Article Per Year (5 Year)
p-Index From 2021 - 2026
5.063
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Journal of ICT Research and Applications JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) Jurnal Teknologi Informasi dan Pendidikan International Journal of Engineering and Emerging Technology Indonesian Journal of Electrical Engineering and Computer Science Jurnal Bali Membangun Bali International Journal of Engineering, Science and Information Technology International Journal of Management Science and Information Technology (IJMSIT) Makara Journal of Technology Lontar Komputer: Jurnal Ilmiah Teknologi Informasi
I ketut Gede Darma Putra
Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana
Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Physics Public Health Social Sciences Transportation Other

Published : 68 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 68 Documents
Search

 3   4   5   6   7 
Deep Learning Implementation Using CNN to Classify Bali God Sculpture Pictures Ni Luh Gede Pivin Suwirmayanti; I Made Budi Sentana; I Ketut Gede Darma Putra; Made Sudarma; I Made Sukarsa; Komang Budiarta
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 15 No. 02 (2024): Vol. 15, No. 2 August 2024
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2024.v15.i02.p02

Abstract

Efforts to preserve Balinese culture can be carried out by integrating art and technology as new steps that need to be developed. This research is motivated by the existence of various forms of God statues which have a central role in Balinese culture. The Deep Learning method is proposed because it has unique features that can be extracted automatically. The technique used in Deep Learning is Convolutional Neural Network (CNN). The training process is first performed to perform the classification process, and then the testing process is performed. We compared our CNN model with two other models, AlexNet and ResNet, based on the experimental results. Using a data split of 70%- 30%, our CNN model has the highest accuracy in managing statue image data. Specifically, our model achieves 97.14% accuracy, while Alexnet and Resnet achieve 24.44% and 33.33%, respectively. Apart from contributing to introducing the Balinese God Statue, this research can also be a basis for developing more comprehensive applications in culture and tourism.
BERT Uncased and LSTM Multiclass Classification Model for Traffic Violation Text Classification Komang Ayu Triana Indah; I Ketut Gede Darma Putra; Made Sudarma; Rukmi Sari Hartati; Minho Jo
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 15 No. 02 (2024): Vol. 15, No. 2 August 2024
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2024.v15.i02.p04

Abstract

The increasing amount of internet content makes it difficult for users to find information using the search function. This problem is overcome by classifying news based on its context to avoid material that has many interpretations. This research combines the Uncased model BiDirectional Encoder Representations from Transformer (BERT) with other models to create a text classification model. Long Short-Term Memory (LSTM) architecture trains a model to categorize news articles about traffic violations. Data was collected through the crawling method from the online media application API through unmodified and modified datasets. The BERT Uncased-LSTM model with the best hyperparameter combination scenario of batch size 16, learning rate 2e-5, and average pooling obtained Precision, Recall, and F1 values of 97.25%, 96.90%, and 98.10%, respectively. The research results show that the test value on the unmodified dataset is higher than on the modified dataset because the selection of words that have high information value in the modified dataset makes it difficult for the model to understand the context in text classification.
Comparative Analysis of Denoising Techniques for Optimizing EEG Signal Processing I Putu Agus Eka Darma Udayana; Made Sudarma; I Ketut Gede Darma Putra; I Made Sukarsa; Minho Jo
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 15 No. 02 (2024): Vol. 15, No. 2 August 2024
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2024.v15.i02.p05

Abstract

Electroencephalogram (EEG) is a non-invasive technology widely used to record the brain's electrical activity. However, noise often contaminates the EEG signal, including ocular artifacts and muscle activity, which can interfere with accurate analysis and interpretation. This research aims to improve the quality of EEG signals related to concentration by comparing the effectiveness of two denoising methods: Independent Component Analysis (ICA) and Principal Component Analysis (PCA). Using commercial EEG headsets, this study recorded Alpha, Beta, Delta, and Theta signals from 20 participants while they performed tasks that required concentration. The effectiveness of the denoising technique is evaluated by focusing on changes in standard deviation and calculating the Percentage Residual Difference (PRD) value of the EEG signal before and after denoising. The results show that ICA provides better denoising performance than PCA, as reflected by a significant reduction in standard deviation and a lower PRD value. These results indicate that the ICA method can effectively reduce noise and preserve important information from the original signal.
Comparison of Gain Ratio and Chi-Square Feature Selection Methods in Improving SVM Performance on IDS Ricky Aurelius Nurtanto Diaz; I Ketut Gede Darma Putra; Made Sudarma; I Made Sukarsa; Naser Jawas
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 15 No. 01 (2024): Vol. 15, No. 01 April 2024
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2024.v15.i01.p06

Abstract

An intrusion detection system (IDS) is a security technology designed to identify and monitor suspicious activity in a computer network or system and detect potential attacks or security breaches. The importance of accuracy in IDS must be addressed, given that the response to any alert or activity generated by the system must be precise and measurable. However, achieving high accuracy in IDS requires a process that takes work. The complex network environment and the diversity of attacks led to significant challenges in developing IDS. The application of algorithms and optimization techniques needs to be considered to improve the accuracy of IDS. Support vector machine (SVM) is one data mining method with a high accuracy level in classifying network data packet patterns. A feature selection stage is needed for an optimal classification process, which can also be applied to SVM. Feature selection is an essential step in the data preprocessing phase; optimization of data input can improve the performance of the SVM algorithm, so this study compares the performance between feature selection algorithms, namely Information Gain Ratio and Chi-Square, and then classifies IDS data using the SVM algorithm. This outcome implies the importance of selecting the right features to develop an effective IDS.
Strategi Penyetelan Hyperparameter untuk YOLOv8n dalam Pemantauan Lalu Lintas Pasca-Kecelakaan Real-Time I Nyoman Eddy Indrayana; Made Sudarma; I Ketut Gede Darma Putra; Anak Agung Kompiang Oka Sudana
Jurnal Teknologi Informasi dan Pendidikan Vol. 19 No. 2 (2026): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v19i2.1132

Abstract

Traffic accidents continue to provide a considerable difficulty in contemporary transportation systems, frequently leading to vehicle damage and heightened risks for pedestrians on streets. Precise and instantaneous identification of post-accident scenarios is thus crucial for facilitating swift response and sophisticated traffic management. This research introduces a streamlined object detection methodology utilizing YOLOv8n to recognize six essential traffic-related categories: bus, automobile, damaged vehicle, motorbike, pedestrian, and truck. The main aim is to examine the impact of hyperparameter modification on detection efficacy, specifically in recognizing damaged automobiles as signs of post-accident situations. Twelve model configurations were created by systematically altering three hyperparameters: learning rate (0.01, 0.001, and 0.0001), batch size (32 and 64), and optimizer type (Adam and MuSGD). All models underwent training for 200 epochs with a dataset derived from actual traffic situations, augmented by techniques such as grayscale transformation, blurring, and rotation. The performance evaluation utilized precision, recall, F1-score, mAP50, and mAP50:95. The findings indicate that hyperparameter selection substantially influences convergence stability and detection accuracy. The optimal model attained a mAP50 of 0.905 and a mAP50:95 of 0.751, utilizing a learning rate of 0.01, a batch size of 64, and the Adam optimizer. Moreover, substantial items like cars, buses, and trucks were identified with high precision, whereas damaged vehicles and pedestrians necessitated more meticulous calibration due to increased visual variability.The findings indicate that optimized lightweight models can attain competitive performance, rendering them appropriate for real-time intelligent traffic monitoring applications.
Smart Stego: A Web Application for Hiding Secret Data in Images with LSB and CNN I Gede Totok Suryawan; Made Sudarma; I Ketut Gede Darma Putra; Anak Agung Kompiang Oka Sudana
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.1008

Abstract

This study develops a web-based steganography model to insert the identity of artisans in the form of palmprint images into the image of gringsing ikat woven cloth as a medium for ownership authentication. The method used in the insertion process combines a Convolutional Neural Network and the Least Significant Bit. In contrast, extracting or re-introducing palmprint images from stego images is carried out using a CNN-based classification model. This system was tested with two scenarios; in the first scenario, one palmprint image was inserted into 26 different cloth motifs, while in the second scenario, one cloth motif was inserted into 99 different palmprint images. The test results showed that the system produced consistent confidence values for all cloth motifs in the first scenario. In contrast, in the second scenario, the system achieved an average confidence of 93.5% and a recognition accuracy of 87%. The developed application has proven to be efficient with a reduction in stego image size of up to 66% while maintaining the quality of the stego image, as well as a speedy average execution time of 0.15 seconds for insertion and 0.09 seconds for extraction. These findings prove that the developed steganography model can effectively insert and re-recognize identity images (palmprints) in woven cloth images and has the potential to be applied as an image-based craft product ownership verification system.
EEG-Based Focus Analysis to Evaluate the Effectiveness of Active Learning Approaches I Putu Agus Eka Darma Udayana; Made Sudarma; I Ketut Gede Darma Putra; I Made Sukarsa; Minho Jo
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.1068

Abstract

Electroencephalography (EEG) has emerged as a non-invasive and objective technique for monitoring brain activity in real time, widely applied to measure cognitive states such as concentration and alertness. Its ability to capture brain responses during learning processes makes EEG a promising tool to evaluate student engagement more accurately than conventional methods. This study investigates the effectiveness of two active learning methods, Project-Based Learning (PjBL) and Problem-Based Learning (PBL), in the context of English tutoring for elementary students using EEG signals as a cognitive indicator. A total of 20 students aged 8–12 years from ThinkerBee Learning Centre Bali participated in the study. EEG data were recorded using the Muse 2 Headband while students completed test-based tasks designed for each learning method. The EEG signals were preprocessed using bandpass filtering, Continuous Wavelet Transform (CWT), and frequency band decomposition. Concentration scores were then calculated using two approaches: a heuristic method based on the Beta/(Theta + Alpha) ratio and a Long Short-Term Memory (LSTM) model. The heuristic method produced average scores of 0.3991 (PjBL) and 0.3822 (PBL), with a 4.42% difference, while the LSTM model showed a more substantial difference, with scores of 0.5454 (PjBL) and 0.4265 (PBL). A Spearman correlation test between EEG-derived scores and students’ academic results yielded a perfect correlation value of 1.0000, indicating a strong relationship between cognitive engagement and learning outcomes. These results demonstrate the potential of EEG as a reliable tool for objectively assessing learning effectiveness in primary education contexts.
Classification of Ceremonial Plants with Vision Transformer Ida Bagus Kade Dwi Suta Negara; I Ketut Gede Darma Putra; Made Sudarma; I Made Sukarsa
International Journal of Management Science and Information Technology Vol. 6 No. 2 (2026): July - December 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijmsit.v6i2.7992

Abstract

The rapid advancement of computer vision technology has accelerated the adoption of artificial intelligence in agriculture, particularly for plant image classification tasks. However, the identification of ceremonial plants remains challenging due to the high visual similarity among species and the continued reliance on manual identification methods, which are time-consuming and require expert knowledge. Unlike previous studies that primarily focused on general crop species or plant disease classification, this study specifically investigates the application of the Vision Transformer (ViT) model for the classification of ceremonial plants, which represent culturally significant plant species with distinctive yet visually similar characteristics. An experimental approach was employed using a dataset of 1,244 ceremonial plant images representing seven classes, with the data divided into training, validation, and testing sets at proportions of 70%, 15%, and 15%, respectively. A pretrained Vision Transformer model was fine-tuned by adapting its classification head to the target classes and evaluated using accuracy, precision, recall, F1-score, and confusion matrix metrics. The experimental results demonstrate that the proposed model achieved a test accuracy of 97.33% and an average class accuracy of 97.01%, indicating its effectiveness in learning complex visual representations and accurately distinguishing visually similar ceremonial plant species. These findings demonstrate the feasibility of Vision Transformer for culturally specific plant recognition and provide a reliable baseline for the development of intelligent ceremonial plant identification systems, contributing to the digital preservation of traditional botanical knowledge and AI-based plant recognition applications.
Co-Authors A. A. K. Oka Sudana Adie Wahyudi Oktavia Gama Agung Udayana Putra Ahmad Catur Widyatmoko Anak Agung Ketut Agung Cahyawan Wiranatha Anak Agung Kompiang Oka Sudana Anindya Santika Devi Ariana, Anak Agung Gede Bagus Arsa, Dewa Made Sri Arya Widyaningrat, Made Gunawan Astutik, Dian Bagus Yudistira Citra Arum Sari Desak Ayu Savita Desak Ayu Sista Dewi Desy Purnami Singgih Putri Dewa Agung Krishna Arimbawa P Dewa Ayu Nadia Taradhita Dewa Made Sri Asra Dwi Putra Githa Dwi Rusjayanthi, Dwi Erdiawan Erdiawan Erdiawan Erdiawan Erdiawan Erdiawan, Erdiawan G M Arya Sasmita Gede Eridya Bayu Gede Ngurah Pasek Pusia Putra Gede Riska Wiradarma I Dewa Gede Wahya Dhiyatmika I Gede Aditya Nugraha I Gede Galang Surya Prabawa I Gede Hendra Parwata I Gede Suarjana I Gede Sujana Eka Putra I Gede Sujana Eka Putra, I Gede Sujana Eka I Gede Totok Suryawan I Gusti Ayu Agung Diatri Indradewi I Gusti Ayu Triwayuni I Gusti Made Ngurah Ardi Yasa I Gusti Ngurah Dwiva Hardijaya I Kadek Erik Priyanto I Kadek Surya Widiakumara I Ketut Adi Purnawan I Made Agus Dwi Suarjaya I Made Aris Satia Widiatmika I Made Budi Adnyana I Made Budi Sentana I MADE SUDARMA I Made Sukafona I Made Sukarsa I Made Sukarsa I Made Sunia Raharja I Made Suwija Putra I Made Suwija Putra, I Made I Made Yudha Arya Dala I N Satya Kumara I Nyoman Eddy Indrayana I Nyoman Gede Arya Astawa I Nyoman Gunantara I Nyoman Piarsa I Nyoman Putu Suwindra I Nyoman Satria Paliwahet I Putu Adi Purnawan I Putu Agung Bayupati I Putu Agus Eka Darma Udayana I Putu Agus Eka Darma Udayana, I Putu Agus Eka I Putu Agus Eka Pratama I Putu Arya Dharmaadi I Putu Bayu Krisnawan I Putu Indra Permana I Putu Jordi Astika I Putu Satwika Putra I Putu Yoga Pertama Yasa I Wayan Agus Surya Darma I Wayan Budi Sentana I Wayan Gunaya I Wayan Muka I Wayan Ryon Waryanta I Wayan Wahyu Gautama Ida Ayu Dwi Giriantari Ida Ayu Putu Febri Imawati Ida Bagus Kade Dwi Suta Negara Ida Bagus Nyoman Yoga Ligia Prapta Kadek Adi Praptha Kadek Suar Wibawa Komang Ayu Triana Indah Komang Budiarta Lie Jasa Linawati Linawati Luki Ardiantoro M Sudarma Made Adi Widyatmika Made Sudarma Made Sudarma Made Sudarma Mimin F Rohmah Minho Jo Minho Jo Minho Jo Naser Jawas Ni Kadek Ariasih, Ni Kadek Ni Kadek Dwi Rusjayanthi, Ni Kadek Ni Kadek Riska Sadini Ni Komang Surya Cahyani Putri Ni Komang Sutiari Ni Komang Widyasanti Ni Luh Gede Pivin Suwirmayanti, S.Kom, MT, Ni Luh Gede Pivin Ni Made Ary Esta Dewi W Ni Made Ary Esta Dewi Wirastuti Ni Made Ika Marini Mandenni Ni Putu Ayu Oka Wiastini Ni Putu Chendy Widya Santi Ni Putu Intan Waindika Dharma Ni Putu Ratindia Apriyanti Ni Putu Sutramiani Nyoman Purnama, Nyoman Nyoman Putra Sastra Nyoman S Kumara Nyoman Sumerta Yasa Perdana, I Putu Iduar Pirade, Evangelika Purnamaswari, Anak Agung Arimas Putra, I Made Suwija Putri Isma Oktawiani Putu Githa Pratiwi Putu Manik Prihatini Putu Putri Wrestra Saridewi putu roy nurbhawa Putu Wira Buana Ricky Aurelius Nutanto Diaz, Ricky Aurelius Riskiyanti, Zuraida Malini Cantika Risky Aswi Ramadhani Rosalia Hadi Rukmi Sari Hartati Rukmi Sari Hartati Siti Helmyati Sulya Arya Wasika Tri Ginarsa, I Nyoman Adi Wayan Oger Vihikan Wijayakusuma, I Gusti Ngurah Lanang Wira Bhuana Wira Bhuana, Wira Wiranatha, AA.Kt. Agung Cahyawan Yandi Perdana Yogiswara Dharma Putra Yudiadewi, Made Aprisintia Yusliza Binti Mohd Yasin