Garuda - Garba Rujukan Digital

Factors Influencing the Difficulty Level of the Subject: Machine Learning Technique Approaches Suparwito, Hari
International Journal of Applied Sciences and Smart Technologies Volume 01, Issue 01, June 2019
Publisher : Universitas Sanata Dharma

The difficulty level of a subject is needed either to understand the student acceptance of the subject and the highest level of student achievement in it. Some factors are considered, what kind of instructions, the readiness of the instructor and students in teaching and learning, evaluation and monitoring systems, and student expectations. Many factors are involved, and educators should know this. It is better if they can discern which are the prime factors and which the secondary factors. The purpose of the study is to find out the determinant factors in establishing the difficulty level of the subject from the students?, teachers? and infrastructure point of view using three machine learning techniques. The MSE and the variable importance measurement were used to predict between some factors such as Attendance, Instructors, and other factors as independent variables and the difficulty level of the subject as a dependent variable. The study result showed that Gradient Boosting Machine obtained the MSE value result 1.14 and 1.30 for training and validation dataset. The model generated five variable importance as an independent factor, i.e. Attendance, Instructor, The course can give a new perspective to students, The quizzes, assignments, projects and exams contributed to helping the learning, and The Instructor was committed to the course and was understandable. The Gradient Boosting Machine is superior to other methods with the lowest MSE and MAE values results. Two methods, Gradient Boosting Machine and Deep Learning, have produced the same five main factors that influenced the difficulty of the subject. It means these factors are significant and should get intention by the stakeholders

Student Perceptions Analysis of Online Learning: A Machine Learning Approach Suparwito, Hari; Polina, Agnes Maria; Budiraharjo, Markus
Indonesian Journal of Information Systems Vol 4, No 1 (2021): August 2021
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v4i1.4594

The covid-19 pandemic is currently occurring affects almost all aspects of life, including education. School From Home (SFH) is one of the ways to prevent the spread of Covid-19. The face-to-face learning method in class turns into online learning using information technology facilities. Even though there are many barriers to implementing classes online, online learning provides a new perspective for students' learning process. One of the factors for the online learning process's success is the interaction between the two main actors in the learning process, i.e., lecturers and students. The study's purpose was to analyze students' perceptions of the online learning process. The research data were obtained from a student questionnaire, which included five main criteria in the learning process: 1) self-management aspects, 2) personal efforts, 3) technology utilization, 4) perceptions of self-roles, and 5) perceptions of the role of the lecturer. Students provide an assessment through a questionnaire about the online learning methods they experience during the Covid-19 pandemic. The random forest algorithm was applied to examine data. The study results were focused on three main criteria (variable importance) that affect students' perceptions of the online learning process. The results described that the students' satisfaction in online learning is influenced by 1) The relationship between students and lecturers. 2) The learning materials need to be changed and adapted to the online learning method; 3) The use of technology to access online learning. The study contributes to improving the online learning method for the student.

PELATIHAN MEDIA BELAJAR BERBASIS ONLINE DI ERA PANDEMI Kartono Pinaryanto; Anastasia Rita Widiarti; Haris Sriwindono; Ridowati Gunawan; Hari Suparwito; Sri Hartati Wijono; Rosalia Arum Kumalasanti; Wiwien Widyastuti
ABDIMAS ALTRUIS: Jurnal Pengabdian Kepada Masyarakat Vol 5, No 1 (2022): April 2022
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/aa.v5i1.3916

The education sector is one of the areas that has been most affected by the COVID-19 pandemic. Schools, which normally hold offline meetings, must now take place online. With this pandemic, the teaching process must be "forced" to be done online. The task model which is usually given in physical mode (questions on paper, done and collected) is no longer relevant to be done because of the limitations of physical meetings. On the other hand, students need an explanation from the teacher directly because they are used to the context of offline learning. Judging from the current level of smartphone ownership, whether owned by students themselves or their parents, we can use smartphone devices to help the teaching and learning process. But of course it requires technological literacy from the student side and the teacher side so that this teaching and learning process can be carried out properly. As a form of concern for the academic community of the Informatics Study Program at Sanata Dharma University to the problems that exist in the environment around the campus, we held training activities for making teaching media for State Elementary School of Timbulharjo teachers who ultimately played an important role in improving teachers' technological literacy in carrying out online learning. This activity had been carried out well offline in 2 stages, namely stage 1 on 9 and 10 June 2021 and stage 2 on 22 and 23 November 2021.

Student Perceptions Analysis of Online Learning: A Machine Learning Approach Hari Suparwito; Agnes Maria Polina; Markus Budiraharjo
Indonesian Journal of Information Systems Vol. 4 No. 1 (2021): August 2021
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v4i1.4594

The covid-19 pandemic is currently occurring affects almost all aspects of life, including education. School From Home (SFH) is one of the ways to prevent the spread of Covid-19. The face-to-face learning method in class turns into online learning using information technology facilities. Even though there are many barriers to implementing classes online, online learning provides a new perspective for students' learning process. One of the factors for the online learning process's success is the interaction between the two main actors in the learning process, i.e., lecturers and students. The study's purpose was to analyze students' perceptions of the online learning process. The research data were obtained from a student questionnaire, which included five main criteria in the learning process: 1) self-management aspects, 2) personal efforts, 3) technology utilization, 4) perceptions of self-roles, and 5) perceptions of the role of the lecturer. Students provide an assessment through a questionnaire about the online learning methods they experience during the Covid-19 pandemic. The random forest algorithm was applied to examine data. The study results were focused on three main criteria (variable importance) that affect students' perceptions of the online learning process. The results described that the students' satisfaction in online learning is influenced by 1) The relationship between students and lecturers. 2) The learning materials need to be changed and adapted to the online learning method; 3) The use of technology to access online learning. The study contributes to improving the online learning method for the student.

Factors Influencing the Difficulty Level of the Subject: Machine Learning Technique Approaches Hari Suparwito
International Journal of Applied Sciences and Smart Technologies Volume 01, Issue 01, June 2019
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v1i1.1869

The difficulty level of a subject is needed either to understand the student acceptance of the subject and the highest level of student achievement in it. Some factors are considered, what kind of instructions, the readiness of the instructor and students in teaching and learning, evaluation and monitoring systems, and student expectations. Many factors are involved, and educators should know this. It is better if they can discern which are the prime factors and which the secondary factors. The purpose of the study is to find out the determinant factors in establishing the difficulty level of the subject from the students, teachers and infrastructure point of view using three machine learning techniques. The MSE and the variable importance measurement were used to predict between some factors such as Attendance, Instructors, and other factors as independent variables and the difficulty level of the subject as a dependent variable. The study result showed that Gradient Boosting Machine obtained the MSE value result 1.14 and 1.30 for training and validation dataset. The model generated five variable importance as an independent factor, i.e. Attendance, Instructor, The course can give a new perspective to students, The quizzes, assignments, projects and exams contributed to helping the learning, and The Instructor was committed to the course and was understandable. The Gradient Boosting Machine is superior to other methods with the lowest MSE and MAE values results. Two methods, Gradient Boosting Machine and Deep Learning, have produced the same five main factors that influenced the difficulty of the subject. It means these factors are significant and should get intention by the stakeholders

Information Technology and Learning Methodology Amid the COVID-19 Pandemic Hari Suparwito
International Journal of Applied Sciences and Smart Technologies Volume 02, Issue 02, December 2020
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v2i2.2886

The impact of the COVID-19 pandemic on the education sector caused schools and universities are closed. Then, teaching and learning are delivered by an online method through information and communication technology. Some issues have emerged, especially on delivering materials and the minimum requirements of online learning. The study aims to review learning methodologies and the role of information and communication technology for future learning. Heutagogy and Computational Thinking have been selected as the learning methodology for approaching digital native generation. It is no doubt that the significant role in undertaking online education is information and communication technology. Therefore, we suggested some tools to enhance learning systems, such as gamification learning, virtual labs, and social media. We also discussed new learning media using information and communication technology in education. The study's contribution is to describe technology's role in the future learning system to be used by decision-makers in implementing e-learning better.

Analisis Unjuk Kerja K-Nearest Neighbour untuk Klasifikasi Citra Aksara Bali Tulis Tangan Anastasia Rita Widiarti; Hari Suparwito
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 12, No 2 (2022): Oktober
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.67796

Keterbatasan tenaga ahli filolog, dan rentannya material daun lontar yang menjadi aset warisan leluhur jaman dulu, menjadi pemicu untuk dilakukannya otomatisasi alih aksara atau transliterasi citra aksara Bali di daun lontar berbantuan komputer. Algoritma klasifikasi k-nearest neighbour atau kNN, bisa menjadi alat yang dapat digunakan untuk transliterasi tersebut. Prinsip kerja kNN yang sederhana, yaitu dengan mencocokan kemiripan data baru ke data-data uji terdekat, mampu digunakan untuk tranlisterasi citra aksara Bali.Pendekatan yang dilakukan pada penelitian ini, selain menitik beratkan pada tahap klasifikasi, juga memperhitungkan dua tahap proses sebelum dilakukan klasifikasi. Perlu proses penyiapan citra yang terdiri dari binerisasi, pemotongan bagian kosong, penyamaan ukuran, dan penipisan, dan proses ektraksi ciri yang menggunakan algoritma intensity of pixels. Dengan mempergunakan 18 kelas yang mewakili 18 aksara Bali, dan jumlah data 1001 citra, diperoleh rerata prosentase akurasi 84.746%. Akurasi tersebut diperoleh dengan menerapkan prinsip uji silang 3-fold. Dari penelitian ini pula dapat disimpulkan, meskipun data citra yang digunakan adalah hasil tulisan tangan, dengan mempergunakan data latih yang cukup besar, kNN mampu digunakan untuk klasifikasi. Hal ini menunjukkan bahwa kNN dapat diterapkan sebagai metode klasifikasi citra aksara Bali di daun lontar, sehingga dapat dikembangkan lebih lanjut sebagai mesin utama untuk transliterasi citra daun lontar.

CLASTERIZATION OF LECTURER'S PROFILE IN ONLINE LEARNING DURING THE COVID-19 PANDEMIC Polina, Agnes Maria; Aprinastuti, Christiyanti; Suparwito, Hari
IJIET (International Journal of Indonesian Education and Teaching) Vol 7, No 2 (2023): July 2023
Publisher : Sanata Dharma University Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijiet.v7i2.6495

The learning process changed from classroom to online learning during the COVID-19 pandemic. One of the things that must be done is to analyze the readiness of lecturers in facing online learning. The purpose of this study is to cluster the profiles of lecturers dealing with online learning. The clustering method uses a Machine Learning approach with the K-means algorithm. Data were taken from 274 lecturers who returned questionnaires during April–June 2022. The questionnaire consisted of 27 questions on a Likert scale (1–4). The Boruta technique is used to determine the five most significant variables (Variable Importance) in the clustering. The results of the clustering show that the lecturers are divided into 2 large groups with the following criteria: focus on learning methods, learning materials, student independence, exploration of new knowledge, and online learning evaluation tools.

Real-Time Vehicle Detection and Air Pollution Estimation Using YOLOv9 Suparwito, Hari; Prakoso, Bernardus Hersa Galih; Kumalasanti, Rosalia Arum; Polina, Agnes Maria
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 1 (2025): JANUARY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i1.2329

Pollution of air, particularly in cities, is becoming an issue to be taken seriously owing to the health and environmental risks associated with it, and the major contributor to air pollution is car emissions. The objective of the study is to identify and classify vehicles such as motorbikes, cars, buses, trucks in order to monitor live traffic and potentially determine the extent to which the pollution level elevates, utilizing the YOLOv9 model. Traffic CCTV camera footage was gathered under a wide range of circumstances including different lighting and varying traffic intensity. Folders were particularly structured and images annotated, in the manner, which served the purpose of meeting the requirements of the YOLO structure. Once it was trained with a labeled dataset, the vehicle identification by YOLOv9 model was found to be quite satisfactory. Overall vehicle identification accuracy was calculated to be mAP50:95 of 0.826. In contrast, it had a harder time with smaller items like motorcycles, with a mAP50:95 of 0.682. Findings indicate that larger items were detected more than smaller items. Camera angles and the small size of the objects often make small objects appear to blend in to the background. This research indicates that AI can be of help when dealing with the urban structure. It offers a way of measuring traffic volume to predict the amount of CO emissions that can be avoided or controlled. The rest are keen in enhancing the effectiveness of recognizing small objects within the system and deploying it in multiple settings.

Image Detection Analysis for Javanese Character Using YOLOv9 Models Suparwito, Hari
International Journal of Applied Sciences and Smart Technologies Volume 06, Issue 1, June 2024
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v6i1.8779

The Javanese script needs to be digitized to improve access and usage, especially among younger generations. Digitizing Javanese characters is crucial for preserving Javanese culture and traditions in the long term. This study aims to detect and recognize Javanese characters using the YOLOv9 algorithm, known for its ability to detect various object types, including Latin and non-Latin scripts. The dataset used consists of 85 images of complete Javanese script arranged in a 4x5 grid of different characters. The dataset was divided into a training dataset (75 images) and a validation dataset (10 images). All data pre-processing was done using Roboflow tools. Two experiments were conducted, varying the weights of the YOLOv9 algorithm model: YOLOv9-c and YOLOv9-c-converted. The research results showed that the YOLOv9-c model outperformed YOLOv9-c-converted, achieving a confidence level of over 80% and an mAP value of 0.95 in recognizing Javanese script images. In other words, the YOLOv9 model succeeded in detecting and recognizing Javanese scripts well

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search