Garuda - Garba Rujukan Digital

p-Index From 2020 - 2025

1.785

P-Index

This Author published in this journals

All Journal Journal of Information Technology and Computer Science Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer UTAMAX : Journal of Ultimate Research and Trends in Education Letters in Information Technology Education (LITE)

Hirashima, Tsukasa

Unknown Affiliation

Author-ID : 1478626

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Energy Engineering

Published : 15 Documents Claim Missing Document

Claim Missing Document

Articles

1 2

Educational Media Design for Learning Basic Programming in Branching Control Structure Material Using Problem-Posing Learning Model Syahidi, Aulia Akhrian; Tolle, Herman; Supianto, Ahmad Afif; Hirashima, Tsukasa
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 4, No 4, November 2019
Publisher : Universitas Muhammadiyah Malang

Basic programming is one subject that tends to be difficult for students to learn. Along with the development of technology, several researchers have provided solutions to solve this problem, by developing educational games, educational media, interactive learning media, and other auxiliary media. However, on average they have not used or adhered to the syntax of various existing learning models. This study focuses on designing educational media that uses the problem-posing learning model to study the material of branching control structures in basic programming learning which is recommended as a learning medium for vocational high school students. Educational media named TOLSYASUPI-EduMed. We use the highest type of research and development (R&D), the level 4 that we adopted to be adapted into a number of steps that are in line with the needs of this research area. Observation techniques are used as a form of generative research which is a type of user experience research, to explore information before designing a product/application. The side that we highlight here is how the form of educational media design by following the syntax of the problem-posing learning model. Then do an A/B testing which is assessed by experts to choose the best design with results that are type B designs with a percentage of 90.9%. We also state the analysis of the functional aspects of educational media to strengthen the validity of this design idea.

Improving Knowledge Structure through Extended Scratch-Build Concept Mapping Prasetya, Didik Dwi; Hayashi, Yusuke; Hirashima, Tsukasa
Letters in Information Technology Education (LITE) Vol 3, No 1 (2020)
Publisher : Universitas Negeri Malang

Extended concept mapping is a potential technique to elicit missing ideas and relationships. This study explored an Extended Scratch-Build (ESB) concept mapping in improving learners' knowledge structure. ESB is an expansion of an open-ended approach that asks students to connect the prior-existing original concept map with the new additional map on related material topics. The practical use of ESB has been conducted and proves positive effects on learning achievements. However, no information has been provided regarding the performance of the concept map components that describe the broad overview of students' attainments. This observationalÂ study focused on improving learners' knowledge using quantity measurements based on concept map features, consists of a number of concepts, number of links, and a number of propositions. University students (N = 27) with a major in Informatics Engineering participated in the study. The results reported that students' knowledge structure on additional maps significantly increased compared to the prior original map.

Measurement of User Satisfaction for Gamification-based Programming E-Learning Platform using End-user Computing Satisfaction Method Pradana, Fajar; Setyosari, Punaji; Ulfa, Saida; Hirashima, Tsukasa; Saputra, Mochamad Chandra
Journal of Information Technology and Computer Science Vol. 9 No. 2: August 2024
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.92572

HSS Learning is a learning media innovation in the form of a gamification-based e-learning platform to support the learning process in programming. HSS Learning has been applied to web design and programming courses, primarily on HTML and CSS topics. This study uses a quantitative model using a descriptive approach to measure the satisfaction level of HSS Learning users—measurement of user satisfaction using End-user Computing Satisfaction (EUCS). The variables used in this research are content, format, ease of use, timeliness, and accuracy. Data collection used a questionnaire consisting of 12 questions, with the number of participant data being 264 participants. The results show that the overall level of user satisfaction reaches 4.30 at level 5 (very strong). The results of this study can be used as a material evaluation for the application of instructional media in the programming field.

Web-based Application for Visual Representation of Learners' Problem-Posing Learning Pattern Supianto, Ahmad Afif; Wicaksono, Satrio Agung; Bachtiar, Fitra A.; Herlambang, Admaja Dwi; Hayashi, Yusuke; Hirashima, Tsukasa
Journal of Information Technology and Computer Science Vol. 4 No. 1: June 2019
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Studentsâ€™ learning process analysis normally involves massive amount of data. This study explores the pattern and relationship of studentsâ€™ learning process data in an interactive learning media to identify their learning process patterns to ease the needs of sophisticated data analysis for class instructors and educational researchers. This study focuses on the development of a web-based software application that creates a visual representation of studentsâ€™ learning process in a learning media. The result of this software is a visualization of studentsâ€™ activity sequence. This result is then used to infer studentsâ€™ learning patterns as well as identifying their learning behavior and to create a better feedback via the learning instructors. As a case study, this research uses the data log of Monsakun, a digital learning environment that focuses on the subject of mathematic for grade school students on the topic of arithmetic using story-based question and problem-posing approach. Investigation result shows four distinct learning activity patterns which are: smart pattern, adventure pattern, peer pattern and cyclic pattern. Each pattern requires different feedback to optimize learning progression, by using this web-based application, appropriate feedback to specific learning pattern is then applied to each student based on its learning activity pattern.

TOLSYASUPI-EduMed: Development of Educational Media Using the Problem-Posing Learning Model for Basic Programming Subjects Syahidi, Aulia Akhrian; Tolle, Herman; Supianto, Ahmad Afif; Hirashima, Tsukasa
Journal of Information Technology and Computer Science Vol. 4 No. 2: September 2019
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

The importance of expertise in the field of programming today makesVocational High Schools as early as a possible incorporate curriculum that canlearn skills in programming, which is then called basic programming subjects.These subjects are the initial foundation, to study other productive subjects thatmust be studied by students in the field of ICT expertise. However, in reality,students tend to dislike these subjects because they feel difficulties inunderstanding and learning them. Therefore, we try to present a solution toovercome this problem by developing basic programming educational media,especially in the material of branching control structures by embedding thesyntax of problem-posing learning models in the type of open-posing into theinteraction flow. This educational media is called TOLSYASUPI-EduMed. Theresearch and development method (R&D) was used as the main method in thisstudy. The model for system development uses ADDIE by adapting the R&Dmethod. A/B testing methods are used to validate the initial selection ofeducational media design. The form of design until the development stage isvalidated by media and material experts as much as 3 iterations, to ensure thatthe educational media can look for effects on the effectiveness of learning. Atotal of 36 students were involved in the use of this educational media.Evaluation of the use of educational media to determine aspects of satisfactionand usability using the Computer System Usability Questionnaire (CSUQ)method. The results of the study stated that 90.9% of experts agreed that VeryStrong to choose design B to continue at the advanced design, development,and implementation stages. The results of the validation of media and materialexperts state that it is feasible to use. Based on functional requirementsspecifications, all features function properly, and non-functionally 94.49% withpredicates Very Strong that end-users (students) are satisfied and feel theusefulness of this TOLSYASUPI-EduMed.

Design and Development of Online Collaborative Learning Platform of Kit-Build Concept Map Pinandito, Aryo; Prasetya, Didik Dwi; Az-zahra, Hanifah Muslimah; Wardhono, Wibisono Sukmo; Hayashi, Yusuke; Hirashima, Tsukasa
Journal of Information Technology and Computer Science Vol. 6 No. 1: April 2021
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

A concept map is deemed a useful teaching and learning tool. It offers many potential advantages over just representing the studentsâ€™ knowledge and understanding during learning, and have been widely used to support learning. Kit-Build concept map is one learning framework that incorporate digital concept map for its learning activities. Learning with Kit-Build concept map has been found to have better learning effects towards students' understanding and knowledge retention. Incorporating Kit-Build concept map into collaborative learning have been reported to have better outcome than the traditional collaborative learning. However, collaborative learning with Kit-Build concept map cannot be accomodated with the current Kit-Build system where learning activity is conducted online. This study presents the design and development of online collaborative learning platform of Kit-Build Concept Map. A prototype of the collaboration system to support collaborative learning with Kit-Build concept map is developed and be evaluated to portray its potential usability for further development and practical use. The result suggested that incorporating Socket.IO as a real-time communication middleware is effective to deliver online collaborative learning features into the Kit-Build system. Preliminary evaluation to the system also suggested that the system has the potential for actual use in supporting distant collaborative learning with Kit-Build concept map.

Comparison of Text Representation for Clustering Student Concept Maps Fatrisna Salsabila, Reni; Dwi Prasetya, Didik; Widyaningtyas, Triyanna; Hirashima, Tsukasa
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 24 No 2 (2025)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i2.4598

This research aims to address the critical challenge of selecting a text representation method that effectively captures students’ conceptual understanding for clustering purposes. Traditional methods, such as Term Frequency-Inverse Document Frequency (TF-IDF), often fail to capture semantic relationships, limiting their effectiveness in clustering complex datasets. This study compares TF-IDF with the advanced Bidirectional Encoder Representations from Transformers (BERT) to determine their suitability in clustering student concept maps for two learning topics: Databases and Cyber Security. The method used applies two clustering algorithms: K-Means and its improved variant, K-Means++, which enhances centroid initialization for better stability and clustering quality. The datasets consist of concept maps from 27 students for each topic, including 1,206 concepts and 616 propositions for Databases, as well as 2,564 concepts and 1,282 propositions for Cyber Security. Evaluation is conducted using two metrics Davies-Bouldin Index (DBI) and Silhouette Score, to assess the compactness and separability of the clusters. The result of this study is that BERT consistently outperforms TF-IDF, producing lower DBI values and higher Silhouette Scores across all clusters (k= 2 - k=10). Combining BERT with K-Means++ yields the most compact and well-separated clusters, while TF-IDF results in overlapping and less-defined clusters. The research concludes that BERT is a superior text representation method for clustering, offering significant advantages in capturing semantic context and enabling educators to identify student misconceptions and improve learning strategies.

Revealing Interaction Patterns in Concept Map Construction Using Deep Learning and Machine Learning Models Laily, F.ti Ayyu Sayyidul; Prasetya, Didik Dwi; Handayani, Anik Nur; Hirashima, Tsukasa
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 24 No 2 (2025)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i2.4641

Concept maps are educational tools for organizing and representing knowledge, enhancing comprehension, and memory retention. In concept map construction, much knowledge can be utilized. Still, concept map construction is complex, involving actions that reflect a user’s thinking and problemsolving strategies. Traditional methods struggle to analyze large datasets and capture temporal dependencies in these actions. To address this, the study applies deep learning and machine learning techniques. This research aims to evaluate and compare the performance of Long Short-Term Memory (LSTM), K-Nearest Neighbors (K-NN), and Random Forest algorithms in predicting user actions and uncovering user interaction patterns in concept map construction. This research method collects and analyzes interaction logs data from concept map activities, using these three models for evaluation and comparison. The results of this research are that LSTM achieved the highest accuracy (83.91%) due to its capacity to model temporal dependencies. Random Forest accuracy (80.53%), excelling in structured data scenarios. K-NN offered the fastest performance due to its simplicity, though its reliance on distance-based metrics limited accuracy (70.53%). In conclusion, these findings underscore the practical considerations in selecting models for concept map applications; LSTM demonstrates effectiveness in predicting user actions and excels for temporal tasks, while Random Forest and K-NN offer more efficient alternatives in computational.

Enhancing Semantic Similarity in Concept Maps Using LargeLanguage Models Wiryawan, Muhammad Zaki; Prasetya, Didik Dwi; Handayani, Anik Nur; Hirashima, Tsukasa; Pratama, Wahyu Styo; Putra, Lalu Ganda Rady
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 3 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i3.4727

This research uses advanced models, Generative Pre-trained Transformer-4 and Bidirectional Encoder Representations from Transformers, to generate embeddings that analyze semantic relationships in open-ended concept maps. The problem addressed is the challenge of accurately capturing complex relationships between concepts in concept maps, commonly used in educational settings, especially in relational database learning. These maps, created by students, involve numerous interconnected concepts, making them difficult for traditional models to analyze effectively. In this study, we compare two variants of the Artificial Intelligence model to evaluate their ability to generate semanticembeddings for a dataset consisting of 1,206 student-generated concepts and 616 link nodes (Mean Concept = 4, Standard Deviation = 4.73). These student-generated maps are compared with a reference map created by a teacher containing 50 concepts and 25 link nodes. The goal is to assess the models’ performance in capturing the relationships between concepts in an open-ended learning environment. The results show that demonstrate that Generative Pretrained Transformers outperform other models in generating more accurate semantic embeddings. Specifically, Generative Pre-trained Transformer achieves 92% accuracy, 96% precision, 96% recall, and 96% F1-score. This highlights the Generative Pretrained Transformer’s ability to handle the complexity of large, student-generatedconcept maps while avoiding overfitting, an issue observed with the Bidirectional Encoder Representationsfrom Transformer models. The key contribution of this research is the ability of two complex models and multi-faceted relationships among concepts with high precision. This makes it particularly valuable in educational environments, where precise semantic analysis of open-ended data is crucial, offering potential for enhancing concept map-based learning with scalable and accurate solutions.

Performance Evaluation of Artificial Intelligence Models for Classification in Concept Map Quality Assessment Pratama, Wahyu Styo; Prasetya, Didik Dwi; Widyaningtyas, Triyanna; Wiryawan, Muhammad Zaki; Putra, Lalu Ganda Rady; Hirashima, Tsukasa
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 3 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i3.4729

Open-ended concept maps generated by students give better flexibility and present a complex analysis process for teachers. We investigate the application of classification algorithms in assessing openended concept maps, with the purpose of providing assistance for teachers in evaluating student comprehension. The method used in this study is experimental methods, which consists of data collection, preprocessing, representation generation, and modelling with Feedforward Neural Network, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, and Logistic Regression. Our dataset, derived from concept maps, consists of 3,759 words forming 690 propositions, scored carefully by experts to ensure high accuracy in the evaluation process. Results of this study indicate that K-NN outperformed all other models, achieving the highest accuracy and Receiver Operating Characteristic-Area Under the Curve scores, demonstrating its robustness in distinguishing between classes. Support Vector Machine excelled in precision, effectively minimizing false positives, while Random Forest showcased a balanced performance through its ensemble learning approach. Decision Tree and Linear Regression showed limitations in handling complex data patterns. FeedforwardNeural Network can model intricate relationships, but needs further optimization. This research concluded that Artificial Intelligence classification enables a better assessment for teachers, enables the path for personalized learning strategies in learning.

Co-Authors Admaja Dwi Herlambang, Admaja Dwi Ahmad Afif Supianto Anik Nur Handayani Ariyanta, Nadindra Dwi Aryo Pinandito Banni Satria Andoko Didik Dwi Prasetya Fajar Pradana Fatrisna Salsabila, Reni Fitra Abdurrachman Bachtiar Hanifah Muslimah Az-Zahra, Hanifah Muslimah Hayashi, Yusuke Herman Tolle Laily, F.ti Ayyu Sayyidul Lalu Ganda Rady Putra Mochamad Chandra Saputra, Mochamad Chandra Pratama, Wahyu Styo Punaji Setyosari Saida Ulfa Satrio Agung Wicaksono Subhi, Dian Hanafudin Syahidi, Aulia Akhrian Triyanna Widyaningtyas, Triyanna Wafiuddin, Naufal Falah Wang, Xia Wibisono Sukmo Wardhono, Wibisono Sukmo Wicaksono, Reo Wiryawan, Muhammad Zaki Zaeni, Ilham Ari Elbaith

Title

Found 15 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 15 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 15 Documents
Search