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

 1   2   3   4   5 
The Influence of Changes in ANN Hidden Layer Unit and Feature Selection on Classification Wijana, Sawendo Eko; Astawa, I Gede Santi; Karyawati, AAIN Eka
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 9 No 3 (2021): JELIKU Volume 9 No 3, Februari 2021
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.2021.v09.i03.p05

Abstract

Abstract Classification is the process of differentiating a set of models into several data classes. There are many methods that can be used for the classification process, one of which is the Artificial Neural Network method. Neural networks are a computational method that mimics biological syafar networks. Artificial condition networks can be used to model complex relationships between input and output to recognize patterns in data [1]. In this study, testing was conducted to determine the effect of uncorrelated or low-correlation features in the data classification process and the effect of changing the number of units in the hidden layer on the classification results. The data used in this study were liver disease dataobtained from the Kaggle Dataset.Where in comparing the results of using feature selection, it is divided into 4 predetermined scenarios through the search for significance values ??with the SPSS correlation test.In the results of the implementation of the Multilayer Perceptron which aims to determine the effect of feature selection on the classification results, the results are that feature selection does not really affect the computation time obtained, and correlated data has more influence on the accuracy obtained when compared to uncorrelated data. In the results of the implementation of the Multilayer Perceptron which aims to determine the effect of changing the number of hidden layer units on the classification results, the results show that changes in the number of units in the hidden layer in Artificial Neural Networks have increased significantly in accuracy in several scenarios, but the computation time increases if the number of units in the hidden layer increases. Keywords: Classification, Artificial Neural Network, Liver Disease, Accuracy, Time.
Analysis of the Effect of Feature Reduction on Accuracy and Computational Time in Mushroom Dataset Classification Prayogo, Agus; Astawa, I Gede Santi
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 10 No 1 (2021): JELIKU Volume 10 No 1, Agustus 2021
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.2021.v10.i01.p15

Abstract

Classification is a technique to mapping the class of a certain data from its attribute or feature values. One of things that affects the classification result is the correlation of its features to the class classification results. Research conducted to determine the effect of the reduction in features that are least correlated or have a distant relationship with the classification result class (dependent variable). Because features that do not have much correlation, have no effect on the classification results. From the research, the accuracy of the reduction of each feature per test scenario has a range between 83% -88% higher than the initial accuracy without feature selection at 82% accuracy. Meanwhile, the computation time obtained does not have a significant difference in changing compared to without feature reduction, in the range of 2.3-2.7. For the data used is the Mushroom dataset obtained from the UCI Machine Learning Repository
Pengaruh Membership Function Pada Fuzzy Dempster-Shafer Gorianto, Frisca Olivia; Santi Astawa, I Gede; Arya Kadyanan, I Gusti Agung Gede
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 9 No 1 (2020): JELIKU Volume 9 No 1, Agustus 2020
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.2020.v09.i01.p08

Abstract

The classification process is the process of labeling a class of data sets that do not have a class label yet. In the classification process there will always be uncertainty. The uncertainty here is that there is a possibility that the label chosen is not right and causing doubts. One method that can be used to overcome uncertainty is to use the Fuzzy and Dempster-Shafer (DS) methods. This research combines the fuzzification step to get the Belief value which will then be used in the DS classification calculation. This research aims to determine the effect of using different types of Membership Function in the classification process and the optimal parameters used in each MF. This research will combine the Fuzzification step from Fuzzy method to obtain the Belief value which will be then used in DS classification calculation. The Fuzzification step uses triangle and bell Membership Function (MF) to produce Belief value for the class label. The MF curve parameter tests are divided into two parts, the first part is where the parameters of the center point of the curve are within the range of the input data and the second part is where the parameters of the center point of the curve are outside the range of the input data. The result show that the optimal parameters for the triangle MF are a1 = a2 = 4, b1 = b2 = 10, c1 = 0 and c2 = 11 and parameters for the bell MF are a1 = -11, b1 = 0, c1 = 11 and a2 = 0, b2 = 1, c2 = 22. 2. The results of the research also show that the shape of bell MF with an accuracy of 88.87% is better than triangle MF.
Optimasi Pembobotan Jaringan Syaraf Tiruan Pada Klasifikasi Kanker Payudara Prebiana, Kiki Dwi; Santi Astawa, I Gede; Supriana, I Wayan
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 9 No 1 (2020): JELIKU Volume 9 No 1, Agustus 2020
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.2020.v09.i01.p15

Abstract

Klasifikasi adalah proses membedakan sekumpulan model kedalam beberapa kelas data. Salah satu algoritma yang dapat digunakan untuk proses klasifikasi adalah Jaringan Syaraf Tiruan. Salah satu proses yang memepengaruhi proses Jaringan Syaraf Tiruan adalah proses pembobotan jaringan antar neuron pada Jaringan Syaraf Tiruan. Terdapat beberapa metode yang dapat digunakan dalam proses pencarian bobot, seperti algoritma genetika dan Particle Swarm Optimization atau PSO. PSO adalah salah satu metode optimasi pada Artificle Intelegent. Pada penelitian ini akan dilakukan proses pengujian pengaruh parameter PSO terhadap hasil akurasi yang diperoleh oleh Jaringan Syaraf Tiruan. Dari penelitian yang telah dilakukan nilai parameter terbaik PSO yang digunakan adalah w=0.8, c1=1.5, dan c2 = 2.2. Dari penelitian tersebut menunjukan bahwa optimasi pebobotan dengan Particle Swarm Optimization (PSO) dapat meningkatkan rata – rata nilai akurasi sebesar 0.5%.
Segmentasi Baris Aksara Bali Pada Citra Lontar Prashanti, Ni Putu Vidya Vira; Santi Astawa, I Gede; Ngurah Eka Karyawati, Anak Agung Istri; Santiyasa, I Wayan; Gede Dwidasmara, Ida Bagus; Supriana, I Wayan
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 10 No 2 (2021): JELIKU Volume 10 No 2, November 2021
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.2021.v10.i02.p03

Abstract

Indonesia merupakan negara kepulauan yang disetiap pulaunya memiliki kebudayaan yang berbeda-beda, seperti misalnya Pulau Bali yang sangat kaya akan warisan budaya, salah satunya yaitu aksara Bali. Aksara Bali merupakan lambang bahasa masyarakat Bali yang sampai saat ini masih digunakan. Salah satu media yang dimanfaatkan untuk menuliskan aksara Bali yaitu lontar dapat mengalami penurunan kualitas dikarenakan usia yang semakin tua. Hal tersebut tentunya berpengaruh terhadap tulisan aksara Bali yang terdapat pada lontar, sehingga menyulitkan pembaca untuk mengetahui informasi yang terkandung pada lontar tersebut. Upaya yang dapat dilakukan untuk menyelamatkan informasi yang terkandung pada lontar adalah dengan mengubahnya kedalam bentuk digital. Tulisan aksara Bali pada lontar terkadang memiliki jarak yang dekat antar baris aksara sehingga karakter aksara pada baris satu dengan karakter aksara pada baris lainnya bersentuhan. Aksara yang bersentuhan juga dapat menyulitkan pembaca memahami makna dari tulisan tersebut. Aksara yang paling sering bersentuhan adalah gantungan pada kasara baris atas dengan pengangge pada baris aksara dibawahnya. Oleh karena itu, diperlukan segmentasi baris untuk menemukan dan memperjelas baris pemisah antara aksara pada baris satu dengan aksara pada baris lainnya. Proses segmentasi baris aksara Bali dilakukan menggunakan Algoritma Genetika. Algoritma Genetika akan mencari kromosom dengan nilai fitness terbaik. Gen pada kromosom tersebut mewakili baris piksel citra biner yang diambil secara acak sesuai batas area segmentasi. Berdasarkan hasil pengujian yang telah dilakukan terhadap 10 bilah citra lontar, diperoleh hasil akurasi proses segmentasi baris aksara Bali menggunakan Algoritma Genetika adalah sebesar 92.17%.
VOCAL TONE PRECISION DETECTION USING HARMONIC PRODUCT SPECTRUM (HPS) AND K-NEAREST NEIGHBOR (KNN) CLASSIFICATION Apsari, Made Sri Ayu; Widiartha, I Made; Agung Raharja, Made; Santi Astawa, I Gede; Arta Wibawa, Gede; Made Mahendra, Ida Bagus
JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) Vol 10 No 3 (2022): JELIKU Volume 10 No 3, February 2022
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.2022.v10.i03.p01

Abstract

The progress of the digital era that is happening today, encourages rapid development in technology and science, one of which is in the field of art. Of all performing arts, the art of singing is the most complex, which requires a lot of preparation and practice. Everyone has a different type of voice. Males generally have three types of voice, namely bass, baritone, and tenor, while women generally have three types of voice, namely contralto (alto), mezzo-soprano, and soprano. However, not everyone knows what kind of voice they have. Therefore, this study will focus on classifying the human voice. In this study, the author uses the Harmonic Product Spectrum (HPS) and K-Nearest Neighbor (K-NN) algorithms. The data used is in the form of primary voice recording data obtained from 258 participants (male and female), where each person has 8 sound files, namely do, re, mi, fa, sol, la, si, and do'. saved in .wav format. From the research conducted, the test was carried out using the K-NN and K-NN methods with Hyperparameters. The results obtained in the form of accuracy of 74% and 81%, so that the Harmonic Product Spectrum (HPS) and K-Nearest Neighbor (K-NN) algorithms give good results for determining the type of human voice.
ALGORITMA PENGATURAN KINEMATIKA ROBOT REDUNDANT UNTUK MENGHINDARI TERJADINYA TUMBUKAN BERDASARKAN SKEMA PRIORITAS TUGAS GEDE SANTI ASTAWA; G.K. GANDHIADI
Jurnal Matematika Vol. 1, No. 1 April 2007
Publisher : Mathematics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JMAT.2007.v01.i01.p02

Abstract

A redundant manipulator has more degree of freedom than minimal needed to do its job. Inthis condition the manipulator can easily do the job, and can say become not optimal. To makethe manipulator more optimal, we try to add some obstacles that must be avoided by themanipulator. in calculation process we use inverse kinematics method in task priority scheme.From the simulation result, it is looked that by adding some jobs do not annoy the main job ofmanipulator, and those prove that the priority of the job can help manipulator do that job moreoptimal.
Rancang Bangun Penilaian Keaktifan Menggunakan Teknik Text Similarity Pada Sistem Tutorial Matematika Diskret I Gede Santi Astawa; Luh Putu Ida Harini; Putri Cahyaning
Jurnal Matematika Vol 5 No 2 (2015)
Publisher : Mathematics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JMAT.2015.v05.i02.p62

Abstract

Facility of student activeness in adaptif tutorial system expected be one of the supporting facilities. Activity of students in learning process is process that construct their own knowledge. They are actively building an understanding of the issues or anything they encounter in the learning process.  Because it is constructed from the inside, causing the activity is difficult to assess without having to do face to face, especially the tendency of students to be silent and conceal their ignorance will cause more difficult to assess the students' activity. In this study, the authors designed an extra feature on discrete mathematics tutorial system that has been built, in the form of an online discussion forum to help educators in scoring liveliness (seen from match students' comments and answer key). In this feature, the method used is the method of measuring similarity (similarity text) Rabin Karp to determine the similarity of the comments. Result of the research shows that the feature has been able to increase student interest in providing comments, which given an average of 2.2 comment in every single student. But rabin Karp algorithm used is still deemed less good if a comment is composed of words with errors in typing, necessitating the addition of other algorithms for increase system performance.
Perancangan Database dalam Sistem Pembelajaran Matematika Dasar Berbasis Konsep Guru dengan Peta Pikir Luh Putu Ida Harini; I Gede Santi Astawa
Jurnal Ilmu Komputer Vol 13 No 2 (2020): Jurnal Ilmu Komputer
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIK.2020.v13.i02.p07

Abstract

The basic concept of mathematics is a mathematical material that is very important to be mastered by students. One of the efforts to increase student understanding is the creation of a computer-based learning system that is able to provide material according to student understanding. Research on the use of mind maps in developing the concept of learning mathematics by teachers in increasing student understanding makes the background for research on the use of mind maps as a reference for making this computer-based learning system. From the results of the preliminary research that has been done, it can be concluded that the use of the concept of mind maps as a method of helping student learning has gone well according to user needs. And from the results of small scale testing by 10 teachers, the results obtained 75% of respondents rated the prototype "Very Good" and 25% rated "Good" Keywords: mind map, learning, computer-based systems
PENGGUNAAN METODE KECERDASAN BUATAN RUNUT MAJU DALAM MEMECAHKAN PERMASALAHAN GAME LABIRIN I Gede Santi Astawa
Jurnal Ilmu Komputer Vol. 5, No. 1 April 2012
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (520.635 KB)

Abstract

Games are an application that is quite attractive because it can be used for refreshing. Maze game is an example of a simple game that aims to determine the appropriate steps to achieve its intended purpose. Maze created in coordinates (x, y), with the known facts are the coordinates of obstacles, and the coordinates of current location, its main task is to find a way out. In this discussion, maze solved using artificial intelligence modeling (forward reasoning).
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