Claim Missing Document
Check
Articles

Found 32 Documents
Search

Prototyping a Chatbot for Student Supervision in a Pre-Registration Process Krisnawati, Lucia Dwi; Butar-Butar, Bill Edward; Virginia, Gloria
CommIT (Communication and Information Technology) Journal Vol 12, No 2 (2018): CommIT Vol. 12 No. 2 Tahun 2018
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v12i2.4813

Abstract

Developing a chatbot becomes a challenging task when it is built from scratch and independent of any Software as a Service (SaaS). Inspired by the idea of freeing lecturers from the burden of answering the same questions repetitively during the pre-registration process, this research has succeeded in building a textbased chatbot system. Further, this research has proved that the combination of keyword spotting technique for the Language Understanding component, Finite-State Transducer (FST) for the Dialogue Management, rulebased keyword matching for language generation, and the system-in-the-loop paradigm for system validation can produce an efficient chatbot. The chatbot efficiency is high enough as its score on Concept Efficiency (CE) reaches 0.946. It shows that users do not need to repeat their utterances several times to be understood. The chatbot performance on recognizing new concepts introduced by users is also more than satisfactory which is presented by its Query Density (QD) score of 0.80.
HOW THE INFORMATION IS PROCESSED IS MORE IMPORTANT Virginia, Gloria
Proceedings of KNASTIK 2009
Publisher : Duta Wacana Christian University

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

Abstract

Informasi adalah hal yang sangat penting dalam pengambilan keputusan. Meskipun demikian, ternyata bagaimanainformasi itu diolah jauh lebih penting dari pada sekedar memiliki informasi. Sebuah studi kasus diberikan dan data awalberupa probabilitas keputusan dievaluasi menggunakan pendekatan kalibrasi dan kovarian. Hasil dari perhitungan dananalisa grafik keduanya kemudian dibandingkan dengan hasil perhitungan data terakhir menggunakan sebuah sistem pakarpengambil keputusan, Expert Choice.
Developing an Automatic Ontology Constructor for Bahasa Indonesia Using Cognitive Approach: A Proposal Virginia, Gloria; Nguyen, Hung Son
Proceedings of KNASTIK 2010
Publisher : Duta Wacana Christian University

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

Abstract

There are great challenges in computer linguistic and information retrieval fields which process Bahasa Indonesia.  Taking advantage from implementation of Linear Model life cycle, an automatic ontology constructor (OC) is going to be generated.  The natural language in emails together with the exhaustive cognitive approach argues to be essential in the process of OC generation that one may achieve deep linguistic analysis.  An ontology-based information retrieval system for Indonesian choral community is going to be developed using 3,000 emails of Indonesian Choral Lovers (ICL) mailing list as a tool of evaluation.  Performance measure of information retrieval (recall and precision) and qualitative measure of ontology (consistency, completeness, and conciseness) are going to be used to find out the OC effectiveness through examining the automatic-thesaurus effectiveness. The associative thesaurus generated manually and automatically will also enrich the IndonesianWordNet being struggled.
IMPLEMENTASI SISTEM PAKAR PADA PEMILIHAN VARIETAS PADI Virginia, Gloria; Purwadi, Joko; Kurniasih, Theresa Mariana
Proceedings of KNASTIK 2009
Publisher : Duta Wacana Christian University

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

Abstract

Sistem pakar untuk pemilihan varietas padi yang dibangun berhasil memberikan solusi berupa alternatif jenisvarietas padi sesuai dengan fakta yang diinputkan user pada sesi konsultasi. Hasil evaluasi sistem mengindikasikan bahwasistem yang dibangun efektif. Alat ukur yang digunakan adalah penilaian terhadap konsistensi basis pengetahuan danakurasi keluaran sistem. Hal ini dicapai dengan menerapkan metode forward chaining sebagai mesin inferensi sistem.Selain itu, basis data dan basis aturan dibangun sebagai basis pengetahuan sistem, dimana 422 aturan yang terdapat dalambasis aturan dibagi menjadi tujuh prosedur.
Evaluasi Perancangan Antarmuka untuk Membangun User Experience pada Layanan SInTA Universitas Kristen Duta Wacana Yogyakarta Neshia Aditya Santoso; Gloria Virginia; Budi Susanto
Jurnal Transformatika Vol 15, No 1 (2017): July 2017
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v15i1.458

Abstract

SInTA is a search engine developed by Duta Wacana Christian University (DWCU) to locate references of final task reports or thesis ever made by DWCU students.The existence and function of SInTA is not widely known by students. In addition, SInTA still require many improvements on feature and UI design to simplify the interaction between users and interface.This research use individual expert review approach to evaluate interface, whereas data divided into 6 User Experience measurement scales. The result of evaluation is User Experience recommendation which used to build prototype.Considering User Experience shall be created a prototype which should attract users, meet the needs of users, and satisfy the users. In this research, prototype has higher User Experience mean values rather than SInTA old interface, thereby the research be assessed as being successful.
PENERAPAN SENTIMENT ANALYSIS PADA HASIL EVALUASI DOSEN DENGAN METODE SUPPORT VECTOR MACHINE Valonia Inge Santoso; Gloria Virginia; Yuan Lukito
Jurnal Transformatika Vol 14, No 2 (2017): January 2017
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v14i2.439

Abstract

The quality of lectures can be determined by some feedbacks from students. From the feedbacks, we can give appreciations for those lectures who get good feedback from students, and evaluations for those who get bad feedback. The problem is classifying large size of feedbacks manually isn’t effective and took a lot of time. Therefore, we need a system that can classify feedbacks automatically. These feedbacks will be classified into positive, negative, and neutral, usually called as sentiment analysis. Sentiment analysis implementation can be done by several methods, one of them that has a good accuracy is Support Vector Machine (SVM). SVM performance in this research is measured with the level of accuracy. The number of accuracy indicate the success level of system. The conclusion of this research is factors that affects the accuracy. The factors are the range of each classes and number of unique words in the training document.
Prototyping a Chatbot for Student Supervision in a Pre-Registration Process Lucia Dwi Krisnawati; Bill Edward Butar-Butar; Gloria Virginia
CommIT (Communication and Information Technology) Journal Vol. 12 No. 2 (2018): CommIT Journal
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v12i2.4813

Abstract

Developing a chatbot becomes a challenging task when it is built from scratch and independent of any Software as a Service (SaaS). Inspired by the idea of freeing lecturers from the burden of answering the same questions repetitively during the pre-registration process, this research has succeeded in building a textbased chatbot system. Further, this research has proved that the combination of keyword spotting technique for the Language Understanding component, Finite-State Transducer (FST) for the Dialogue Management, rulebased keyword matching for language generation, and the system-in-the-loop paradigm for system validation can produce an efficient chatbot. The chatbot efficiency is high enough as its score on Concept Efficiency (CE) reaches 0.946. It shows that users do not need to repeat their utterances several times to be understood. The chatbot performance on recognizing new concepts introduced by users is also more than satisfactory which is presented by its Query Density (QD) score of 0.80.
Pemodelan Representasi Pengetahuan Berbasis OWL untuk Objek Arsitektur Candi di Indonesia Thalia Maria Camilo; Gloria Virginia; Budi Susanto; Umi Proboyekti
Jurnal Terapan Teknologi Informasi Vol 4 No 1 (2020): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2020.41.190

Abstract

Candi merupakan salah satu contoh warisan budaya. Jumlah candi Indonesia yang banyak membuat informasi yang tersebar di internet juga sangatlah banyak. Namun informasi tersebut bukanlah suatu kesatuan informasi. Oleh karena itu, dibutuhkan sebuah sistem yang dapat menyimpan informasi-informasi tersebut. Untuk membantu pengolahan data candi, maka dibuat sistem semantic web. Sistem ini akan membantu memodelkan data candi. Tujuan dari sistem ini adalah untuk memodelkan data dan menampilkan informasi yang akurat tentang candi yang ada di Indonesia. Sistem dibangun dengan menggunakan metode On-To-Knowledge. Sistem semantic web yang dibangun berbasis OWL dan database yang digunakan adalah SPARQL. Sistem semantic web mampu menghubungkan data kebudayaan candi dengan kebudayaan yang lain. Selain itu, sistem juga dapat menampilkan informasi berdasarkan deskripsi dan gambar dari candi.
Pembangunan Model Pengetahuan Kerajinan Tradisional Indonesia dengan Pendekatan On-To-Knowledge Ni Luh Muryanti; Gloria Virginia; Budi Susanto; Umi Proboyekti
Jurnal Terapan Teknologi Informasi Vol 4 No 2 (2020): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2020.42.196

Abstract

Kerajinan tradisional adalah karya yang dibuat dengan peralatan sederhana dan berbahan alami. Kerajinan tradisional terdiri dari anyaman, batik, gerabah, kain tenun, kerajinan kayu dan kerajinan perak. Jenis kerajinan tradisional yang ada berbanding terbalik dengan informasi yang tersedia mengenai kerajinan tradisional Indonesia. Oleh karena itu sangat penting untuk memperkenalkan dan mendokumentasikan kerajinan tradisional pada masyarakat Indonesia. Salah satu cara untuk mendokumentasikan kerajinan tradisional Indonesia yaitu menggunakan semantic web. Semantic web mampu mengelola sekumpulan data dan model yang dinamis sehingga dapat memberikan keterbukaan akses infromasi. Pengetahuan tentang kerajinan tradisional Indonesia direpresentasikan ke bentuk OWL. Pada penelitian ini, penulis menggunakan metodologi On-To-Knowledge untuk membangun ontologi kerajinan tradisional Indonesia. Dalam metodologi On-To-Knowledge terdapat 5 tahapan, namun penulis hanya menggunakan 4 tahapan yaitu tahap feasibility study, kick off, refinement, dan evaluation. Tahap feasibility study bertujuan untuk melakukan studi kelayakan terhadap sistem yang akan dibangun dengan mengidentifikasi masalah, pengguna sistem dan use case. Tahap kick-off bertujuan untuk mendefinisikan kebutuhan ontologi kerajinan tradisional Indonesia dan sumber pengetahuan yang digunakan. Tahap refinement bertujuan untuk melakukan pemodelan ontologi kerajinan tradisional Indonesia yang dilakukan dengan beberapa tahap yaitu ekstraksi pengetahuan secara manual, membuat description logic dan pembuatan T-Box. Evaluasi adalah tahap pengujian menggunakan reasoner HermiT pada aplikasi protégé, DL Query dan completeness check.
Smart Water Dispenser Terintegrasi untuk Monitoring Konsumsi Air Minum Harian Deni Ariyanto Abadi; Laurentius Kuncoro Probo Saputra; Gloria Virginia
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 2 (2021): April 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i2.2950

Abstract

Lack of water can cause serious health problems.  In reality, some people do not know the amount of water they must drink daily.  It's hard to find out the daily water intake needs because it is affected by a lot of things and it will be better to involve a nutritionist or health expert to get the best amount, which may require extra cost. To overcome these problems, it is necessary to have a system that is incorporated in an integrated system with the ability to calculate the ideal level of water needs for the body according to factors that affect the level of water needs and able to remind users to keep their daily needs. IoT-based smart water dispensers that can be integrated with android applications and cloud servers into a single system can be used to help solve these problems. The system has a knowledge base obtained from professionals to determine user water consumption. The system calculates the water consumption using the GPPAQ questioner and Estimated Energy Requirement (EER) formula. The base knowledge is implemented on Android applications, and this application can track the amount of water that has been consumed by the user. The test results show that the system can calculate the amount of water demand based on some factors such as the level of physical activity, age, and body weight. The water dispenser system has an accuracy of recording the amount of air released by 92.6%, so there is a difference in the calculation in the Android application to the amount of air that the user takes from the water dispenser