Garuda - Garba Rujukan Digital

p-Index From 2021 - 2026

10.122

P-Index

This Author published in this journals

Adie Wahyudi Oktavia Gama

Universitas Pendidikan Nasional

Author-ID : 1313516

Religion Agriculture, Biological Sciences & Forestry Arts Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Public Health Social Sciences Veterinary Other

Published : 71 Documents Claim Missing Document

Claim Missing Document

Articles

4 5 6 7 8

Optimalisasi Kunjungan Industri sebagai Sarana Transfer Pengetahuan untuk Penguatan UMKM Swari, Luh Gede Widi; Negara, Komang Ayu Aprillia Puspa; Gama, Adie Wahyudi Oktavia
E-Dimas: Jurnal Pengabdian kepada Masyarakat Vol 16, No 4 (2025): E-DIMAS
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/e-dimas.v16i4.24673

Kegiatan company visit merupakan salah satu metode pembelajaran yang efektif untuk memberikan pengalaman langsung kepada mahasiswa dalam memahami industri kreatif dan kewirausahaan lokal. Penelitian ini bertujuan mendeskripsikan proses transfer pengetahuan dari hasil kunjungan ke industri kuliner Bakpia Wong Keraton Yogyakarta ke UMKM lokal, yaitu Pia Karomah di Pasuruan. Pendekatan yang digunakan adalah experiential learning (Kolb, 2015), yang menekankan pada keterlibatan aktif mahasiswa dalam mengamati, merefleksikan, dan mengimplementasikan hasil pembelajaran di lapangan. Data dikumpulkan melalui wawancara, observasi, dan kuesioner pre-test dan post-test. Hasil menunjukkan adanya peningkatan signifikan pada tujuh indikator, meliputi pemahaman SOP produksi, strategi pemasaran digital, kreativitas desain kemasan, integrasi nilai budaya dalam promosi, pemahaman target pasar, efisiensi proses produksi, dan inovasi varian produk. Rata-rata skor keseluruhan meningkat dari 2,8 sebelum kegiatan menjadi 4,3 sesudah kegiatan. Hasil ini membuktikan bahwa sinergi antara dunia akademik dan praktik lapangan mampu memperkuat kapasitas kewirausahaan lokal sekaligus melestarikan nilai budaya daerah.

Analisis Performa XGBoost dan Gaussian Naive Bayes untuk Klasifikasi Dini Penyakit Hipertensi Ni Made Ochiana Septhi Pratiwi; Adie Wahyudi Oktavia Gama
Jurnal Ilmiah Teknik Informatika dan Komunikasi Vol. 6 No. 1 (2026): Maret : Jurnal Ilmiah Teknik Informatika dan Komunikasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juitik.v6i1.2119

Hypertension is one of the leading causes of premature death globally that often goes undetected due to minimal clinical symptoms, earning it the nickname “silent killer.” The application of artificial intelligence (AI), particularly Machine Learning, is a strategic approach to early detection, but the main challenge lies in balancing diagnostic accuracy with detection sensitivity so that no patients at risk are overlooked. This study aims to analyze and compare the performance of the Extreme Gradient Boosting (XGBoost) algorithm with the Cost-Sensitive strategy compared to Gaussian Naive Bayes (GNB) as a baseline in hypertension risk classification. The dataset used included 1,985 electronic medical records with 9 clinical attributes, which were evaluated using the 10-Fold Cross-Validation method to determine model validity. The test results showed that XGBoost consistently outperformed GNB across all evaluation metrics. XGBoost recorded superior performance with an Accuracy of 92.19% and an AUC of 0.9752, far surpassing GNB, which obtained an Accuracy of 84.13%. The application of Cost-Sensitive Learning in XGBoost proved effective in overcoming performance trade-offs by producing a Recall of 91.26% and a Precision of 93.53%. Furthermore, Feature Importance analysis identified Blood Pressure History, Smoking Status, and Family History as the most dominant risk factors, which is in line with global medical guidelines. Based on these results, it is concluded that XGBoost is a more reliable and accurate method to be applied in early detection systems for hypertension compared to classical probabilistic approaches.

ANALISIS KOMPARATIF METODE DEMPSTER-SHAFER DAN CERTAINTY FACTOR PADA SISTEM PAKAR UNTUK DIAGNOSA PENYAKIT DIABETES I Nyoman Rizky Anggika; Adie Wahyudi Oktavia Gama
Berajah Journal Vol. 6 No. 2 (2026): Berajah Journal
Publisher : CV. Lafadz Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47353/bj.v6i2.370

This study aims to analyze and compare the performance of the Dempster-Shafer and Certainty Factor methods in expert systems for diagnosing diabetes. The research uses a qualitative approach with a literature study method by reviewing various scientific publications related to both methods in medical expert systems. The analysis focuses on key aspects such as diagnostic accuracy, ability to handle uncertainty, computational complexity, and ease of implementation. The results show that the Certainty Factor method is more efficient and easier to implement, making it suitable for structured data with lower uncertainty, while the Dempster-Shafer method is more effective in handling complex uncertainty and incomplete data due to its evidence-based approach, although it requires more complex computations. The study concludes that no single method is universally superior, as each method has its own strengths depending on data characteristics and system requirements, and suggests that combining methods could improve the performance of expert systems in diabetes diagnosis.

Early Diagnosis of Eye Disease Using an Expert System-Based Chatbot Adie Wahyudi Oktavia Gama; I Kadek Dwi Yudiarsana Dharma; I Nyoman Gde Artadana Mahaputra Wardhiana; Ni Made Widnyani
Indonesian Journal of Global Health Research Vol 6 No S6 (2024): Indonesian Journal of Global Health Research
Publisher : GLOBAL HEALTH SCIENCE GROUP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37287/ijghr.v6iS6.5390

Chatbots have emerged as popular tools across various domains, including expert systems for disease diagnosis. This research aims to develop a chatbot leveraging the Naive Bayes method within an expert system for diagnosing eye diseases. The Naive Bayes method was chosen for its efficiency in handling data classification and its ability to provide the necessary class probabilities in diagnosis. The resulting chatbot is designed to simplify the diagnosis process for users by providing a user-friendly and easily understandable interface. Evaluation of the system demonstrated an 87% accuracy rate in initial diagnoses when compared against specialist evaluations. Additionally, the User Acceptance Test revealed a high acceptance rate, with an average score of 84.75%, indicating strong user satisfaction with the system’s performance and ease of use. These findings suggest that deploying a chatbot with the Naive Bayes method in an expert system for diagnosing eye diseases has the potential to serve as a valuable platform in supporting medical practitioners in diagnosing eye diseases more efficiently and accurately.

RAINFALL ANALYSIS AND FORECASTING USING THE PROPHET METHOD ON TIME SERIES DATA Ni Komang Sintya Dewi; Adie Wahyudi Oktavia Gama
Multidiciplinary Output Research For Actual and International Issue (MORFAI) Vol. 6 No. 4 (2026): Multidiciplinary Output Research For Actual and International Issue
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.21885526

Climate change has increased rainfall variability, making it more difficult to predict rainfall patterns in terms of intensity, duration, and spatial distribution. This study aims to develop a daily rainfall forecasting model using the Prophet method, which is capable of handling seasonal patterns and long-term trends in time series data. The data used consist of daily rainfall records from 2015 to 2025 across nine regions in Bali Province, obtained from the NASA POWER platform. The research methodology includes data collection, data preprocessing, exploratory data analysis (EDA), Prophet model development with parameter optimization, cross-validation, and forecasting. Model performance is evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics on test data. The results indicate that the Prophet method is capable of effectively modeling seasonal patterns and rainfall trends, producing stable predictions for future periods. This forecasting system is expected to serve as a decision-support tool in agriculture, water resource management, and hydrometeorological disaster mitigation.

Comparative Performance of Machine Learning Algorithms for Diabetes Prediction I Made Ardi Sudestra; Adie Wahyudi Oktavia Gama; Gede Humaswara Prathama; I Gusti Ngurah Darma Paramartha; Musawer Hakimi
Journal of Technology and Informatics (JoTI) Vol. 8 No. 1 (2026): Vol. 8 N. 1 (2026)
Publisher : Universitas Dinamika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37802/joti.v8i1.1195

Early detection of diabetes mellitus is crucial to prevent severe complications. This study evaluates three machine learning algorithms for diabetes prediction using a quantitative comparative experimental design. The algorithms are k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and Random Forest. These methods were chosen to compare distinct learning paradigms. k-NN is distance-based, SVM is margin-based, and Random Forest is an ensemble method. The goal is to find the optimal model for clinical use. The Pima Indians Diabetes dataset was used. It includes 390 patients and 15 clinical features. Performance was measured by accuracy, precision, recall, and F1-score. Random Forest had the highest accuracy (89.7%) and F1-score, providing the most balanced classification. SVM followed with 84.6%, and k-NN achieved 76.9%. Although k-NN had the highest recall (0.750), its precision was low (0.375), showing a high false-positive rate. Feature importance analysis pointed to blood glucose levels as the most significant predictor, which matches clinical knowledge. In summary, ensemble techniques like Random Forest offer the most reliable results. This highlights the importance of selecting the right algorithm for early diabetes detection in clinical applications.

Simple Modification for an Apriori Algorithm with Combination Reduction and Iteration Limitation Technique Gama, Adie Wahyudi Oktavia; Widnyani, Ni Made
Knowledge Engineering and Data Science
Publisher : citeus

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

Apriori algorithm is one of the methods with regard to association rules in data mining. This algorithm uses knowledge from an itemset previously formed with frequent occurrence frequencies to form the next itemset. An a priori algorithm generates a combination by iteration methods that are using repeated database scanning process, pairing one product with another product and then recording the number of occurrences of the combination with the minimum limit of support and confidence values. The a priori algorithm will slow down to an expanding database in the process of finding frequent itemset to form association rules. Modification techniques are needed to optimize the performance of a priori algorithms so as to get frequent itemset and to form association rules in a short time. Modifications in this study are obtained by using techniques combination reduction and iteration limitation. Testing is done by comparing the time and quality of the rules formed from the database scanning using a priori algorithms with and without modification. The results of the test show that the modified a priori algorithm tested with data samples of up to 500 transactions is proven to form rules faster with quality rules that are maintained.

Mitigasi Double Booking pada Penjadwalan Dermaga Melalui Sistem Visualisasi Spasial Real-Time Dimas Rangga Marshandika; Gede Humaswara Prathama; Adie Wahyudi Oktavia Gama; Md. Wira Putra Dananjaya
Indonesian Journal of Multidisciplinary on Social and Technology Vol. 4 No. 3 (2026): Juli - Oktober
Publisher : PT Ilmu Data Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/ijmst.v4i3.13111

Pelabuhan Benoa sebagai salah satu simpul penting logistik maritim menghadapi tantangan operasional berupa latensi informasi dan potensi tumpang tindih jadwal (double booking) pada proses pra-penjadwalan sandar kapal yang masih dikelola secara konvensional. Penelitian ini bertujuan untuk merancang dan membangun sebuah sistem Pra-Booking dan monitoring dermaga berbasis website yang dilengkapi dengan visualisasi Berthing Plan secara real-time. Pembangunan perangkat lunak ini menggunakan metode Prototyping dengan memanfaatkan kerangka kerja React.js berarsitektur Virtual DOM pada sisi antarmuka untuk merender tata letak grafik dua dimensi secara responsif. Pada sisi server, sistem menggunakan Node.js dan pustaka Socket.io untuk mengelola transmisi data berlatensi rendah. Basis data PostgreSQL digunakan untuk mengamankan integritas transaksional melalui penerapan mekanisme penguncian baris data (row-level locking). Logika pencegahan benturan jadwal dikelola melalui algoritma Bounding Box Collision yang mengevaluasi irisan spasial dan temporal secara simultan, serta didukung oleh fitur mitigasi keterlambatan operasional (Extend Time). Hasil pengujian fungsional menggunakan metode Black Box Testing yang menerapkan teknik Equivalence Partitioning dan Boundary Value Analysis menunjukkan tingkat keberhasilan 100%. Hal ini membuktikan bahwa algoritma validasi kapasitas fisik dermaga dan deteksi konflik beroperasi secara akurat. Selanjutnya, pengujian penerimaan pengguna (User Acceptance Testing) yang melibatkan agen pelayaran menghasilkan persentase rata-rata sebesar 90,63%, menempatkan sistem pada kategori "Sangat Layak". Sistem ini terbukti efektif mereduksi miskomunikasi, menjaga transparansi data, dan siap diimplementasikan untuk mendukung tata kelola operasional di Dermaga Timur Pelabuhan Benoa.

Pemodelan Prediksi Banjir di Kota Denpasar Menggunakan Random Forest Theresia Ananda Eleonora; Adie Wahyudi Oktavia Gama; Gede Humaswara Prathama; Md. Wira Putra Dananjaya
Indonesian Journal of Multidisciplinary on Social and Technology Vol. 4 No. 3 (2026): Juli - Oktober
Publisher : PT Ilmu Data Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69693/ijmst.v4i3.13424

Banjir merupakan salah satu bencana hidrometeorologi yang paling sering terjadi di Indonesia, dan Kota Denpasar, Bali, menghadapi kejadian banjir berulang akibat pesatnya urbanisasi, berkurangnya daerah resapan air, serta kondisi topografi yang rendah. Penelitian ini mengembangkan model prediksi potensi banjir untuk Kota Denpasar menggunakan algoritma Random Forest, yang dilatih menggunakan lima variabel lingkungan berbasis penginderaan jauh yang diekstraksi melalui Google Earth Engine, yaitu curah hujan (CHIRPS), elevasi (SRTM), tutupan lahan (ESA WorldCover), indeks vegetasi (NDVI dari Landsat 8), dan kelembapan tanah (ERA5-Land). Data historis lokasi kejadian banjir dari Badan Penanggulangan Bencana Daerah (BPBD) Kota Denpasar periode 2020-2025 digabungkan dengan variabel-variabel lingkungan tersebut untuk membentuk dataset berlabel. Teknik Random Undersampling diterapkan untuk mengatasi ketidakseimbangan kelas, menghasilkan dataset seimbang sebanyak 416 data, yang kemudian dibagi menjadi 80% data latih dan 20% data uji. Tiga konfigurasi model dibangun dan dibandingkan, yaitu Random Forest baseline, model hasil optimasi Grid Search, dan model hasil optimasi Particle Swarm Optimization (PSO), yang masing-masing dievaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Di antara ketiga konfigurasi model, model Random Forest baseline menghasilkan performa terbaik secara keseluruhan, dengan accuracy tertinggi (88,10%), precision tertinggi (83,33%), recall tertinggi (95,24%), dan F1-score tertinggi (88,89%), serta waktu komputasi tersingkat (0,23 detik). Sebaliknya, optimasi menggunakan Grid Search dan PSO justru menurunkan performa di seluruh metrik evaluasi dibandingkan baseline, dengan accuracy masing-masing sebesar 84,52% dan 85,71%. Temuan ini menunjukkan bahwa kombinasi data penginderaan jauh dengan algoritma Random Forest mampu menghasilkan model prediksi potensi banjir yang andal untuk mendukung perencanaan mitigasi bencana di Kota Denpasar.

Deteksi Penyakit Daun Cabai Menggunakan Teknik Augmentasi Leafgan dan Deep Learning Model Ni Wayan Ariningsih; Ngakan Nyoman Kutha Krisnawijaya; Ni Luh Putu Ika Candrawengi; Adie Wahyudi Oktavia Gama
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 6 No. 2 (2026): Agustus : Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v6i2.7756

Leaf diseases in chili plants, such as leaf spot and yellow virus, pose a significant threat to agricultural productivity in Indonesia, often leading to substantial economic losses for farmers. Traditional manual identification remains inefficient and highly dependent on individual expertise, which frequently results in inconsistent diagnosis. This research proposes an automated detection system utilizing the YOLOv8n deep learning architecture to provide a more reliable and real-time solution. A major hurdle in developing robust AI models for agriculture is the scarcity of balanced field dataset s and the presence of complex natural backgrounds. To address this, the study employs Leafgan , a generative augmentation technique capable of transforming healthy leaf images into realistic diseased samples while preserving the original field environment. By leveraging an attention mechanism, Leafgan maintains high-frequency textural details, allowing the YOLOv8n model to generalize better across diverse environmental conditions. Data management is streamlined through the Roboflow platform to ensure consistent integration of primary and synthetic dataset s. The primary goal of this integration is to enhance model stability, aiming for a minimum mean Average Precision (mAP) within actual plantation settings.

Co-Authors Adhiya Garini Putri, Dewa Ayu Agus Ariana, I Komang Ajeng Ayu Fitri Ariatmaja Ariesta, Ni Luh Wina Sinta Arta, Kadek Ananda Dwi Pebri Arya Putra Sanjaya, I Ketut Gede Bunga, Melania Pritama Danang Utomo Dananjaya, Md. Wira Putra Darma, I Gede Wahyu Surya Darmaastawan, Kadek Davi, Nadine Kalina Dennatan, Monalisa Devi Anggreni, Ni Komang Ayu Devi, Ni Kadek Sintya Dewa Ayu Putu Adhiya Garini Putri Dewa Gede Hendra Divayana, Dewa Gede Hendra Dewi Puspita Ningrat, Qorry Diantari, Putu Yuliska Dimas Rangga Marshandika Dwi Sanjani Mertaningsih, Ni Kadek Gede Hendra Divayana, Dewa Gede Humaswara Prathama Ginanita Utami, Cokorda Istri Ustana Grren, Agustini Degni Melsy Gunanti, A A Istri Indah Paristya Gunawan, Putu Vina Junia Antarista Gusi Putu Lestara Permana Gusti Ngurah Darma Paramartha, I Hari Putri, Tasya Prajna Pratisthita Hayu Mas Wrespatiningsih I Dewa Putu Arjun Suhartana Wisesa I G. N. Oka Ariwangsa I Gede Artha Negara I Gusti Ayu Cintya Wardani I Gusti Ayu Intan Candra Dewi I Gusti Ngurah Darma Paramartha I Gusti Ngurah Putu Dharmayasa I Gusti Putu Riyan Nugraha I Kadek Dwi Yudiarsana Dharma I ketut Gede Darma Putra I Made Ardana I Made Ardi Sudestra I Made Riski Aditya Darma I Made Sudiksa I Made Wirya Darma I Nyoman Gde Artadana Mahaputra Wardhiana I Nyoman Gde Artadana Mahaputra Wardhiana I Nyoman Hary Kurniawan I Nyoman Rizky Anggika I Putu Agung Bayupati I Putu Mahendra Putra I Putu Wisna Ariawan I Wayan Abimayu Angga Nugraha I Wayan Aditya Suranata I Wayan Dikse Pancane I Wayan Sukadana I Wayan Sukadana I Wayan Sutama I Wayan Sutama Irma Suryanti Ivan Surya Pramana Putra, Kadek Bagus John Junieargo Timotius John Timotius Junieargo Kadek Devi Kalfika Anggaria Wardani Kadek Devi Kalfika Anggria Wardani Kadek Prasilia Candra Dewi Komang Bagus Novan Bayu Pramana Putra Kurniawan, I Nyoman Hary Lin, Fanny Made Jana Narendra Made Widnyani, Ni Maharani, Faradita Putri Aura Maulidan, Bagus Maw, Me Me Md. Wira Putra Dananjaya Musawer Hakimi Negara, I Gede Artha Negara, Komang Ayu Aprillia Puspa Ngakan Nyoman Kutha Krisnawijaya Ngurah Komang Wiradnyana Ni Kadek Nadya Kartika Paramita Ni Komang Sintya Dewi Ni Luh Putu Ika Candrawengi Ni Made Ochiana Septhi Pratiwi Ni Nyoman Triana Margareta Ni Putu Jenifer Febriari Ni Putu Widayanti Ni Wayan Ariningsih Nilton Da Conceicao Marques Nimadeni Yuniartika Nur Aprilya, Fira Nurullita Wardani, Venti Oktama Setyawan, I Kadek P. WAYAN ARTA SUYASA Permana, Putu Indra Pertama, Gusti Putu Lestara Praditya Maha Wiguna, I Made Putra, Komang Satria Wibawa Putri Prema Paramitha Putu Emy Samiadnyani Putu Purnama Dewi Putu Riska Indah Mentari putu suparna, putu Rena Mariani, Ni Wayan Sastra Dewanti, Wayan Ari Sudestra, I Made Ardi Sugiana, I Putu Sugiharni, Gusti Ayu Dessy Suputra, Komang Yudi Swari, Luh Gede Widi T Krisna Narayana, Made Gede Bagus Theresia Ananda Eleonora Wardhiana, Nyoman Dana Wayan Sugandini Widnyani, Ni Made Wisesa, I Dewa Putu Arjun Suhartana

Title

Found 71 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 71 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 71 Documents
Search