Claim Missing Document
Check
Articles

Found 6 Documents
Search

Topic Discovery of Online Course Reviews Using LDA with Leveraging Reviews Helpfulness Fetty Fitriyanti Lubis; Yusep Rosmansyah; Suhono H. Supangkat
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 1: February 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1648.325 KB) | DOI: 10.11591/ijece.v9i1.pp426-438

Abstract

Despite the popularity of the Massive Open Online Courses, small-scale research has been done to understand the factors that influence the teaching-learning process through the massive online platform. Using topic modeling approach, our results show terms with prior knowledge to understand e.g.: Chuck as the instructor name. So, we proposed the topic modeling approach on helpful subjective reviews. The results show five influential factors: “learn easy excellent class program”, “python learn class easy lot”, “Program learn easy python time game”, and “learn class python time game”. Also, research results showed that the proposed method improved the perplexity score on the LDA model.
Real-time passenger social distance monitoring with video analytics using deep learning in railway station Iqbal Ahmad Dahlan; Muhammad Bryan Gutomo Putra; Suhono Harso Supangkat; Fadhil Hidayat; Fetty Fitriyanti Lubis; Faqih Hamami
Indonesian Journal of Electrical Engineering and Computer Science Vol 26, No 2: May 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v26.i2.pp773-784

Abstract

Recently, at the end of December, the world faced a severe problem which is a pandemic that is caused by coronavirus disease. It also must be considered by the railway station's authorities that it must have the capability of reducing the covid transmission risk in the pandemic condition. Like a railway station, public transport plays a vital role in managing the COVID-19 spread because it is a center of public mass transportation that can be associated with the acquisition of infectious diseases. This paper implements social distance monitoring with a YOLOv4 object detection model for crowd monitoring using standard CCTV cameras to track visitors using the DeepSORT algorithm. This paper used CCTV surveillance with the actual implementation in Bandung Railway Station with the accuracy at 96.5 % result on people tracking with tested in real-time processing by using minicomputer Intel(R) Xeon(R) CPU E3-1231 v3 3.40GHz RAM 6 GB around at 18 FPS.
Evaluasi dan Perbaikan Desain Interaksi Edunex dengan Pendekatan User-Centered Design Alya Mizani; Fetty Fitriyanti Lubis
Jurnal Sistem Cerdas Vol. 5 No. 2 (2022)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v5i2.205

Abstract

Edunex is the Learning Management System used in Institut Teknologi Bandung to support online and hybrid learning and teaching activities. However, there are still some improvements that could be implemented in order to further meet the users’ needs. To do so, the user-centered design approach is used. The development prioritizes implementing fixes in Homepage, My Courses, Exams, and Presences because those pages have high values towards users and high feasibility to fix. Besides that, based on the questionnaire that had been shared, there are needs for new features, such as Reminder and Tutorial that need to be implemented. The outcome of this project is a high-fidelity prototype of a website for desktop screens that fulfills usability and user experience goals effective to use, efficient to use, easy to learn, and helpful. The usability and user experience goals were measured using Completion Rate for effective to use, Single Ease Question (SEQ) for easy to learn, System Usability Scale (SUS) for efficient to use, and Intrinsic Motivation Inventory (IMI) with value/usefulness subscale for helpful. After conducting the evaluation by usability testing, Completion Rate value of 100%, SEQ of 6,9 out of 7, SUS value of 90 out of 100, and IMI value/usefulness value of 6,7 per 7 are achieved. Based on those values, it could be concluded that the prototype designed has fulfilled the usability and user experience goals.
Interaction Design of ITB Library Application Using User-Centered Design Elisabeth Levana Thedjakusuma; Fetty Fitriyanti Lubis
JURNAL TEKNIK INFORMATIKA Vol 15, No 2 (2022): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v15i2.27956

Abstract

The Technical Implementation Unit is a part of a university or institute that supports the three pillars of higher education, one of which is the library. Library has a large collection of resources that can be accessed through a library catalog. ITB Library is a mobile application that allows users to search catalogs, but it currently lacks optimal appearance and user experience. The aim of this final project is to improve the ITB Library by implementing a user-centered design approach, which focuses on understanding and addressing user needs. The end goal is to create a high-fidelity prototype that meets the usability goals of effective to use, have good utility, easy to learn, and the user experience goal of being helpful. To evaluate the design, usability testing was conducted on the prototype. Testing was evaluated using several metrics, including task completion rate (100%), System Usability Scale (SUS) (93/100), Single Ease Question (SEQ) (6.7/7), and Intrinsic Motivation Inventory (IMI) (6.7/7 for the value/usefulness subscale) during the third iteration. Based on the results of the testing, the interaction design of the ITB Library meets the usability and user experience goals that were set out to be achieved.
Pengukuran User Experience Platform Otomasi Proses berbasis Low Code Menggunakan UEQ Falih, Noor; Supangkat, Suhono Harso; Lubis, Fetty Fitriyanti; Prabowo, Okyza Maherdy
Jurnal Sistem Cerdas Vol. 6 No. 2 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i2.320

Abstract

This study analyzes the user experience of a Low Code-based Process Automation Platform to enhance efficiency, productivity, and accuracy in business processes. In this study, an analysis of user experience was carried out using a modified long version of the User Experience Questionnaire (UEQ), consisting of six scales: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty. Based on the evaluation of the 26 items from the UEQ, the dependability and novelty scales scored the lowest compared to the other scales. Therefore, it is necessary to improve the aspects related to these two scales in order to enhance the platform's role in improving the holistic user experience of the platform.
Mixed Data Type Analysis: A Systematic Literature Review Pratama, Hasta; Fitriyanti Lubis, Fetty; Sembiring, Jaka
IDEALIS : InDonEsiA journaL Information System Vol. 7 No. 2 (2024): Jurnal IDEALIS Juli 2024
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/idealis.v7i2.3168

Abstract

This research aims to determine the direction of research in the analysis of mixed data types. The world is currently filled with increasingly diverse data, especially in terms of data types, which are not only numerical or categorical but can be both (mixed). In Data Mining, the analysis of mixed data poses significant challenges because numerical and categorical data exhibit different properties. The research methodology employed in this study utilizes the PICOC framework (Population, Intervention, Comparison, Outcome, Context) to collect and review relevant literature. The primary findings from this comprehensive literature survey reveal that a majority of the research related to mixed data is published in reputable journals Q1, indicating sustained interest in the topic of mixed data analysis. Clustering models emerge as the most frequently used models in the field of mixed data analysis. However, it's noteworthy that accuracy metrics remain the predominant evaluation benchmark, often leading to comparisons with the ideal clustered data. The management of mixed data typically involves normalization techniques, specifically normalizing the scale to amalgamate the two types of data. The conclusion drawn from the results of the literature review is the necessity to develop unlabeled mixed data, encompassing both the model and metrics required to assess the outcomes. Additionally, this research emphasizes the significance of a comprehensive development model, ranging from feature selection to evaluation models. Therefore, the analysis of mixed data types remains a field with ample opportunities for exploration and potential innovation. This potential is particularly evident in the areas of dynamic model development and the ability to handle structured and extensive data.