cover
Contact Name
Gst. Ayu Vida Mastrika Giri
Contact Email
vida@unud.ac.id
Phone
+6285737241069
Journal Mail Official
jeliku@cs.unud.ac.id
Editorial Address
-
Location
Kota denpasar,
Bali
INDONESIA
(JELIKU) Jurnal Elektronik Ilmu Komputer Udayana
Published by Universitas Udayana
ISSN : 23015373     EISSN : 26545101     DOI : https://doi.org/10.24843/JLK
Core Subject : Science,
Aim and Scope: JELIKU publishes original papers in the field of computer science, but not limited to, the following scope: Computer Science, Computer Engineering, and Informatics Computer Architecture Parallel and Distributed Computer Computer Network Embedded System Human—Computer Interaction Virtual/Augmented Reality Computer Security Software Engineering (Software: Lifecycle, Management, Engineering Process, Engineering Tools and Methods) Programming (Programming Methodology and Paradigm) Data Engineering (Data and Knowledge level Modeling, Information Management (DB) practices, Knowledge Based Management System, Knowledge Discovery in Data) Network Traffic Modeling Performance Modeling Computer Security IT Governance Networking Technology Robotic Instrumentation Information Search Engine Multimedia Security Information Retrieval Mobile Processing Natural Language Processing Artificial intelligence & soft computing and their applications Neural networks Machine Learning Reasoning and evolution Intelligence applications Computer vision and speech understanding Multimedia and cognitive informatics Data mining and machine learning tools, heuristic and AI planning strategies and tools, computational theories of learning
Articles 488 Documents
Pengembangan Model Ontologi Pada Sistem Informasi Bahasa Bali
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p04

Abstract

Balinese is the language of communication for the Balinese ethnic community. The Balinese language has a coarse to fine vocabulary called anggah-ungguhing basa Bali. The Balinese language is increasingly being abandoned by the younger generation of Bali. To help overcome these problems, the Balinese language needs to be built using the Balinese language system using the concept of a semantic ontology. The ontology development method used is Methontology and produces a consistent and valid ontology. The system built will be able to provide information about Balinese words. The system features semantic browsing, semantic search, and opposite words. To ensure system functionality, Black-Box testing was carried out. The result is that the system has good functionality.
Cover & Table of Contents JELIKU Vol. 11 No. 3
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 2023
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

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

Abstract

Pengembangan Sistem Pengenalan Karakter Aksara Suku Simalungun Berbasis Android
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p18

Abstract

Simalungun script is the script used by the Simalungun people to communicate with each other in their time. But over time, this character is rarely used. Therefore, the Simalungun script needs special attention because it is already threatened with extinction due to limited data and information. To overcome this, it is necessary to use the role of information technology. In this study, a system was built that can classify and introduce the Simalungun tribal characters using the Android-based Convolutional Neural Network (CNN) method. In addition, in this study, CNN MobileNetV2 and TensorFlow Lite architectures were used for deploying android needs. From the results of the training using the MobileNetV2 architecture by testing 29 characters, the accuracy results are 81% and the test results are 82%. In testing the feasibility of the application, the author uses the concept of usability testing by involving 15 respondents and giving a percentage of 78%.
Implementasi Metode Hybrid Particle Swarm Optimization dan Genetic Algorithm Pada Penjadwalan Job Shop Scheduling
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p09

Abstract

Job shop problem is one of the non-deterministic combinatorial optimization problems with polynomial time (NP-complete). Genetic Algorithm optimization will be applied to solve Job Shop problems. hybrid particle swarm optimization. In this study.This Study is an attempt to solve Job Shop Scheduling problem using hybrid particle swarm optimization and genetic algorithm method, to find minimum Makespan. 5 parameters, C1, C2, inertia weight, crossover rate and mutation rate, will be compared with a range from 0.1 to 1 with difference 0.2, the test will look for combination parameter ??that get the minimum Makespan, The results of the implementation of the hybrid particle swarm optimization method and genetic algorithm are makespan of 29 days is obtained with an objective function value of 0.0043, with optimal parameters (C1) = 0.7, (C2) = 0.3, (w) = 0.3, (Cr) = 0.5, and (Mr) = 0.7.
Pengenalan Pola Karakter Tulisan Tangan Aksara Bali Menggunakan Fitur Zoning, Direction, dan Backpropagation
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p23

Abstract

Balinese script has a character with high similarity. Identifying classes between characters requires an optimal pattern recognition model by maximizing the use of feature extraction methods. The use of feature extraction methods in the dataset aims to obtain the characteristic value of each character, in the case of Balinese script data, a method with detailed feature retrieval is used using the zoning method. This study also added the additional factor of the direction feature. The learning method uses a neural network with a backpropagation algorithm. Tests on character data get the highest accuracy in the combination of 16x16 zone ICZ + ZCZ zoning features with the addition of direction features that are 91.18%, ZCZ zone 16x16 zoning and direction with 86.82% accuracy, and ICZ zoning 16x16 and direction zones with 82.43% accuracy. The highest increase in accuracy is found in the ZCZ feature with a difference of addition of 4.36%. The implementation of the model in word testing has an accuracy of 66.2 % and the results of segmentation testing are 97.33 %.
Klasifikasi Aksara Bali Berbasis Suara Dengan Metode KNN dan FastDTW
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p14

Abstract

Bahasa Bali merupakan bahasa yang digunakan masyarakat Bali untuk berkomunikasi. Untuk menulis bahasa Bali, mereka dapat menggunakan Aksara Bali. Pada era globalisasi ini, aksara Bali mulai di tinggalkan oleh masyarakat atau mulai menuju kepunahan. Saat ini aksara Bali membutuhkan pengembangan di dunia digital sehingga mampu menyesuaikan dengan perkembangan jaman, khususnya pada media pembelajaran seperti sebuah aplikasi. sebelum membangun aplikasi perlu dibuatkan sebuah sistem yang dapat mendukung aplikasi tersebut. Penulis membuat sistem klasifikasi dengan metode KNN dan FastDTW untuk mengenali suara aksara Bali khususnya aksara Wreasta. Hasil penelitian yang telah dilakukan mendapatkan akurasi yang baik yaitu 100% pada model klasifikasi dengan nilai k-3, k-5, k-7 dan k-9 serta akurasi terendah pada k-19 dengan akurasi 94,44%
Perancangan Aplikasi Sistem Informasi Kain Tenun Endek Bali
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p05

Abstract

Bali memiliki banyak warisan budaya yang dapat menambah daya tarik wisatawan domestik maupun internasional. Salah satu warisan budaya tersebut adalah kain Endek Bali. Endek adalah kain tenun yang berasal dari Bali. Endek Bali umumnya dipakai untuk upacara adat, namun seiring berjalannya waktu kini banyak digunakan sebagai pakaian sehari-hari, seragam kantor dan seragam sekolah. Setiap Endek memiliki ciri khas berupa motif yang berbeda-beda. Umumnya ada yang memiliki motif fauna dan fauna, ukiran hingga wayang. Karena warisan budaya ini perlu dilestarikan agar tidak punah, maka diperlukan solusi untuk mewujudkannya dalam bentuk digital. Dalam mengatasi masalah tersebut, digunakan konsep ontologi semantik untuk merepresentasikan warisan budaya ini dalam bentuk digitalisasi. Pengembangan model ontologi ini nantinya dapat digunakan kembali untuk terus dikembangkan oleh penelitian selanjutnya. Ontologi Endek Bali menghasilkan 19 kelas, 16 properti objek, 2 properti data, dan 124 individu.
Analisis Sentimen Berbasis Aspek Ulasan Pelanggan Hotel di Bali Menggunakan Metode Decision Tree
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p19

Abstract

The main means of tourism is the accommodation industry. Therefore, accommodation cannot be separated from the tourism industry because they both need each other. One of the accommodations that is most closely related to tourism is hospitality accommodation. With the increasing number of hotels in Bali, the hotel certainly needs the right marketing strategy. So, it is necessary to process customer reviews automatically to determine sentiment analysis based on customer reviews based on certain aspects. In this study, the author builds a model for aspect-based sentiment analysis using the Decision Tree method. The data used in this study is hotel customer review data in Indonesian language. Evaluation is done by measuring the performance of the Decision Tree model. The Decision Tree model for aspects produces performance, accuracy, precision, recall, and F1-Score, respectively 82,5%, 80%, 90,9%, and 85,1%, the Decision Tree model for service aspect sentiment produces accuracy, precision, recall performance , and F1-Score, respectively, which are 75%, 72,7%, 80%, and 76,2%, while the Decision Tree model for the sentiment of cleanliness aspect produces performance of accuracy, precision, recall, and F1-Score, respectively, which is 81,8%, 87,5%, 77,8%, and 82,4%.
Klasifikasi Motif Kain Tradisional Cepuk Menggunakan GLCM dan KNN
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p10

Abstract

Cepuk weaving is one of the typical woven fabrics from the Balinese area, precisely in Tanglad Village, Nusa Penida District, Klungkung Regency, which is usually used by the people of Nusa Penida for ceremonial/ritual needs, such as cutting teeth, cremation, melukat to daily clothing needs. For generations, Tanglad has six types of cepuk, namely Mekawis, Amethyst, Lingking Paku, Tangi Gede, Sudamala, and Kurung. Each type has a different motif with a distinctive color. Therefore, this study was conducted to determine whether the selection of features affects the accuracy value resulting from the system testing carried out, as well as introducing cepuk fabrics to the general public using AI that can classify types of cepuk woven fabrics using the (K-Nearest Neighbor) KNN method, after performing the feature extraction using (Grey Level Co-occurrence Matrix) GLCM method. The features taken are Contrast, Energy, Entropy, Homogeneity, Dissimilarity, ASM (Angular Second Moment), and IDM (Inverse Differential Moment), with variations in the angle of 0º, 45º, 90º, 135º. Based on research conducted on 44 testing data with 11 data for each class, the results obtained are 91.7% accuracy using the parameter value of k = 3.
Diagnosis Penyakit Retinopati Diabetes Menggunakan SVM dengan Optimasi Algoritma Genetika
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 11 No 3 (2023): JELIKU Volume 11 No 3, February 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.v11.i03.p01

Abstract

Diabetes mellitus is a non-communicable disease that is widely infected in the community. People with diabetes mellitus often do not realize that they are infected and are only known after complications occur. Diabetic retinopathy is one of the complications of diabetes mellitus. Diabetic retinopathy occurs when the vessels in the retina are damaged, causing visual disturbances. Diabetic retinopathy is divided into 2 stages, namely Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR).This study diagnoses diabetic retinopathy using classification methods, namely SVM and GLCM as feature extraction methods. In addition, this study adds an optimization method, namely genetic algorithms to determine the optimal parameters for SVM. The amount of data used is 885 images with 3 labels, namely Normal, NPDR, and PDR. The test results in this study, SVM with genetic algorithms get better results than SVM without optimization. In SVM without F1 optimization the highest score was obtained at 0.7372 while in SVM with F1 optimization the highest score was obtained at 0.7578 with an increase in the percentage of F1 Score by 2.06%.