potensi kecerdasan buatan dalam pelestarian budaya.Kata kunci: Bali; EfficientNet; Inception; Klasifikasi; Motif
PEMANFAATAN TEKNOLOGI ARTIFICIAL INTELLIGENCE (AI) UNTUK ANALISIS TEKS VEDA: PENDEKATAN NLP DALAM STUDI ṚG VEDA MANDALA 1 SUKTA 1 Eka Sura Adnyana; Gde Wikan Pradnya Dana; I Made Ade Prayoga
Vidyottama Sanatana: International Journal of Hindu Science and Religious Studies Vol 9 No 2 (2025)
Publisher : UHN I Gusti Bagus Sugriwa Denpasar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25078/vidyottama.v9i2.5380

Abstract

This research discusses the utilization of Artificial Intelligence (AI) technology with a Natural Language Processing (NLP) approach in the study of Hindu literature, especially in the text of Ṛgveda Mandala 1 Sukta 1. The analysis was conducted through the stages of tokenization, lemmatization, and topic modeling to identify keywords, frequency of occurrence, and main themes in the text. The results found four central themes: (1) ritual (yajña), (2) theological (Agni's role as an intermediary between humans and gods), (3) spiritual and material goals (ratna), and (4) cosmic order (ṛta). AI  findings were then compared with traditional philological interpretations that emphasize philosophical meaning, symbolism, and historical context. The comparison results show that AI excels in speed, scale, and consistency of analysis, while traditional philology is stronger in providing depth of interpretation and understanding spiritual values. This study concludes that the integration of AI with the philological approach can result in a more comprehensive, rapid, and faithful study of the Vedas.
PENINGKATAN INFRASTRUKTUR DRAINASE PURA PEJENENGAN DADIA TEBEN DAYANG, DESA SIBETAN, KECAMATAN BEBANDEM, KAB. KARANGASEM I Made Kusuma Wiranata; Cokorda Agung Yujana; Gde Wikan Pradnya Dana
Jurnal Abdi Daya Vol. 5 No. 2 (2025): Jurnal Abdi Daya Vol.5 No.2 Tahun 2025
Publisher : Universitas Warmadewa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22225/jad.5.2.2025.11-20

Abstract

Program Pengabdian Kepada Masyarakat (PKM) ini berfokus pada peningkatan infrastruktur drainase di Pura Pejenengan Dadia Teben Dayang, Desa Sibetan, Kecamatan Bebandem, Kabupaten Karangasem, Bali. Wilayah ini menghadapi masalah genangan air, erosi tanah, dan pengelolaan air hujan yang tidak optimal akibat curah hujan tinggi dan permeabilitas tanah rendah, yang mengganggu aktivitas keagamaan dan kenyamanan masyarakat. Solusi utama adalah penerapan teknologi biopori, lubang resapan vertikal berbahan pipa PVC berdiameter 150 mm dengan lubang-lubang untuk meningkatkan infiltrasi air, mengurangi genangan, mencegah erosi, dan memanfaatkan sampah organik sebagai pupuk. Kegiatan meliputi survei awal, pengukuran, penyelidikan tanah, analisis data, desain titik biopori dan drainase, serta pemasangan bersama masyarakat. Hasil menunjukkan Kebutuhan Biopori pada lahan Pura ini yaitu 24 Buah dan akan dipasang 20 buah biopori dengan diameter 150 mm dengan dalam 1 meter, selain itu juga dikombinasikan dengan rekomendasikan titik pembuatan saluran drainase untuk memperecepat keluarnya limpasan air hujan di area pura. Program ini diharapkan meningkatkan kesiapsiagaan lingkungan, kelestarian pura, dan menjadi model pembangunan berkelanjutan. Rencana lanjutan: monitoring efektivitas dan ekspansi ke lokasi serupa.
Pemberdayaan Petani Alpukat di Desa Pempatan Bali melalui Inovasi Tongkat Panen Teleskopik Cerdas dan Sistem Monitoring Digital I Made Surya Kumara; Gde Wikan Pradnya Dana; Ni Luh Putu Putri Setianingsih
Journal of Community Development Vol. 6 No. 1 (2025): August
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v6i1.1733

Abstract

Pertanian memiliki peran strategis dalam perekonomian nasional, khususnya di negara agraris seperti Indonesia. Salah satu komoditas hortikultura bernilai ekonomi tinggi adalah alpukat, yang di Bali banyak dibudidayakan di Desa Pempatan, Kecamatan Rendang, Kabupaten Karangasem. Desa ini dikenal sebagai sentra produksi alpukat dengan hasil melimpah, namun masih menghadapi sejumlah permasalahan, seperti metode panen tradisional yang berisiko tinggi terhadap keselamatan kerja, terdapatnya tingkat kerusakan buah akibat jatuh, serta ketiadaan sistem pencatatan digital yang akurat untuk mendukung pengambilan keputusan. Program pengabdian ini dirancang untuk memberdayakan petani melalui penerapan inovasi tongkat panen teleskopik cerdas dan sistem monitoring panen berbasis web. Evaluasi efektivitas program dilakukan dengan metode pre-test dan post-test terhadap 16 kelompok tani. Hasil analisis menunjukkan adanya peningkatan pada aspek produksi, ditandai dengan percepatan waktu panen (56,2% responden menilai panen menjadi jauh lebih cepat), penurunan tingkat kesulitan (68,8% menyatakan cukup mudah dan 31,2% sangat mudah), serta berkurangnya kerusakan buah (87,5% responden melaporkan kerusakan sangat berkurang). Pada aspek manajemen, terjadi peningkatan kemampuan pencatatan digital, dengan 50% responden mulai mandiri atau dengan sedikit bantuan, serta penguatan persepsi manfaat pencatatan untuk akuntabilitas usaha tani. Temuan ini menunjukkan bahwa inovasi teknologi panen mampu meningkatkan efisiensi, kualitas hasil, dan tata kelola produksi alpukat.
Uncovering Algorithmic Avidyā in Generative AI: A Catur Pramāṇa Red Teaming Approach Gde Wikan Pradnya Dana; Putu Eka Sura Adnyana
Jurnal Penelitian Agama Hindu Vol 10 No 3 (2026)
Publisher : Jayapangus Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37329/jpah.v10i3.5435

Abstract

Western-centric AI ethics frameworks currently marginalize Hindu epistemology, triggering an epistemological crisis within spiritual domains. Addressing this, this study operationalizes the Balinese Hindu Catur Pramāṇa framework to empirically audit the Gita-GPT model, aiming to diagnose Algorithmic Avidyā (Algorithmic Ignorance) and formulate mitigation strategies. Using a qualitative epistemological red teaming methodology, 15 adversarial prompts nuanced with Balinese theology were executed, with outputs deductively analyzed against authoritative texts. The results emphatically demonstrate that the system systematically generates Algorithmic Avidyā through four fatal mechanisms. First, at the Śabda layer, the machine actively executes epistemic fabrication and hallucination of sacred verses. Second, at the Pratyakṣa layer, it causes severe context collapse by failing to recognize critical spatial-cultural boundaries (Desa-Kala-Patra). Third, at the Upamāṇa layer, it imposes materialistic comparative fallacies that distort theological analogies. Fourth, at the Anumāṇa layer, it constructs illusions of reasoning entirely devoid of causal spiritual awareness. Consequently, this study concludes that uncalibrated generative AI fundamentally disrupts authentic spiritual mediation, creating a representational hegemony that directly threatens traditional religious authority and erodes Balinese customary law (Dresta). To mitigate these severe ethical impacts and preserve the local religious ecosystem, we strongly advocate for a paradigm shift toward theological sovereignty. This requires constructing an endemic Nusantara Large Language Model, mandating Expert-in-the-Loop governance involving spiritual authorities (Sulinggih), and aligning Reinforcement Learning algorithms explicitly with Dharma principles.
The Effects of Youth Political Participation on Political Awareness and Perception in Indonesia: a Systematic Review and Meta-Analysis Gede Wikan Pradnya Dana; Teddy Chrisprimanata Putra; I Komang Agus Widiantara
Poltanesa Vol 27 No 1 (2026): June 2026
Publisher : P3KM Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tanesa.v27i1.3709

Abstract

Youth political participation, particularly among university students and novice voters, serves as a crucial element in dynamizing democracy and driving socio-political change in Indonesia. While the digital era has significantly expanded participatory channels ranging from offline institutional movements to contemporary digital activism, the quantitative impact of these multidimensional activities on actual cognitive outcomes remains largely unsynthesized. The existing empirical evidence is highly fragmented, necessitating a comprehensive evaluation. Therefore, this study aims to systematically estimate the correlation strength between youth political participation and their levels of political awareness and democratic perception. Guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this research synthesized 12 primary quantitative studies comprising a total of 2,345 youth participants. The statistical analysis utilized a Random Effects Model to accommodate contextual diversity, alongside Egger's regression and funnel plot analysis to rigorously evaluate publication bias. The analytical results reveal a highly robust, statistically significant positive correlation [] between political involvement and cognitive maturation, despite substantial inter-study heterogeneity (I-squared = 94%). Subsequent bias detection objectively confirmed the absence of the file-drawer problem, ensuring the reliability of the pooled estimate. Ultimately, this meta-analysis empirically confirms that active youth participation substantially functions as a school of democracy that accelerates cognitive mobilization. The findings offer a solid empirical foundation for educational stakeholders, electoral commissions, and student organizations to design evidence-based political education programs and digital literacy interventions to safeguard novice voters against electoral disinformation.
Inovasi Digital Melalui Pengembangan Website Desa Adat Untuk Mewujudkan Desa Wisata Berkelanjutan Di Desa Adat Sibetan Gde Wikan Pradnya Dana; I Gede Wira Darma; Putu Ika Wahyuni
Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Vol. 5 No. 6 (2025): November 2025 - Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/altifani.v5i6.930

Abstract

Desa Adat Sibetan memiliki potensi pariwisata yang signifikan sebagai sentra salak terbesar di Bali, namun pengembangannya terhambat oleh keterbatasan strategi promosi digital. Menjawab tantangan tersebut, program pengabdian ini mengimplementasikan inovasi digital melalui pengembangan sebuah website yang berfungsi sebagai model strategis untuk mewujudkan desa wisata yang mandiri dan berkelanjutan. Dengan menerapkan pendekatan partisipatif berbasis komunitas, program diawali dengan analisis SWOT secara kolaboratif untuk memetakan potensi dan tantangan desa. Hasil analisis tersebut kemudian menjadi landasan fundamental dalam merancang dan mengembangkan website menggunakan Metode Agile yang fleksibel. Hasil utama dari program ini adalah terciptanya sebuah website resmi yang fungsional dan responsif, yang berfungsi sebagai etalase virtual untuk mempromosikan seluruh aset unggulan desa secara terintegrasi. Secara krusial, efektivitas program alih pengetahuan kepada masyarakat telah divalidasi secara empiris. Hasil Uji t Berpasangan (Paired Samples t-Test) mengonfirmasi adanya peningkatan kapasitas digital peserta yang signifikan secara statistik (p < 0.001) setelah mengikuti pelatihan.
Technological and Environmental Evaluation of Incinerator Systems for Sustainable Waste-to-Energy Solutions in Denpasar City Putu Aryastana; I Putu Manik Kurniawan; I Gusti Agung Putu Eryani; Gde Wikan Pradnya Dana; Jackson Chang Hian Wui
Indonesian Journal of Social and Environmental Issues (IJSEI) Vol. 6 No. 2 (2025): August
Publisher : CV. Literasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47540/ijsei.v6i2.1696

Abstract

The rapid urbanization and tourism growth in Denpasar City, Bali, have led to increasing waste management challenges. Currently, only 22% of the daily 850 tons of waste is managed at the source, with the rest transported to landfills. This study aims to evaluate the implementation of Waste-to-Energy (WES) incineration systems as a potential solution to both waste disposal and energy production. The research uses a quantitative method involving primary data collection through interviews and secondary data from existing documentation. Three incinerator designs were analyzed based on parameters like energy efficiency, emissions, and environmental impact. The results show that the third incinerator system delivers the highest power output at 445.67 KW, although it also produces moderate pollutant emissions. The second design system, however, strikes a better balance, offering both lower emissions and effective power generation, making it the most environmentally favorable option. The study contributes to the growing body of research on WES technology, highlighting the need for advanced design optimization to minimize environmental impacts while maximizing energy output.
Co-Authors Ayu Dwinita Yoga Saraswati, Ida Cokorda Agung Yujana Darma, I Gede Wira Darma, Wira Eka Sura Adnyana I Gede Dyana Arjana I Gede Wira Darma I Gede Wira Darma I Gusti Agung Putu Eryani I Gusti Ngurah Agung Widya I Kadek Agus Wahyu Raharja I Komang Agus Widiantara I Made Ade Prayoga I Made Adi Bhaskara I Made Kusuma Wiranata I Made Surya Kumara I Putu Manik Kurniawan I Putu Suta Suyasa I Wayan Parwata I Wayan Runa Ida Ayu Dwinita Yoga Saraswati Jackson Chang Hian Wui Kumara, Surya Made Sudarma Ni Luh Putu Putri Setianingsih Ni Putu Widya Yuniari Putri Suardani Putu Aryastana Putu Aryastana Putu Eka Sura Adnyana PUTU IKA WAHYUNI Teddy Chrisprimanata Putra Tjok Gede Indra Partha Wayan Wahyu Adnyana Tamara Yuniari, Widya