Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Jurnal ULTIMATICS

Design and Development of a Learning Style Identification Application for JPTK Students using the K-Nearest Neighbor Ramadhan, Firdaus Ditio; Liantoni, Febri; Prakisya, Nurcahya Pradana Taufik
ULTIMATICS Vol 15 No 2 (2023): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v15i2.3299

Abstract

Learning styles are crucial for all students, as the chosen learning style can greatly assist them in learning. The data source for this research originates from questionnaire results distributed to JPTK students of the 2019-2021 cohorts, which were used to assess the effectiveness of a learning style product on the students' JPTK website. This study employs the K-Nearest Neighbor approach, which utilizes the principle of nearest neighbors to categorize students' learning styles based on provided features. The data used in this research is derived from the website that students use to input information about their preferred learning styles. Various elements, including visual, auditory, and kinesthetic preferences, are present in the questionnaire on the website. Subsequently, the data is processed and fed into a Python K Nearest Neighbor model to predict students' learning styles and nearest neighbors. The evaluation results indicate that the developed classification model achieves a reasonably high accuracy level of 93%, making it a useful tool for effectively and efficiently identifying students' learning styles. It is hoped that implementing this learning style classification model will benefit the field of education. By understanding students' learning styles, educators can create more tailored lesson plans, enhance learning outcomes, and reduce the likelihood of knowledge loss.
Application of Convolutional Neural Network Using TensorFlow as a Learning Medium for Spice Classification Saputro, Muhammad Naufal Adi; Liantoni, Febri; Maryono, Dwi
ULTIMATICS Vol 16 No 1 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i1.3304

Abstract

The purpose of this research are: (1) To determine the accuracy of the CNN method in the development of a website for classifying spices, (2) To assess the feasibility of the spice classification website as a learning medium, (3) To ascertain user responses to the spice classification website as a learning medium. The method employed in this research is research and development. This study utilizes the ADDIE development method, which comprises 5 stages: (1) Analysis, (2) Design, (3) Development, (4) Implementation, and (5) Evaluation. The research yielded a significantly high accuracy rate. This is demonstrated by the results showing an accuracy of 96%, precision of 97%, and recall of 96%. Moreover, the research found the developed website to be feasible. This is supported by the evaluation using the Learning Object Review Instrument (LORI), resulting in a score of 88% from media experts and a score of 90% from subject matter experts. Additionally, user response was positive. This is evidenced by testing the learning media on 10th-grade culinary students from SMK N 4 Surakarta, which yielded a score of 76% using the System Usability Scale (SUS), indicating a favorable usability assessment. In conclusion, the spice classification website, as a learning medium, can be employed as a suitable educational tool.
Clustering Student Competencies Using the K-Means Algorithm Andini, Ratih Friska Dwi; Liantoni, Febri; Budianto, Aris
ULTIMATICS Vol 17 No 1 (2025): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v17i1.4071

Abstract

This study aims to evaluate the effectiveness of the K-Means algorithm in clustering student competencies. The subject of the study is students of the Informatics and Computer Engineering Education study program at a public university in Indonesia, with course score data representing various areas of competence as features. The K-Means algorithm is used to group student data into several clusters based on academic grade patterns. The results show that the K-Means algorithm is quite effective in identifying the initial pattern of student competence, with a Silhouette Score of 0.3489, which falls into the medium category. This study concludes that the use of the K-Means algorithm alone is sufficient to support the analysis of student areas of competence, with potential applications as a recommendation system for students in choosing elective courses and as an evaluation tool for study programs to identify areas of competence that need improvement.
Design and Development of a Learning Style Identification Application for JPTK Students using the K-Nearest Neighbor Ramadhan, Firdaus Ditio; Liantoni, Febri; Prakisya, Nurcahya Pradana Taufik
ULTIMATICS Vol 15 No 2 (2023): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v15i2.3299

Abstract

Learning styles are crucial for all students, as the chosen learning style can greatly assist them in learning. The data source for this research originates from questionnaire results distributed to JPTK students of the 2019-2021 cohorts, which were used to assess the effectiveness of a learning style product on the students' JPTK website. This study employs the K-Nearest Neighbor approach, which utilizes the principle of nearest neighbors to categorize students' learning styles based on provided features. The data used in this research is derived from the website that students use to input information about their preferred learning styles. Various elements, including visual, auditory, and kinesthetic preferences, are present in the questionnaire on the website. Subsequently, the data is processed and fed into a Python K Nearest Neighbor model to predict students' learning styles and nearest neighbors. The evaluation results indicate that the developed classification model achieves a reasonably high accuracy level of 93%, making it a useful tool for effectively and efficiently identifying students' learning styles. It is hoped that implementing this learning style classification model will benefit the field of education. By understanding students' learning styles, educators can create more tailored lesson plans, enhance learning outcomes, and reduce the likelihood of knowledge loss.
Application of Convolutional Neural Network Using TensorFlow as a Learning Medium for Spice Classification Saputro, Muhammad Naufal Adi; Liantoni, Febri; Maryono, Dwi
ULTIMATICS Vol 16 No 1 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i1.3304

Abstract

The purpose of this research are: (1) To determine the accuracy of the CNN method in the development of a website for classifying spices, (2) To assess the feasibility of the spice classification website as a learning medium, (3) To ascertain user responses to the spice classification website as a learning medium. The method employed in this research is research and development. This study utilizes the ADDIE development method, which comprises 5 stages: (1) Analysis, (2) Design, (3) Development, (4) Implementation, and (5) Evaluation. The research yielded a significantly high accuracy rate. This is demonstrated by the results showing an accuracy of 96%, precision of 97%, and recall of 96%. Moreover, the research found the developed website to be feasible. This is supported by the evaluation using the Learning Object Review Instrument (LORI), resulting in a score of 88% from media experts and a score of 90% from subject matter experts. Additionally, user response was positive. This is evidenced by testing the learning media on 10th-grade culinary students from SMK N 4 Surakarta, which yielded a score of 76% using the System Usability Scale (SUS), indicating a favorable usability assessment. In conclusion, the spice classification website, as a learning medium, can be employed as a suitable educational tool.
Identifying Academic Performance Patterns Among PTIK Students Using K-Means Clustering Anwar, Rizak Al Hasbi; Liantoni, Febri
ULTIMATICS Vol 17 No 2 (2025): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v17i2.3998

Abstract

This study explores the identification of academic performance patterns among students in the Informatics and Computer Engineering Education Study Program (PTIK) at Sebelas Maret University, focusing on the 2022 cohort. Using the K-Means clustering method within the scope of Data Mining, this research analyzes student performance data across multiple course categories from the first to fourth semesters. Through the Elbow method, four optimal clusters were established, each representing distinctive patterns of academic achievement. The analysis was conducted using RapidMiner software to reveal nuanced insights into student learning outcomes. Cluster 1 consists of students with moderate achievements in most categories, with a particular strength in Multimedia. Cluster 2 includes students with generally lower academic performance but shows a relative strength in General Courses. Cluster 3 is composed of high-achieving students who excel across categories, particularly in Software Engineering (RPL), Multimedia, and Educational subjects, indicating well-rounded academic proficiency. Cluster 4 comprises students with notable strengths in Software Engineering and Computer Networking, yet demonstrates lower performance in certain specialized subjects. These findings highlight the potential to tailor educational programs to address the specific learning needs and strengths of each student group, facilitating more personalized and effective academic support.