Article Per Year (5 Year)
p-Index From 2021 - 2026
1.757
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi PROSIDING CSGTEIS 2013 JUTIK : Jurnal Teknologi Informasi dan Komputer Jurnal Pelayanan dan Pengabdian Masyarakat (Pamas) Progresif: Jurnal Ilmiah Komputer Journal of Applied Data Sciences DEVOTE: Jurnal Pengabdian Masyarakat Global
Ni Putu Widya Yuniari
Universitas Warmadewa
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Penerapan Teknik Fast Motion Estimation Pada Algoritma Frame Rate Up-Conversion Video Ni Putu Widya Yuniari; I Made Oka Widyantara
PROSIDING CSGTEIS 2013 CSGTEIS 2013
Publisher : PROSIDING CSGTEIS 2013

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

Abstract

Abstrak— Video surveillance merupakan salah satu aplikasi yang sering dimanfaatkan pada sistem keamanan yakni dengan menempatkan satu atau beberapa kamera untuk memantau suatu ruangan kemudian ditransmisikan ke dekoder. Pada jaringan yang memiliki keterbatasan bandwidth transmisi, untuk tetap memperoleh video dengan resolusi tinggi terdapat suatu mekanisme yakni pada sisi enkoder harus menurunkan frame rate dengan mengirimkan sebagian dari urutan video asli. Sedangkan di dekoder harus mengupgrade kembali frame rate tersebut dengan suatu teknik yang dinamakan Frame Rate Up-Conversion (FRUC). FRUC merupakan suatu teknik menyisipkan sebuah frame yang baru (intermediate) ke dalam suatu urutan video asli untuk meningkatkan frame rate. Salah satu teknik FRUC adalah Motion Compensation Interpolation (MCI). Teknik ini menyandarkan pada suatu proses yang disebut Motion Estimation (ME). Proses ME untuk algoritma MCI pada FRUC yakni memprediksikan posisi frame berupa Motion Vector (MV) yang sekarang berdasarkan pada frame referensi. MV yang telah diperoleh disimpan di dekoder sebagai informasi yang digunakan untuk penyisipan frame intermediate. Terdapat suatu metode untuk mempercepat proses ME dengan mengurangi jumlah blok kandidat yang disebut Fast Search. Salah satu metode Fast Search adalah Three Step Search {TSS). Dengan mengadopsi pengkodean video berbasis blok, pada paper ini mengajukan penerapan teknik Fast Search TSS untuk ME pada algoritma FRUC. Sasarannya adalah menurunkan kompleksitas di enkoder dengan mengurangi jumlah kandidat blok pencarian dan untuk memberikan informasi MV frame intermediate yang akan disisipkan pada dekoder sehingga mampu meningkatkan frame rate.Kata kunci: Motion Compensation Interpolation, Motion Estimation , Fast Search , Three Step Search.
PERSEPSI MAHASISWA BERDASARKAN GENDER TERHADAP SISTEM PEMBELAJARAN ONLINE DAN OFFLINE I Made Adi Bhaskara; I Made Surya Kumara; I Gede Wira Darma; Ni Putu Widya Yuniari; Gde Wikan Pradnya
Jurnal Teknologi Informasi dan Komputer Vol. 10 No. 2 (2024): Jurnal Teknologi Informasi dan Komputer
Publisher : LPPM Universitas Dhyana Pura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36002/jutik.v10i2.2970

Abstract

Sistem pembelajaran secara online (daring) awalnya bertujuan sebagai alternatif darisistem pembelajaran di semua jenjang pendidikan. Dengan adanya pandemi Covid-19terjadi perubahan drastis yaitu sistem pembelajaran online secara penuh. Meredanyapandemi Covid-19 akhirnya sistem pembelajaran secara hibrid yaitu gabungan antaraoffline dan online. Penelitian ini bertujuan untuk mengetahui minat peserta didik tentangsistem pembelajaran dikaitkan dengan terkait faktor gender. Sebanyak 157 mahasiswaeksakta digunakan sebagai sampel yang terdiri dari 65 laki-laki dan 92 perempuan.Penelitian observasional menggunakan kuisener dengan pertanyaan tentang pemilihansistem pembelajaran (offline, online dan hibrid), pemilihan waktu (pagi, siang, sore danmalam) dan persepsi tentang pembelajaran offline (mudah memahami, menyenangkan,praktis). Hasil penelitian diperoleh bahwa pembelajaran online lebih banyak dipilih olehlaki-laki, sebaliknya perempuan lebih banyak memilih sistem offline. Berdasarkanpemilihan waktu pembelajaran online, peserta didik laki-laki lebih memilih waktu pagihari, sedangkan perempuan lebih banyak memilih waktu siang, sore dan malam. Secarakeseluruhan sistem pembelajaran offline lebih memudahkan pemahaman materipembelajaran dibandingkan online. Dapat disimpulkan bahwa ada persepsi yang berbedatentang pembelajaran online antara peserta didik laki-laki dengan yang perempuan. Perluteknis dan strategi yang berbeda antara pembelajaran online kepada peserta didik laki-laki dan perempuan
PENERAPAN TEKNIK MULTI-LEVEL THRESHOLDING FUZZY ENTROPY DAN DIFFERENTIAL EVOLUTION PADA KOMPRESI CITRA Ni Putu Widya Yuniari
Jurnal Teknologi Informasi dan Komputer Vol. 10 No. 2 (2024): Jurnal Teknologi Informasi dan Komputer
Publisher : LPPM Universitas Dhyana Pura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36002/jutik.v10i2.2973

Abstract

Kompresi citra memainkan peran penting dalam berbagai aplikasi, seperti penyimpanan digital,transmisi citra, dan pemrosesan multimedia. Teknik kompresi citra yang efektif dapat secara signifikanmengurangi ukuran file citra digital tanpa mengorbankan kualitas visualnya. Penelitian ini mengusulkanevaluasi kinerja teknik kompresi citra dengan mengkombinasikan teknik Multi-Level Thresholdingdengan metode Fuzzy Entropy dan Differential Evolution. Metode ini diterapkan pada citra wajah dancitra medis. Kinerja metode ini dinilai berdasarkan Peak Signal-to-Noise Ratio (PSNR), StructuralSimilarity Index (SSIM), dan Feature Similarity Index Measure (FSIM). Analisis lebih lanjut diketahuibahwa nilai PSNR, SSIM, dan FSIM bertambah seiring dengan kenaikan level threshold, dengan nilaitertinggi diperoleh pada level threshold 40. Hal ini menunjukkan bahwa peningkatan level thresholdmenghasilkan kompresi citra yang selaras tanpa mengorbankan kualitas visual citra terkompresi.
Integrate Yolov8 Algorithm For Rupiah Denomination Detection In All-In-One Smart Cane For Visually Impaired Kumara, I Made Surya; Jati, Gde Putu Rizkynindra Sukma; Yuniari, Ni Putu Widya
Techno.Com Vol. 23 No. 1 (2024): Februari 2024
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/tc.v23i1.9734

Abstract

The eyes are crucial tools for human observation and perception, facilitating various tasks in daily life. Individuals, including those with visual impairments or blindness, engage in currency transactions, posing challenges in recognizing notes and preventing mishaps with counterfeit money. Despite government efforts, features like embossing on banknotes have limited effectiveness due to the circulated currency's disheveled condition. Addressing the visually impaired community's needs is imperative. An innovative solution, the "all-in-one smart white cane," integrated with machine learning supports daily activities, enhancing independence for visually impaired individuals. The YOLOv8 algorithm is employed for the precise detection of monetary denominations, subsequently recorded through a camera and seamlessly integrated into a smart cane, resulting in a consolidated device. This device, designed with standout features, excels in detecting Indonesian Rupiah banknote denominations. Detection performance testing, incorporating methods like object rotation, utilized a dataset divided into training (70%), validation (20%), and test (10%) segments. Modifications to contrast and variability rotation are essential in the context of real-time nomination recognition. These adjustments are implemented to ensure accurate and swift identification in dynamic, real-world scenarios. Testing results reveal a 99% average accuracy in recognizing currency note denominations, presenting an effective solution for the visually impaired community.
Environment Sentiment Analysis of Bali Coffee Shop Visitors Using Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer 2 (GPT2) Model Yuniari, Ni Putu Widya; Iswari, Ni Made Satvika; Kumara, I Made Surya
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.302

Abstract

Bali is one of the provinces with the most abundant natural and cultural wealth in Indonesia. One commodity that supports it is coffee. Bali Coffee is not only a gastronomic identity, but also a cultural identity which makes it have added value to be developed into various business lines. One business derivative that is quite promising is a coffee shop. However, these favorable conditions also need to be maintained to ensure good quality reaches consumers. One thing that can do is analyze reviews from customers. One of the most popular methods is Sentiment Analysis. This technique allows business to analyze customer reviews on social media. It can be a feedback to maintaining and improving quality and good relationships with customers. This research aims to create a machine learning model to analyze customer reviews at several coffee shops in Bali which are divided into three labels, namely: positive, negative and neutral. The methods used are: scraping, cleaning, stopword removal, embedding, undersampling, and modeling. The algorithms used are Bidirectional Encoder Representation from Transformer (BERT) and Generative Pre-trained Transformers (GPT). The performance metrics used in this research are precision, recall, accuracy and loss. This research succeeded in creating a sentiment analysis model for coffee shop customers in Bali. The BERT model obtained an accuracy value of 78% without undersampling with a loss in the 10th iteration of 0.27. Meanwhile, the BERT model with undersampling obtained an accuracy value of 32.85% with a loss in the 10th iteration of 0.16. The GPT2 model without undersampling gets an accuracy of 78% with a loss in the 10th iteration of 0.25. Meanwhile, the GPT model with undersampling obtained an accuracy value of 32.85% with a loss in the 10th iteration of 0.15.
PENGABDIAN KEPADA MASYARAKAT “TERASDigital Peguyangan Kaja” (Transformasi Era Layanan Administrasi Menuju Sistem Digital Desa Peguyangan Kaja Melalui Tanda Tangan Elektronik) Dana, Gde Wikan Pradnya; Yuniari, Ni Putu Widya; Aryastana, Putu; Kumara, I Made Surya; Bhaskara, Made Adi; Darma, I Gede Wira; Raharja, I Kadek Agus Wahyu
Jurnal Pelayanan dan Pengabdian Masyarakat (Pamas) Vol 9, No 3 (2025): Jurnal Pelayanan dan Pengabdian Masyarakat (PAMAS)
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM Universitas Respati Indonesia)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52643/pamas.v9i3.5189

Abstract

Information technology within organizations, companies, and government institutions today plays a very significant role. However, the implementation of information technology in Indonesia still faces challenges in terms of efficiency and effectiveness, particularly in the village governance sector. On July 9, 2024, the Computer Engineering Faculty at Warmadewa University conducted a Community Service Program titled "TERAS Digital Peguyangan Kaja," which involved outreach and training to maximize the use of electronic signatures, evaluated using SWOT analysis. This program offers benefits such as the effectiveness and efficiency of public services. The implementation of electronic signatures is hindered by infrastructure issues and social resistance, necessitating outreach, intensive training, and infrastructure improvements. This community service program, in collaboration with the Denpasar City Communication and Information Agency (Diskominfo). This activity involved 25 participants consisting of village officials and service implementers, as well as representatives from the Denpasar City Communication and Information Office (Diskominfo). The evaluation of activities was carried out using SWOT analysis, involving socialization, training, and mentoring to implement the use of electronic signatures. evaluation using SWOT analysis. The implementation of socialization and training has increased the digital literacy of the community and village officials, increasing efficiency and effectiveness in solving the problems of the people of Peguyangan Kaja Village when the party whose signature is required by the village apparatus is in the way. . Although electronic signature technology has just begun to be implemented, there are technical obstacles and infrastructure limitations in Peguyangan Kaja Village that need to be overcome to ensure that this technology functions optimally and is accepted by the community. Future plans focus on improving the overall implementation of electronic signatures and increasing socialization to ensure the sustainability and effectiveness of the program. Keywords: Electronic Signatures, Socialization, Training, SWOT Analysis\
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 Performa Siswa dalam E-Learning I Made Surya Kumara; Kannan Nataraj; Ni Putu Widya Yuniari; Jauzaa Maylia Suhendro; I Gusti Agung Made Yoga Mahaputra; Depandi Enda
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.v21i1.2569

Abstract

-
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
PEMBERDAYAAN BERBASIS MASYARAKAT YANG MENGINTEGRASIKAN DESAIN EFISIEN DAN TEKNOLIGI UMKM BATAKO DAN PAVING DI DESA SABA, BLAHBATUH, GIANYAR Ni Komang Indra Mahayani; Km. Deddy Endra Prasandya; Ni Putu Widya Yuniari
Devote: Jurnal Pengabdian Masyarakat Global Vol. 4 No. 4 (2025): Devote: Jurnal Pengabdian Masyarakat Global, 2025
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/devote.v4i4.5199

Abstract

This community empowerment programme aims to enhance the production efficiency, material quality, and market competitiveness of micro-enterprises producing concrete blocks and paving units in Saba Village, Blahbatuh, Gianyar. The initiative was led by Ni Komang Indra Mahayani and supported by an academic team comprising an Architecture lecturer, a Computer Engineering lecturer, and three students from Universitas Warmadewa. The methodological framework involved site observation, spatial diagnostics, needs assessment, architectural reconfiguration of the production layout, integration of sustainable design principles, and digital capacity-building for marketing. The intervention focused on reorganising production zones into a more linear and coherent spatial sequence—encompassing moulding, curing, storage, and packaging—to minimise unnecessary circulation and improve workflow continuity. Sustainable strategies were incorporated through the provision of a waste-processing area enabling material recirculation, enhanced natural ventilation, and the introduction of green pockets to promote environmental comfort. Material performance was evaluated through a compressive strength test to ensure the paving products comply with technical standards required for governmental and private-sector projects. Improvements to occupational safety included dedicated rest facilities, sanitary amenities, clear evacuation routes, and acoustic treatment within high-noise production areas. Additionally, training in e-catalogue development and digital marketing was delivered to expand market reach and support participation in electronic procurement systems. The outcomes demonstrate significant improvements in production efficiency, product reliability, and operational readiness, highlighting the role of architectural intervention and academic collaboration in strengthening the long-term sustainability and resilience of local micro-enterprises.
Co-Authors Darma, I Gede Wira Depandi Enda Dharma, Eddy Muntina I Gede Wira Darma I Gede Wira Darma I Gusti Agung Made Yoga Mahaputra I Kadek Agus Wahyu Raharja I Made Adi Bhaskara I Made Oka Widyantara I Made Surya Kumara I Nyoman Yudi Anggara Wijaya Jati, Gde Putu Rizkynindra Sukma Jauzaa Maylia Suhendro Kannan Nataraj Komang Deddy Endra Prasandya Ni Komang Indra Mahayani Ni Made Satvika Iswari Nunik Afriliana Putu Aryastana Wikan Pradnya Dana, Gde