Claim Missing Document
Check
Articles

PENGEMBANGAN PROTOTIPE SISTEM INFORMASI MANAJEMEN PRESTASI DAN BEASISWA UNDIKSHA (PRABA) Pradnyana, I Made Ardwi; Permana, Agus Aan Jiwa
JST (Jurnal Sains dan Teknologi) Vol. 7 No. 1 (2018)
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (836.977 KB) | DOI: 10.23887/jstundiksha.v7i1.13789

Abstract

Dokumentasi dan manajemen data prestasi dan beasiswa masih menjadi masalah krusial yang harus segera diselesaikan. Jika dibiarkan, masalah tersebut dapat mengganggu pengelolaan perguruan tinggi saat ini dan kedepannya. Penelitian ini merupakan penelitian pengembangan yang menghasilkan prototipe Sistem Informasi Manajemen Prestasi dan Beasiswa Undiksha (PRABA). Prototipe PRABA berhasil dikembangkan melalui metode pengumpulan data dan studi literatur, analisis dan perancangan serta implementasi dan pengujian. Pengumpulan data dilakukan dengan metode wawancara dan mengkaji dokumen beasiswa. Studi literatur dilakukan dengan mempelajari dasar teori mengenai diagram use case dan aktivitas serta perancangan basis data dengan ERD. Analisis dilakukan untuk mendapatkan kondisi yang selama ini terjadi (As Is). Kemudian penulis  merumuskan syarat fungsional yang harus dimiliki sistem untuk menangani kendala yang terjadi saat ini. PRABA diimplementasikan berbasis website dengan bahasa pemrograman PHP dan basis data MySQL. Hasil pengujian terhadap PRABA menggunakan metode pengujian black box menunjukkan bahwa PRABA sudah memenuhi syarat fungsionalitas yang sudah ditetapkan terkait manajemen data prestasi dan beasiswa.
USABILITY TESTING PADA WEBSITE E-COMMERCE MENGGUNAKAN METODE SYSTEM USABILITY SCALE (SUS) (STUDI KASUS : UMKMBULELENG.COM) Jiwa Permana, Agus Aan
JST (Jurnal Sains dan Teknologi) Vol. 8 No. 2 (2019)
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (722.151 KB) | DOI: 10.23887/jstundiksha.v8i2.22858

Abstract

Pengembangan perangkat lunak sangat bermanfaat untuk membantu di beberapa bidang. Salah satunya adalah bidang pemasaran. Dengan perkembangan internet, proses pemasaran sudah lumbrah dilakukan melalui online dengan beberapa metode jual beli yang dilakukan seperti cash on delivery (COD), bayar di muka,  atau bayar barang saja dengan ongkos kurir dibayar setelah barang diterima. Pemasaran online memerlukan E-commerce  untuk membantu menghubungkan pembeli dengan penjual. Seperti yang dilakukan oleh kelompok perajin di Singaraja, dengan alamat website yang dapat diakses pada http://umkmbuleleng.com. Website ini sudah online, namun perlu dilakukan uji terkait untuk mengetahui apakah user dapat dengan mudah menggunakan aplikasi secara efektif dan efisien. Hal ini dilakukan untuk mengetahui tingkat kepuasan pengguna. Sebelum produk di launching secara luas, perlu dilakukan proses pengujian ini. Metode yang digunakan untuk melakukan pengujian ini adalah System Usability Scale (SUS). Hasil pengujian diperoleh yaitu baik. Sehingga aplikasi yang dikembangkan untuk perajin secara umum sudah sesuai dengan harapan pengguna
Pelatihan Penggunaan AI untuk Mendukung Pembelajaran di Tingkat Sekolah Dasar Lab Undiksha Sindu, I Gede Partha; Permana, Agus Aan Jiwa; Kertiasih, Ni Ketut; Setemen, Komang; Pracasitaram, Gede Made Surya Bumi
Al-DYAS Vol 4 No 3 (2025): OKTOBER
Publisher : Lembaga Yasin AlSys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/aldyas.v4i3.7615

Abstract

The community service activity titled Training on the Use of AI to Support Learning at the Elementary School Level, conducted at the Undiksha Laboratory School, was driven by the urgent need to enhance teachers’ competencies in response to rapid developments in digital technology, particularly generative artificial intelligence (generative AI). Teachers are expected to integrate technology into the educational process to make learning more effective, relevant, and innovative. The primary goal of this activity was to equip elementary school teachers with both conceptual understanding and practical skills in utilizing AI as a tool to support learning. The training was structured around four core topics: basic introduction to AI, the use of AI in lesson planning, AI-assisted development of interactive learning media, and practical application of AI-based tools. The implementation methods included material delivery, active discussions, and hands-on practice to ensure a balance between theory and application. Evaluation results showed a significant improvement in participants’ understanding and skills related to AI usage, increased motivation to innovate in teaching, and strengthened technological orientation in classroom practice. Participants also appreciated the training as a valuable initiative and recommended its continuation. Therefore, this training has made a tangible contribution to enhancing teacher capacity and supporting the transformation of learning at the elementary school level.
Peningkatan Value Added Sentra Kerajinan Tenun Ikat Endek dengan Penerapan Smart Ecodigital Purnamawati, I Gusti Ayu; Herliyani, Elly; Jiwa Permana, Agus Aan; Baskara Nugraha, I Gusti Bagus; Pranadi Sudhana, I G P Fajar
Jurnal Pengabdian kepada Masyarakat Nusantara Vol. 5 No. 4 (2024): Jurnal Pengabdian kepada Masyarakat Nusantara (JPkMN) Edisi September - Desembe
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jpkmn.v5i4.4584

Abstract

Desa Gelgel, Klungkung, Bali, dikenal sebagai sentra kerajinan tenun ikat endek, namun para pengrajin menghadapi tantangan dalam meningkatkan nilai tambah produk dan mengelola usaha secara efektif. Tujuan pengabdian masyarakat ini adalah untuk meningkatkan nilai tambah produk kerajinan melalui penerapan smart ecodigital dan sistem akuntansi terintegrasi, sehingga para pelaku UKM dapat menjadi lebih mandiri. Metode yang digunakan meliputi pendekatan partisipatif, sesi pelatihan teori dan praktik, serta pendampingan individu untuk penerapan teknologi dan manajemen keuangan. Hasil kegiatan menunjukkan peningkatan pemahaman peserta tentang nilai tambah, dengan 80% peserta menyatakan memahami konsep tersebut secara lebih baik. Sekitar 70% peserta mulai mengadopsi perangkat lunak akuntansi dan memanfaatkan media sosial untuk pemasaran produk. Selain itu, 65% peserta berhasil menerapkan sistem akuntansi yang lebih terstruktur, meningkatkan transparansi dan akuntabilitas usaha mereka. Kegiatan ini memberikan dasar yang kuat untuk keberlanjutan usaha kerajinan di Desa Gelgel dan diharapkan mendorong pengrajin untuk terus mengembangkan keterampilan serta meningkatkan daya saing produk mereka di pasar.
Sistem Pakar Pemilihan Menu Diet Sesuai Kondisi Kesehatan Pasien Kusumadewi, Ni Putu Ari; Permana, Agus Aan Jiwa; Swari, Gusti Putu Ayu Mas Meita Pradnya; Yudhantara, Kadek Prasta; Mahagangga, Komang Adi Satya; Artha, I Komang Windra
MASALIQ Vol 5 No 3 (2025): MEI
Publisher : Lembaga Yasin AlSys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/masaliq.v5i3.5439

Abstract

Expert Systems, a branch of artificial intelligence, are designed to replicate decision-making capabilities of human experts. This study focuses on developing an Expert System for Diet Menu Selection Based on Health Conditions. The system aims to assist users in planning nutritious and balanced diets tailored to individual health profiles, thereby enhancing health management through clear and practical guidelines. The Forward Chaining inference method is employed to derive conclusions from known health data, while the Agile development methodology supports iterative progress, adaptability to changes, and active stakeholder involvement to ensure optimal functionality. Given the rising public awareness of healthy living, this system presents a practical and innovative alternative for individuals seeking to manage their dietary habits effectively—without the need for constant consultations with nutritionists.
Machine Learning-Based Prediction of HIV/AIDS Infection and Treatment Effectiveness: A Clinical Dataset Analysis Jiwa Permana, Agus Aan; Wikranta Arsa, I Gusti Ngurah; Naswin, Ahmad; Sumiyatun
International Journal of Artificial Intelligence in Medical Issues Vol. 3 No. 2 (2025): International Journal of Artificial Intelligence in Medical Issues
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijaimi.v3i2.362

Abstract

The early and accurate prediction of HIV/AIDS infection is critical to improving clinical decision-making and ensuring effective patient management. This study presents a comprehensive machine learning-based approach to predict HIV/AIDS infection status and evaluate the effectiveness of antiretroviral treatments using a well-documented clinical dataset from 1996, comprising 2,139 patient records and 34 features. Through rigorous preprocessing, exploratory data analysis, and feature engineering, several new clinically relevant attributes were constructed, such as CD4/CD8 ratios and immunological change metrics. Four machine learning models—Logistic Regression, Support Vector Machine, Random Forest, and Gradient Boosting—were trained and evaluated. Among these, the Gradient Boosting classifier achieved the highest ROC-AUC score of 0.9335, while Random Forest provided strong predictive performance with a ROC-AUC of 0.9180 and was selected for further evaluation due to its model transparency. Key features influencing infection prediction included CD4+ and CD8+ dynamics, baseline immunological levels, and treatment history. Additionally, the study examined treatment effectiveness by analyzing CD4+ cell count responses across different therapy types. The combination of ZDV and ddI emerged as the most effective regimen, improving immune outcomes and lowering infection rates, while ZDV monotherapy showed the least favorable results. This work underscores the potential of machine learning as a clinical decision support tool in HIV/AIDS care and provides data-driven insights into treatment optimization. Future studies should incorporate longitudinal patient data and real-world clinical environments for broader applicability.
Forecasting Kunjungan Wisatawan Dengan Long Short Term Memory (LSTM) Sugiartawan, Putu; Jiwa Permana, Agus Aan; Prakoso, Paholo Iman
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 1 No 1 (2018): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (965.51 KB) | DOI: 10.33173/jsikti.5

Abstract

Bali is one of the favorite tourist attractions in Indonesia, where the number of foreign tourists visiting Bali is around 4 million over 2015 (Dispar Bali). The number of tourists visiting is spread in various regions and tourist attractions that are located in Bali. Although tourist visits to Bali can be said to be large, the visit was not evenly distributed, there were significant fluctuations in tourist visits. Forecasting or forecasting techniques can find out the pattern of tourist visits. Forecasting technique aims to predict the previous data pattern so that the next data pattern can be known. In this study using the technique of recurrent neural network in predicting the level of tourist visits. One of the techniques for a recurrent neural network (RNN) used in this study is Long Short-Term Memory (LSTM). This model is better than a simple RNN model. In this study predicting the level of tourist visits using the LSTM algorithm, the data used is data on tourist visits to one of the attractions in Bali. The results obtained using the LSTM model amounted to 15,962. The measured value is an error value, with the MAPE technique. The LSTM architecture used consists of 16 units of neuron units in the hidden layer, a learning rate of 0.01, windows size of 3, and the number of hidden layers is 1.
Comparison of CNN and CNN-LSTM Performance in Facial Expression Classification Based on FER2013 Dataset Savitri, Putu Ananda Adi; Permana, Agus Aan Jiwa; Puspa Dewi, Ni Putu Novita
Asian Journal of Science, Technology, Engineering, and Art Vol 4 No 1 (2026): Asian Journal of Science, Technology, Engineering, and Art
Publisher : Darul Yasin Al Sys

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58578/ajstea.v4i1.8252

Abstract

Although facial expression recognition (FER) using deep learning has received increasing attention in prior studies, research specifically addressing the comparative effectiveness of sequential modeling on static image data remains limited. This study aims to evaluate and compare the performance of a pure Convolutional Neural Network (CNN) model and a hybrid CNN–Long Short-Term Memory (CNN-LSTM) model in classifying seven basic facial expressions using the static FER2013 dataset. A quantitative experimental approach with a comparative study design was employed, utilizing the publicly available FER2013 dataset and two custom deep learning architectures. Data were obtained from FER2013 and model performance was evaluated using accuracy, precision, recall, F1-score, and AUC-ROC metrics. The findings indicate that the pure CNN model significantly outperformed the CNN-LSTM model, achieving a testing accuracy of 63.25% compared to 46.82% for the hybrid model; the CNN provided strong discrimination for visually distinct classes but continued to struggle with visually similar expressions. These results contribute to the theoretical development of deep learning architecture selection and expand understanding of the application of sequence models to static data. The study concludes that data characteristics (static versus temporal) play a crucial role in determining model effectiveness, and that for static datasets such as FER2013, a pure CNN constitutes the more appropriate choice. The implications of this research include theoretical contributions to the growing literature on deep learning-based FER and practical recommendations for developers to prioritize CNN architectures for non-temporal image classification tasks, while also highlighting opportunities for future research on transfer learning and attention mechanisms to better capture subtle expression nuances.
IMPLEMENTASI MODEL LLAMA VISION DENGAN IN-CONTEXT LEARNING UNTUK PEMBUATAN CAPTION OTOMATIS Joe Aqilla Vandyta; Ketut Agus Seputra; Agus Aan Jiwa Permana
JUTIM (Jurnal Teknik Informatika Musirawas) Vol 11 No 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2860

Abstract

Penelitian ini bertujuan untuk merancang dan membangun aplikasi Android bernama Descripix yang memanfaatkan model LLaMA Vision untuk menghasilkan caption gambar secara otomatis. Latar belakang dari penelitian ini adalah banyaknya content creator, fotografer, dan pengguna media sosial yang mengalami creative block dalam membuat caption, sehingga menghambat konsistensi publikasi konten mereka. Metode pengembangan yang digunakan adalah Waterfall dengan pengujian Black Box. Sistem yang dibangun mengintegrasikan metadata gambar seperti author, tanggal pengambilan dan lokasi sebagai input tambahan dalam proses captioning. Penerapan metode In-Context Learning (ICL) dalam prompting menghasilkan caption yang lebih konsisten, kontekstual, dan sesuai dengan pola linguistik yang diharapkan. Perbandingan hasil generasi caption dengan dan tanpa metode ICL membuktikan bahwa, penerapan ICL menghasilkan output yang lebih akurat, konsisten, dan kontekstual dengan mengeliminasi elemen yang tidak relevan. Aplikasi memiliki dua mode pengguna: guest dapat mengunggah gambar dan menghasilkan caption, sementara authenticated user dapat menyimpan, mengedit, dan mengelola riwayat caption. Hasil pengujian Black Box terhadap 12 skenario menunjukkan bahwa seluruh fungsi utama aplikasi menunjukan tingkat keberhasilan 100%, memvalidasi bahwa seluruh fitur utama berfungsi sesuai espektasi. Dengan demikian, aplikasi ini dapat menjadi solusi efektif untuk membantu pengguna tetap aktif di media sosial saat mengalami creative block dan meningkatkan produktivitas dalam pembuatan konten.
Self-help online psychoeducation to overcome anxiety during covid-19 outbreak. Suranata, Kadek; Ifdil, Ifdil; Gading, I Ketut; Permana, Agus Aan Jiwa
COUNS-EDU: The International Journal of Counseling and Education Vol. 6 No. 1 (2021)
Publisher : Indonesian Institute for Counseling, Education, and Therapy & Indonesian Counselor Association

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23916/0020210634010

Abstract

This study aims to compare the effectiveness of mindfulness and relaxation techniques with self-help methods through web tutorials to overcome anxiety during the Covid-19 outbreak. Random control trial experiment performed by invite 418 Balinese Community (Age 15 years and above) to preliminary screening on anxiety sub-scale of 21-DASS. A total of 129 participants who met the random assignment criteria were then grouped into three groups, namely experimental group 1 who will take self-help mindfulness exercises, experimental group 2 who will participate in self-help relaxation exercises, and waiting-list control group. The results of study shows that web-based self-help mindfulness and relaxation tutorials are effective for reducing anxiety levels. The comparison of the two also shows that mindfulness techniques are more effective than relaxation techniques. The results of this study have theoretical and practical implications in efforts to overcome anxiety disorders experienced during the Covid-19 outbreak. 
Co-Authors A. A. Gede Yudhi Paramartha Agus Halid, Agus Agus Seputra I Ketut Alkautsar, Yoga Rizky Artha, I Kadek Bayu Danu Artha, I Komang Windra Baskara Nugraha, I Gusti Bagus Darmayasa, Ngakan Nyoman DIATMIKA, KETUT TUTUR Elly Herliyani Erma Susanti Gede Aditra Pradnyana Gede Arya Ardivan Pratama Saputra Gede Nanda Ageng Nugraha Gede Saindra Santyadiputra Gede Wahyu Purnama Gunawan, I Gede Made Deny Surya I Gd Ny Werdyana Guna Mertha I Gusti Agung Putu Bagus Satria Wicaksana I Gusti Ayu Purnamawati I Gusti Ngurah Wikranta Arsa, I Gusti Ngurah I Kadek Nicko Ananda I Kadek Suranata I Ketut Gading I Ketut Purnamawan I Made Ardwi Pradnyana I Made Bayu Sastra Wiguna I Made Pageh I Made Putrama I Made Sukarsa I Made Sukarsa I Nyoman Laba Jayanta I Nyoman Saputra Wahyu Wijaya I Nyoman Saputra Wahyu Wijaya I Putu Dion Arditya Ida Bagus Sebali Mahesa Yogi Ifdil Ifdil Ika Arfiani Joe Aqilla Vandyta Kadek Wirahyuni Ketut Agus Suputra Komang Setemen Kusuma, I Komang Arya Adi Kusumadewi, Ni Putu Ari Made Padmi Wirayani Made Sudarma Made Sudarma Mahagangga, Komang Adi Satya Marta Dinata, Kadek Prima Giant Naswin, Ahmad Ni Ketut Kertiasih Ni Luh Ita Purnami Ni Putu Dwi Sucita Dartini Ni Putu Novita Puspa Dewi Ni Wayan Marti Octavia, I Gusti Ayu Adiani Okthen Orlanda Naitboho pande sindu Pande, Satria Imawan Adi Putra Pande Pracasitaram, Gede Made Surya Bumi Pracasitaram, I Gede Made Surya Bumi Prakoso, Paholo Iman Pramudya, Dewa Gede Bhaskara Pranadi Sudhana, I G P Fajar Puridiasta, I Gede Deindra Dwija Puspa Dewi, Ni Putu Novita Putrama, Made Putu Ony Andewi PUTU SUGIARTAWAN Rezania Agramanisti Azdy, Rezania Agramanisti Rissa Nurmalasari Rukmi Sari Hartati Rukmi Sari Hartati Saputra Wahyu Wijaya Savitri, Putu Ananda Adi Siami, M. Ikbal Sindu, I Gede Partha Sumiyatun Sunia Raharja, I Made Swari, Gusti Putu Ayu Mas Meita Pradnya Tarigan, Thomas Edyson Widodo Prijodiprodjo Wijaya, I Gede Saputra Wahyu Winata, I Gede Arya Wirayani, Made Padmi Witjaksana, Putu Gede Dimas Yoga Rizky Alkautsar Yoga Sucipta, Gede Yudhantara, Kadek Prasta