Garuda - Garba Rujukan Digital

p-Index From 2021 - 2026

4.399

P-Index

This Author published in this journals

All Journal International Journal of Electrical and Computer Engineering IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Ilmu Komputer (JELIKU) Jurnal Elektronik Ilmu Komputer Udayana Jurnal Buana Informatika Jurnal Teknologi Informasi dan Ilmu Komputer Proceeding of the Electrical Engineering Computer Science and Informatics JITK (Jurnal Ilmu Pengetahuan dan Komputer) Indonesian Journal of Global Health research Jurnal Pengabdian Informatika (JUPITA) Jurnal Nasional Teknologi Informasi dan Aplikasinya

Anak Agung Istri Ngurah Eka Karyawati

Program Studi Teknik Informatika, Fakultas Matematika Dan Ilmu Pengetahuan Alam, Universitas Udayana

Author-ID : 5951632

Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Health Professions Languange, Linguistic, Communication & Media Library & Information Science Nursing Public Health Other

Published : 41 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3 4 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

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%.

Ontology-based Why-Question Analysis Using Lexico-Syntactic Patterns A.A.I.N. Eka Karyawati; Edi Winarko; Azhari Azhari; Agus Harjoko
International Journal of Electrical and Computer Engineering (IJECE) Vol 5, No 2: April 2015
Publisher : Institute of Advanced Engineering and Science

This research focuses on developing a method to analyze why-questions. Some previous researches on the why-question analysis usually used the morphological and the syntactical approach without considering the expected answer types. Moreover, they rarely involved domain ontology to capture the semantic or conceptualization of the content. Consequently, some semantic mismatches occurred and then resulting not appropriate answers. The proposed method considers the expected answer types and involves domain ontology. It adapts the simple, the bag-of-words like model, by using semantic entities (i.e., concepts/entities and relations) instead of words to represent a query. The proposed method expands the question by adding the additional semantic entities got by executing the constructed SPARQL query of the why-question over the domain ontology. The major contribution of this research is in developing an ontology-based why-question analysis method by considering the expected answer types. Some experiments have been conducted to evaluate each phase of the proposed method. The results show good performance for all performance measures used (i.e., precision, recall, undergeneration, and overgeneration). Furthermore, comparison against two baseline methods, the keyword-based ones (i.e., the term-based and the phrase-based method), shows that the proposed method obtained better performance results in terms of MRR and P@10 values.

Class Association Rule Pada Metode Associative Classification Eka Karyawati; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 5, No 3 (2011): November
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.5207

Frequent patterns (itemsets) discovery is an important problem in associative classification rule mining. Differents approaches have been proposed such as the Apriori-like, Frequent Pattern (FP)-growth, and Transaction Data Location (Tid)-list Intersection algorithm. This paper focuses on surveying and comparing the state of the art associative classification techniques with regards to the rule generation phase of associative classification algorithms. This phase includes frequent itemsets discovery and rules mining/extracting methods to generate the set of class association rules (CARs). There are some techniques proposed to improve the rule generation method. A technique by utilizing the concepts of discriminative power of itemsets can reduce the size of frequent itemset. It can prune the useless frequent itemsets. The closed frequent itemset concept can be utilized to compress the rules to be compact rules. This technique may reduce the size of generated rules. Other technique is in determining the support threshold value of the itemset. Specifying not single but multiple support threshold values with regard to the class label frequencies can give more appropriate support threshold value. This technique may generate more accurate rules. Alternative technique to generate rule is utilizing the vertical layout to represent dataset. This method is very effective because it only needs one scan over dataset, compare with other techniques that need multiple scan over dataset. However, one problem with these approaches is that the initial set of tid-lists may be too large to fit into main memory. It requires more sophisticated techniques to compress the tid-lists.

Comparison of SVM and LIWC for Sentiment Analysis of SARA AAIN Eka Karyawati; Prasetyo Adi Utomo; I Gede Arta Wibawa
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 16, No 1 (2022): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.69617

SARA is a sensitive issue based on sentiments about self-identity regarding ancestry, religion, nationality or ethnicity. The impact of the issue of SARA is conflict between groups that leads to hatred and division. SARA issues are widely spread through social media, especially Twitter. To overcome the problem of SARA, it is necessary to develop an effective method to filter negative SARA. This study aims to analyze Indonesian-language tweets and determine whether the tweet contains positive or negative SARA or does not contain SARA (neutral). Machine learning (i.e., SVM) and lexicon-based method (i.e., LIWC) were compared based on 450 tweet data to determine the best approach for each sentiment (positive, negative, and neutral). The best evaluation results are shown in the negative SARA classification using SVM with λ = 3 and γ = 0.1, where Precision = 0.9, Recall = 0.6, and F1-Score = 0.72. The best results from the positive SARA classification were shown in the LIWC method, where Precision = 0.6, Recall = 0.8, and F1-Score = 0.69. The best evaluation results for neutral classification are shown in SVM with λ = 3 and γ = 0.1, with Precision = 0.52, Recall = 0.87, and F1-Score = 0.65.

O ONTOLOGY-BASED PARAGRAPH EXTRACTION AND CAUSALITY DETECTION-BASED SIMILARITY FOR ANSWERING WHY-QUESTION A A I N Eka Karyawati
Jurnal Ilmu Komputer Vol 11 No 1 (2018): Jurnal Ilmu Komputer
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Paragraph extraction is a main part of an automatic question answering system, especially in answering why-question. It is because the answer of a why-question usually contained in one paragraph instead of one or two sentences. There have been some researches on paragraph extraction approaches, but there are still few studies focusing on involving the domain ontology as a knowledge base. Most of the paragraph extraction studies used keyword-based method with small portion of semantic approaches. Thus, the question answering system faces a typical problem often occuring in keyword-based method that is word mismatches problem. The main contribution of this research is a paragraph scoring method that incorporates the TFIDF-based and causality-detection-based similarity. This research is a part of the ontology-based why-question answering method, where ontology is used as a knowledge base for each steps of the method including indexing, question analyzing, document retrieval, and paragraph extraction/selection. For measuring the method performance, the evaluations were conducted by comparing the proposed method over two baselines methods that did not use causality-detection-based similarity. The proposed method shown improvements over the baseline methods regarding MRR (95%, 0.82-0.42), P@1 (105%, 0.78-0.38), P@5(91%, 0.88-0.46), Precision (95%, 0.80-0.41), and Recall (66%, 0.88-0.53).

Ontology-Based Sentence Extraction for Answering Why-Question A. A. I. N. Eka Karyawati; Edi Winarko; Azhari Azhari; Agus Harjoko
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section

Most studies on why-question answering system usually used the keyword-based approaches. They rarely involved domain ontology in capturing the semantic of the document contents, especially in detecting the presence of the causal relations. Consequently, the word mismatch problem usually occurs and the system often retrieves not relevant answers. For solving this problem, we propose an answer extraction method by involving the semantic similarity measure, with selective causality detection. The selective causality detection is applied because not all sentences belonging to an answer contain causality. Moreover, the motivation of the use of semantic similarity measure in scoring function is to get more moderate results about the presence of the semantic annotations in a sentence, instead of 0/1. The semantic similarity measure employed is based on the shortest path and the maximum depth of the ontology graph. The evaluation is conducted by comparing the proposed method against the comparable ontology-based methods, i.e., the sentence extraction with Monge-Elkan with 0/1 internal similarity function. The proposed method shows the improvements in term of MRR (16%, 0.79-0.68), P@1 (15%, 0.76-0.66), P@5 (14%, 0.8-0.7), and Recall (19%, 0.86-0.72).

Planning Problems in the Improvement of Access to Emergency Obstetric Care in Eastern Indonesia Frederika Rambu Ngana; AAIN Eka Karyawati
Indonesian Journal of Global Health Research Vol 3 No 2 (2021): Indonesian Journal of Global Health Research
Publisher : GLOBAL HEALTH SCIENCE GROUP

Maternal death is the worst performing of the Millennium Development Goals (MDGs) and Indonesia did not achieve its MDG #5 target in 2015. Therefore, the Indonesian government needs to review its strategies to decrease maternal deaths. One cause of maternal death is a lack of infrastructure, which can delay reaching emergency obstetric care (called Poned). This qualitative study investigated problems with priority planning in the Kupang district in order to improve access to emergency obstetric care (EMOC). A number of observations were conducted in the musrenbang (the district planning process). Interviews were carried out to gain an insight into the planning process from village to district level. A model for travel time to EMOC was created to support this study. In this study, six problems were identified in the district planning (musrenbang) regarding improving access to EMOCs. Those were (1) no planning proposal about improving access to EMOC, (2) budget constraints, (3) decision on the priority planning not being based on the level of urgency, (4) undue political influence, (5) lack of evidence and (6) incorrect measure of accessibility to obstetric care. Hence, to improve access to EMOC, scenario modelling with combined cost-benefit analyses (CBA) as an evidence-based planning should be applied in the musrenbang. It will help the health planners in Eastern Indonesia to gain a deep understanding about the problems in district planning process for access improvement to EMOC. Scenario modelling with CBA could provide the evidence during musrenbang.

BALINESE AUTOMATIC TEXT SUMMARIZATION USING GENETIC ALGORITHM Cokorda Gde Abimanyu; Ngurah Agus Sanjaya ER; A. A. Istri Ngurah Eka Karyawati
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol 6 No 1 (2020): JITK Issue August 2020
Publisher : LPPM Nusa Mandiri

A summary contains the important idea of a text. However, summarizing a text requires one to read its entire content. In this study, text summarization is done automatically by applying a genetic algorithm to optimize the weight of five sentence features. The features include positive and negative keywords, the similarity between sentences and titles, the similarity between sentences, and cosine similarity. The collection of documents in this study are Balinese text stories. The summarization technique used is the extraction technique which eliminates unnecessary sentences, without changing the structure of the original sentence. The score of a sentence is generated by multiplying the feature value of each sentence by the weight of the feature. Summarization of the text is done by sorting the sentences based on the score. At the training stage, the best weight combination is chosen based on the average fitness value. Evaluation of the proposed method is carried out using 50 test data in the form of Balinese text stories. From the test results, it can be concluded that the fitness value of the feature weights is affected by the crossover and mutation rate of the genetic algorithm. Furthermore, accuracy is also influenced by the compression parameters used.

Penerapan Metode Fast Independent Component Analysis (FastICA) dalam Memisahkan Vokal dan Instrumen Seni Geguntangan Luh Arida Ayu Rahning Putri; I Gede Erwin Winata Pratama; I Dewa Made Bayu Atmaja Darmawan; A. A. I. N. Eka Karyawati; Ida Bagus Made Mahendra; I Ketut Gede Suhartana
Jurnal Buana Informatika Vol. 13 No. 1 (2022): Jurnal Buana Informatika, Volume 13, Nomor 1, April 2022
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v13i1.5693

Abstract. Application of Fast Independent Component Analysis (Fastica) Method in Separating Vocals and Instruments in Geguntangan. Gamelan Geguntangan is often used in religious ceremonies to accompany ceremonies and entertain the public. Along with its development, the Geguntangan gamelan is also used to accompany the Pesantian. Geguntangan recording plays instruments and vocal sounds, most of which have been mixed. The mixed sounds caused the learning process to be less effective for people who will study Pesantian. The students could not focus because of the distracting sound of the instrument. This study aims to separate the sound of instruments and vocals of Geguntangan using deflationary-based FastICA. The non-linear function used is Logcosh. This study also examines the effect of mixing matrix variables and alpha values on nonlinear functions on SDR, SIR, and SAR values. The results of the paired t-test carried out by these two values did not have a significant effect on SDR, SIR, and SAR. The difference in the average time of the mixing matrix testing process is 0.09 seconds and 0.42 seconds for testing the alpha value.Keywords: Pesantian, Geguntangan, BSS, FastICA, Deflationary Based. Abstrak. Gamelan Geguntangan sering dipakai dalam upacara keagamaan baik untuk mengiringi jalannya upacara dan hiburan masyarakat. Seiring perkembangannya, gamelan Geguntangan juga digunakan untuk mengiringi Pesantian. Pada rekaman Geguntangan terdapat suara instrumen dan vokal yang sebagian besarnya sudah tercampur. Hal ini menyebabkan proses belajar yang kurang efektif bagi orang yang akan belajar Pesantian. Para pemelajar tidak bisa fokus karena adanya suara instrumen yang mengganggu. Penelitian ini bertujuan untuk memisahkan suara instrumen dan vokal seni Geguntangan menggunakan deflationary based FastICA. Fungsi non linear yang digunakan adalah Logcosh. Penelitian ini juga menguji pengaruh variabel matriks pencampuran dan nilai alpha pada fungsi nonlinear terhadap nilai SDR, SIR dan SAR. Hasil uji-t berpasangan yang dilakukan kedua nilai ini tidak mempunyai pengaruh yang signifikan terhadap SDR, SIR dan SAR. Selisih rata-rata waktu proses pengujian matriks pencampuran ialah 0.09 detik dan 0.42 detik untuk pengujian nilai alpha.Kata Kunci: Pesantian, Geguntangan, BSS, FastICA, Deflationary Based.

DESAIN ANTARMUKA SISTEM TANYA JAWAB ANTAR ORGANISASI PERANGKAT DAERAH (OPD) WILAYAH DENPASAR Putu Widya Eka Safitri; Anak Agung Istri Ngurah Eka Karyawati; Ida Bagus Made Mahendra
Jurnal Pengabdian Informatika Vol. 1 No. 1 (2022): JUPITA Volume 1 Nomor 1, November 2022
Publisher : Jurusan Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana

Banyaknya pertanyaan yang masuk ke BPKAD Kota Denpasar menyebabkan kewalahan bagi pegawai untuk menjawabnya, dengan menggunakan aplikasi pengirim pesan online membuat Kepala Badan tidak bisa melihat dan susahnya merekap semua pertanyaan yang masuk, oleh karena itu di buatkanlah suatu website yang bisa menampung semua pertanyaan dari OPD dan pegawai BPKAD Kota Denpasar akan menjawab dengan baik, disamping itu juga pada website ini direncanakan akan ditampilkan pertanyaan-pertanyaan yang sering ditanyakan.

Co-Authors Agus Harjoko Agus Harjoko Agus Muliantara Ary Mahayasa, I Gusti Agung Gede Aryo Widano, Gusti Putu Azhari Azhari Azhari, Azhari Christirahma, Ratri Desy Cokorda Gde Abimanyu Darmayasa, I Nengah Oka Desak Ketut Puri Trisnantya Aji Devan Bramantya Edi Winarko Fransiska Christina Sio Da Silva Frederika Rambu Ngana Gotra, Anak Agung Ngurah Mahadana Apta Gst. Ayu Vida Mastrika Giri Hendrawan, Made Chandra I Dewa Made Bayu Atmaja Darmawan, I Dewa Made Bayu I Gede Arta Wibawa I Gede Arta Wibawa I Gede Erwin Winata Pratama I Gede Martayasa I Gede Santi Astawa I Gusti Agung Gede Arya Kadyanan I Gusti Ngurah Anom Cahyadi Putra I Ketut Gede Suhartana I Komang Sutrisna Eka Wijaya I Made Arya Dwisada I Made Widiartha I Putu Dana Putra I Putu Gede Hendra Suputra I WAYAN SANTIYASA I Wayan Supriana Ida Bagus Gede Dwidasmara Ida Bagus Made Mahendra Karsten, Julian Seph Komang Dhiyo Yonatha Wijaya Luh Arida Ayu Rahning Putri Martayasa, I Gede Muhammad Akbar Hamid Ngurah Agus Sanjaya ER Ni Made Putri Wahyuni Paulus Mbaba Prasetyo Adi Utomo Prashanti, Ni Putu Vidya Vira Putra, I Gede Ari Putra, I Gusti Ngurah Agung Widiaksa Putu Widya Eka Safitri Raharja, Made Agung Rizky, Muhammad Firyanul Sidharta, Matthew Novan Sutrisna, Benedict Emanuel Taksa Wibawa, I Made Sudarsana Utomo, Prasetyo Adi Wijana, Sawendo Eko Winarko, Edi Yasa, I Wayan Restama Yonatha Wijaya, Komang Dhiyo

Title

Found 41 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 41 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 41 Documents
Search