Article Per Year (5 Year)
p-Index From 2021 - 2026
8.704
P-Index
This Author published in this journals
All Journal Jurnal Matematika Jurnal Ilmu Komputer (JELIKU) Jurnal Elektronik Ilmu Komputer Udayana E-Jurnal Matematika AdMathEdu : Jurnal Ilmiah Pendidikan Matematika, Ilmu Matematika dan Matematika Terapan PYTHAGORAS: Jurnal Program Studi Pendidikan Matematika Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) Jurnal WIDYA LAKSMI (Jurnal Pengabdian Kepada Masyarakat) Jurnal Pengabdian Informatika (JUPITA) Prosiding Seminar Nasional Universitas Ma Chung Jurnal Nasional Teknologi Informasi dan Aplikasinya
I Gede Santi Astawa
Program Studi Teknik Informatika, Jurusan Ilmu Komputer. Fakultas Matematika Dan Ilmu Pengetahuan Alam, Universitas Udayana
Humanities Computer Science & IT Education Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Public Health Other

Published : 86 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 86 Documents
Search

 4   5   6   7   8 
Deteksi Rasa Buah Jeruk Siam Kintamani Menggunakan SVM dengan Optimasi Algoritma Genetika Ni Wayan Yulia Damayanti; I Gede Arta Wibawa; I Gede Santi Astawa; Anak Agung Istri Ngurah Eka Karyawati
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 13 No 1 (2024): JELIKU Volume 13 No 1, August 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

Kintamani Siam oranges are one of the important commodities in Indonesian agriculture, especially in Bangli Regency, Bali. However, assessing the quality of orange taste still often relies on subjective manual identification. In an effort to enhance objectivity and consistency in assessing orange quality, this study proposes the use of Support Vector Machine (SVM) algorithm optimized with genetic algorithm. The aim of this research is to detect the quality of Kintamani Siam orange taste based on texture characteristics in orange images. Test results show that SVM optimized with genetic algorithm has better accuracy than SVM without optimization. For instance, SVM without optimization yields an accuracy of 0.78, while after optimization with genetic algorithm, the accuracy increases to 0.80. These results indicate the significant potential of genetic algorithm in improving the performance of SVM in detecting the quality of Kintamani Siam orange taste, which can help enhance efficiency and consistency in the orange industry.
Perbandingan Kriptografi Klasik Hill Cipher dengan Affine Cipher dalam Pengamanan Data Citra I Nyoman Dwi Pradnyana Putra; I Gede Santi Astawa
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 12 No 3 (2024): JELIKU Volume 12 No 3, February 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JLK.2023.v12.i03.p06

Abstract

The development of technology affects several aspects of life, especially in securing confidential data and information. Because of this, there is a way to secure data, namely cryptography, many cryptography techniques have been implemented to hide data information, one of which image data, the purpose of securing image data is to prevent unwanted things such as fraud by using other people’s identities supported by personal photos. In this research, two classical cryptography algorithms will be tested, namely hill cipher and affine cipher by comparing the MSE and PSNR Image values when encryption is carried out. The encryption process is done 6 times with different image in each algorithm, the results of the encryption are compared between the results of the hill cipher encryption image with the affine cipher
Penerapan Metode Content Based Filtering Dan K-Nearest Neighbor Dalam Sistem Rekomendasi Musik I Made Teja Sarmandana; I Made Widiartha; Luh Arida Ayu Rahning Putri; I Gede Santi Astawa
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 13 No 1 (2024): JELIKU Volume 13 No 1, August 2024
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

Current technological developments are able to change the way the younger generation enjoys music, where music can now be packaged in digital form, which is a new innovation in the music industry in Indonesia. Given the large amount of music data available on the internet, a system that provides services for users to search for their favorite music is really needed. The recommendation system will provide relevant information based on the preferences that the user wants to search for. Content Based Filtering recommends that users utilize the information contained in the data to use as parameters. The K-Nearest Neighbor (K-NN) algorithm is a method of classifying objects based on the closest training data to the object under test. In this study, accuracy testing techniques were used to measure the performance of the classification that has been carried out. The classification process that was created succeeded in obtaining the highest accuracy value at 90,49% with a value of k=9 which shows that the classification and recommendation process can run quite well. Keywords: Accuracy, Content Based Filtering, Classification, Recommendation System, K-Nearest Neighbor, Music
Sistem Rekomendasi Seri Animasi Jepang (Anime) Menggunakan User-Based Collaborative Filtering dan Spearman Rank Correlation Coefficient I Kadek Gowinda; I Gede Santi Astawa; I Gusti Ngurah Anom Cahyadi Putra; Ngurah Agus Sanjaya; Ida Bagus Gede Dwidasmara; I Dewa Made Bayu Atmaja Darmawan
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 12 No 2 (2023): JELIKU Volume 12 No 2, November 2023
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JLK.2023.v12.i02.p26

Abstract

The number of existing anime is increasingly varied and more in line with the increasing number of enthusiasts. The surge in anime series among anime enthusiasts has become an obstacle to finding anime that matches their taste. This underlies the writer to create an anime recommendation system using User-Based Collaborative Filtering method. The research process consisted of several stages, namely data collection from the Kaggle website with 3 pieces of data uploaded, namely in the .csv format. Determination of users who have a correlation, using the Spearman Rank Correlation Coefficient method. Calculation of predictions using a weighted sum algorithm. The final stage is the implementation of the recommendations and evaluation of the recommendation system used to calculate the level of collaborative filtering using the Mean Absolute Error (MAE).. This research has output in the form of a website which has several components, namely Home Page, Login-Register, Search, Recommend, Result Page, Single View and Rating. Testing on the system uses MAE calculations which are carried out on 50 users with the most rating history. The results from the test show that the percentage of error obtained is 15.8% and the prediction accuracy results obtained are 84.12%. The smallest MAE value of the 50 profiles is 0.894933222 by Archaeon and the highest MAE value is 3.572438553 by Krunchyman.
Identifikasi Plat Nomor Kendaraan Di Indonesia Menggunakan Metode Convolutional Neural Network (CNN) I Nyoman Restu Muliarta; I Gede Santi Astawa
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 12 No 2 (2023): JELIKU Volume 12 No 2, November 2023
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JLK.2023.v12.i02.p11

Abstract

Seiring dengan perkembangan zaman, teknologi juga semakin berkembang. Contohnya dengan menggunakan suatu system yang mampu mengidentifikasi plat nomor kendaraan secara efisien dan akurat. Contoh metode yang digunakan adalah metode CNN. CNN atau Convolutional Neural Network merupakan salah satu metode deep learning yang sering digunakan untuk pengenalan citra. Hal ini disebabkan karena metode CNN berkonsep system pengenalan citra pada visual cortex manusia sehingga memiliki kemampuan mengolah citra informasi. Dengan menggunakan metode ini, dapat mengenali simbol pada plat nomor kendaraan. Penelitian ini menggunakan beberapa sampel gambar plat kendaraan yang diambil dari berbagai media. Berdasarkan hasil penelitian yang telah dilakukan maka diperoleh hasil, yaitu tingkat keakuratan dalam mendeteksi setiap karakter pada plat kendaraan.
Perancangan Sistem Penyisipan Pesan pada Gambar dengan Metode Least Significant Bit (LSB) Berbasis Website Saputra, I Wayan Wirahadi; Astawa, I Gede Santi
Jurnal Nasional Teknologi Informasi dan Aplikasnya Vol 2 No 2 (2024): JNATIA Vol. 2, No. 2, Februari 2024
Publisher : Informatics Study Program, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

The advancement of digital communication and the need for secure information exchange have led to the development of various techniques for data hiding and steganography. One of the widely used methods is the Least Significant Bit (LSB) technique, which allows the embedding of secret messages within digital images without perceptible visual changes. In this paper, we present the design and implementation of a message embedding system based on LSB method, integrated into a web-based platform. The proposed system provides a user-friendly interface for selecting an image and entering a secret message to be embedded. Utilizing HTML5 canvas and JavaScript, the system processes the selected image, extracts the LSB of each pixel, and replaces it with the corresponding bits of the secret message. The resulting image with the hidden message is then displayed to the user. Furthermore, the system offers the capability to extract the hidden message from an image previously processed by the system. The web-based nature of the system allows for easy accessibility and usage across different devices without the need for additional software installations. It provides a practical and interactive environment for users to experiment with message embedding techniques, thereby fostering understanding and awareness of data security issues. The experimental results demonstrate the effectiveness and efficiency of the system in embedding and extracting messages from various images while maintaining satisfactory visual quality. The system's user-friendly interface, combined with its robust functionality, makes it a valuable tool for users interested in secure communication and digital steganography. Keywords: Data hiding, steganography, Least Significant Bit (LSB), image processing, web-based system
Analisis Emosi Anjing Melalui Klasifikasi Citra untuk Deteksi Ekspresi Wajah Hewan Peliharaan Adi Pradana, I Gede Surya; Astawa, I Gede Santi
Jurnal Nasional Teknologi Informasi dan Aplikasnya Vol 2 No 4 (2024): JNATIA Vol. 2, No. 4, Agustus 2024
Publisher : Informatics Study Program, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2024.v02.i04.p06

Abstract

Emotion Detection in Dogs through Image Classification for Pet Facial Expression Analysis utilizes convolutional neural networks (CNNs) to discern and quantify dogs' emotional states based on their facial expressions. This approach leverages advanced image processing techniques to recognize subtle cues indicative of various emotions like happiness, fear, or sadness in dogs. By applying CNNs to analyze image data, pet owners can gain valuable insights into their dogs' emotional well-being and address their needs accordingly. This technology offers a promising avenue for enhancing the bond between pets and owners by facilitating more informed and empathetic care tailored to each dog's emotional state and personality. Keywords: Emotion Recognition, Dog Facial Expressions, Image Classification, Convutional Neural Networks (CNNs), Pet Well-Being
Analisis Clustering Paket Data Internet di Indonesia Menggunakan Metode K-Means Wijaya, I Putu Ananta; Astawa, I Gede Santi
Jurnal Nasional Teknologi Informasi dan Aplikasnya Vol 1 No 1 (2022): JNATIA Vol. 1, No. 1, November 2022
Publisher : Informatics Study Program, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

Disruption of technology and the impact of the recent pandemic has made people access the internet longer than before, especially with smartphones. Before accessing the internet, users must purchase a data package provided by an internet service provider. Various data packages are provided by internet service providers. Starting from network coverage, speed, number of quotas, active period, to tariffs are the choices of each operator. These various offerings often make users confused because they have to adjust to economic conditions. The existence of knowledge analysis in the database, grouping data packets can be done using the k-means method. K-means groups data by iterating and creating groups based on the closest distance of the data to the center point. K-means is very widely used because of its simplicity. Before clustering, the data will go through a preprocessing process. The end result is four clusters that have their own characteristics. For example, cluster four has the characteristics of a small quota with a long active period, which is suitable for the typical community who only wants to stay connected to the internet for communication.
Perlindungan pada Citra Motif Kain Endek dengan Teknik Watermarking menggunakan DCT Steganography Dewi, Dewa Agung Ayu Mutiara; Astawa, I Gede Santi
Jurnal Nasional Teknologi Informasi dan Aplikasnya Vol 2 No 1 (2023): JNATIA Vol. 2, No. 1, November 2023
Publisher : Informatics Study Program, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

This research develops a steganographic watermarking technique using the DCT method to protect the Endek fabric motifs. In DCT-based steganography method for watermark embedding in images, DCT transformation is used to separate the image into DCT coefficients that represent frequency information. The embedded watermark serves as an identification mark that is difficult to remove or modify without damaging the authenticity of the original motif. Accuracy testing using PSNR and MSE yielded average PSNR (54.367dB) and MSE (0.234), indicating that this technique is effective in preserving the authenticity and integrity of the Endek fabric motifs.
Klasifikasi Penyakit HepatitisC Menggunakan Algoritma Support Vector Machine Trisnawati, Ni Kadek; Astawa, I Gede Santi
Jurnal Nasional Teknologi Informasi dan Aplikasnya Vol 1 No 4 (2023): JNATIA Vol. 1, No. 4, Agustus 2023
Publisher : Informatics Study Program, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

Hepatitis is an inflammation of the liver which is often caused by a virus. Hepatitis that lasts less than 6 months is called "acute hepatitis", hepatitis that lasts more than 6 months is called "chronic hepatitis" Hepatitis consists of various types starting from hepatitis A, B, C, D and E. This study will discuss the classification Hepatitis C is classified as blood based (blood donor), suspected blood donor, fibrosis (moderate to severe hepatitis) and cirrhosis (chronic hepatitis). Classification uses the Support Vector Machines (SVM) algorithm with Confusional Matrix testing. The dataset used was obtained from the kaggle.com site with a total of 590 data consisting of 14 features or attributes. This study produces an accuracy of 93%. Keywords: Hepatitis, Support Vector Machines (SVM)
Co-Authors Adi Pradana, I Gede Surya Agus Juniartha, I Wayan Agus Prayogo Anak Agung Istri Ngurah Eka Karyawati Anak Agung Istri Ngurah Eka Karyawati Apsari, Made Sri Ayu Cahyani, Ni Putu Intan Christirahma, Ratri Desy Cokorda Rai Adi Pramartha Dewa Agung Ayu Mutiara Dewi Dewi, Dewa Agung Ayu Mutiara Dharma, Nyoman Hendradinata G.K. GANDHIADI Gede Gery Sastrawan Gede Maharta Pamuji Gorianto, Frisca Olivia Gotra, Anak Agung Ngurah Mahadana Apta Gst. Ayu Vida Mastrika Giri I Dewa Made Bayu Atmaja Darmawan I Gede Arta Wibawa I Gusti Agung Gede Ary Mahayasa I Gusti Agung Gede Arya Kadyanan I Gusti Ayu Purnami Pinatih I Gusti Ngurah Anom Cahyadi Putra I Gusti Ngurah Bagus Pramana Putra I Kadek Gowinda I Kadek Gowinda I Komang Ari Mogi I Komang Ari Mogi I Made Teja Sarmandana I Made Widiartha I Made Widiartha I Made Widiartha I Nyoman Dwi Pradnyana Putra I Nyoman Restu Muliarta I Putu Ananta Wijaya I Putu Gede Hendra Suputra I Putu Indie Surya Jayadi I Putu Rama Anadya I Putu Ryan Paramaditya I Putu Sedana Wijaya I Wayan Agus Juniartha I WAYAN SANTIYASA I Wayan Supriana Ida Ayu Taria Putri Mahadewi Ida Bagus Gede Bayu Priyanta Ida Bagus Gede Dwidasmara Ida Bagus Made Mahendra Jonas Kuntoro Junior, Vodka Joe Kadek Vincky Sedana Kompiang Gede Sukadharma Luh Arida Ayu Rahning Putri LUH PUTU IDA HARINI Made Darma Yunantara Marselinus Putu Harry Setyawan Ngurah Agus Sanjaya ER Ni Kadek Trisnawati Ni Made Novia Nurtiani Ni Made Rai Nirmala Santhi Ni Putu Intan Cahyani Ni Wayan Yulia Damayanti Nurtiani, Ni Made Novia Nyoman Hendradinata Dharma Pasha Renaisan Pradyto, Kadek Dwitya Adhi Prashanti, Ni Putu Vidya Vira Prawira, Agus Prebiana, Kiki Dwi Putra, Putu Pasek Wahyu Chandra Putri Cahyaning Putu Bayu Baskara Raharja, Made Agung Rasita Natasya Br Sitepu Renaisan, Pasha Restu Muliarta, I Nyoman Roger Julian Sitorus Saputra, I Wayan Wirahadi Sitorus, Roger Julian Suwitra, I Made Pradnyanandana Suwitra Theresia Seftiani Girsang Trisnawati, Ni Kadek Valerie Laurent Wijana, Sawendo Eko Wijaya, I Putu Ananta Yowe, Samson Cornelius Gele