Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jurnal Linguistik Komputasional JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Mewati Ayub
Unknown Affiliation
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Pemanfaatan Epistemic Network Analysis sebagai Pendukung Analisis Sentimen dalam Collaborative Learning Roy Parsaoran; Jonathan Bernad; Tifani Astadini; Hapnes Toba; Maresha Caroline Wijanto; Mewati Ayub
Jurnal Linguistik Komputasional Vol 3 No 2 (2020): Vol. 3, No. 2
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v3i2.36

Abstract

A lot of blended learning methods have been applied to modern learning system. One of the most used learning methods is collaborative learning which combines and extends group discussion. The recorded data during a collaborative learning session could be useful to enhanced the interaction among the class members, including the lecturer. Using sentiment analysis, the discussion can be categorized whether the discussion goes well or not, it can also be seen which group members are most active and have a positive impact on the work assigned to the group. In this preliminary research, sentiment analysis approach will be combined with Epistemic Network Analysis (ENA) so that it can see a graphical depiction of each member's contribution in a group discussion. Our experimental results show that ENA displays better insights of the students activities than only using the sentiment analysis.
Integrasi Micro-Apps Individual menjadi One-Stop Services Maranatha Application Suite Joseph Sanjaya; Erick Renata; Vincent Elbert Budiman; Francis Anderson; Mewati Ayub
Jurnal Teknik Informatika dan Sistem Informasi Vol 5 No 3 (2019): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v5i3.1993

Abstract

Use of information systems at the university, which is the standard management of the university, is required to support all the activities of the academic community. Aside of determining the smooth operations, information technology also maintain the competitiveness of the competitors by constantly updating the information technology so as not to miss. Trends in the development of technology will make a strong connectivity between universities and stakeholders, governments, and partners. Some of the problems that occur when information systems are not yet fully integrated system, separate user management, application is implemented on different platforms and dashboards for management, not integrated. It is important for the university to provide Single and Integrated Application applications that are integrated into each of their services. Single and Integrated Applications are available at the web application / desktop / mobile multi-platform, for which data are available in real time, and there is no duplication of data occurs.
Augmentasi Data Pengenalan Citra Mobil Menggunakan Pendekatan Random Crop, Rotate, dan Mixup Joseph Sanjaya; Mewati Ayub
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 2 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i2.2688

Abstract

Deep convolutional neural networks (CNNs) have achieved remarkable results in two-dimensional (2D) image detection tasks. However, their high expression ability risks overfitting. Consequently, data augmentation techniques have been proposed to prevent overfitting while enriching datasets. In this paper, a Deep Learning system for accurate car model detection is proposed using the ResNet-152 network with a fully convolutional architecture. It is demonstrated that significant generalization gains in the learning process are attained by randomly generating augmented training data using several geometric transformations and pixel-wise changes, such as image cropping and image rotation. We evaluated data augmentation techniques by comparison with competitive data augmentation techniques such as mixup. Data augmented ResNet models achieve better results for accuracy metrics than baseline ResNet models with accuracy 82.6714% on Stanford Cars Dataset.
BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper Feliks Victor Parningotan Samosir; Hapnes Toba; Mewati Ayub
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 1 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i1.4474

Abstract

This study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level.
Co-Authors Erick Renata Feliks Victor Parningotan Samosir Francis Anderson Hapnes Toba Jonathan Bernad Joseph Sanjaya Maresha Caroline Wijanto Roy Parsaoran Tifani Astadini Vincent Elbert Budiman