Garuda - Garba Rujukan Digital

Development of an Android-based Machine Learning Student Problem Identification Tool Application at YPT Banjarmasin VHS Muhammad Arisandy Rizky; Handaru Jati
Jurnal Penelitian Pendidikan IPA Vol. 9 No. 11 (2023): November
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i11.4420

The era of the 5.0 Industrial Revolution demands that we develop automation and digitalization technologies in various aspects of life, including education. Even Guidance and Counseling teachers who manually analyze counseling instrument items need assistance in swiftly and accurately analyzing instruments for hundreds of students. This research aims to support counselors in analyzing the Student Problem Identification Tool Instrument, which consists of 225 items, through studentâ€™s Android devices, thereby enabling the prompt resolution of student issues. Through the stages of Research and Development (R&D), the Student Problem Identification Tool Application is developed using the Multinomial Logistic Regression method within Machine Learning. This is achieved by replicating the capabilities of counselors based on analysis data from various previous instances of the Student Problem Identification Tool Instrument. Research outcomes reveal that the application achieves an accuracy rate of 100% when compared to manual analysis by counselors and application-based analysis for 30 students. The average performance test result is 85.00%, and the feasibility test result is 96.30%, categorizing it as "Highly Feasible." In conclusion, Machine Learning facilitates the effective and efficient analysis of extensive data when supported by quality training data and the appropriate method selection for problem-solving

Development of an Android-based Machine Learning Student Problem Identification Tool Application at YPT Banjarmasin VHS Muhammad Arisandy Rizky; Handaru Jati
Jurnal Penelitian Pendidikan IPA Vol 9 No 11 (2023): November
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i11.4420

The era of the 5.0 Industrial Revolution demands that we develop automation and digitalization technologies in various aspects of life, including education. Even Guidance and Counseling teachers who manually analyze counseling instrument items need assistance in swiftly and accurately analyzing instruments for hundreds of students. This research aims to support counselors in analyzing the Student Problem Identification Tool Instrument, which consists of 225 items, through studentâ€™s Android devices, thereby enabling the prompt resolution of student issues. Through the stages of Research and Development (R&D), the Student Problem Identification Tool Application is developed using the Multinomial Logistic Regression method within Machine Learning. This is achieved by replicating the capabilities of counselors based on analysis data from various previous instances of the Student Problem Identification Tool Instrument. Research outcomes reveal that the application achieves an accuracy rate of 100% when compared to manual analysis by counselors and application-based analysis for 30 students. The average performance test result is 85.00%, and the feasibility test result is 96.30%, categorizing it as "Highly Feasible." In conclusion, Machine Learning facilitates the effective and efficient analysis of extensive data when supported by quality training data and the appropriate method selection for problem-solving

Enhancing Humanoid Robot Soccer Ball Tracking, Goal Alignment, and Robot Avoidance Using YOLO-NAS Jati, Handaru; Ilyasa, Nur Alif; Dominic, Dhanapal Durai
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21839

This research aims to enhance humanoid robot soccer Ball Tracking, Goal Alignment, and Robot avoidance tasks using YOLO-NAS. The study followed a three-stage approach involving model engineering, which involves model training, code integration, and testing by comparing it with YOLO-v8 and YOLOv7. We measured the mAP (Mean Avegara Precision) and the speed of the detection of each model. Descriptive and Friedman techniques were employed to interpret testing results. In the ball tracking task, YOLO-NAS achieved a success rate of 53.3% compared to YOLOv7 with 68.3%. In the goal alignment task, YOLO-NAS achieved the highest success rate of 91.7%. In the Robot Avoidance task, YOLO-NAS, the same as YOLOv8, 100% nailed the test. These findings suggest that YOLO-NAS performs exceptionally well in the goal-alignment task but does not excel in two other tasks related to humanoid robot soccer.

ANALISIS SENTIMEN DATA TWITTER TERKAIT CHATGPT MENGGUNAKAN ORANGE DATA MINING Pahtoni, Tri Yuli; Jati, Handaru
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 2: April 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20241127276

Perkembangan teknologi bergerak begitu cepat, diikuti dengan popularitas media sosial yang semakin meluas. Platform media sosial mampu membangun profil big data pengguna, dengan melacak setiap aktivitas seperti partisipasi, pengiriman pesan, dan kunjungan situs Web. Saat ini banyak orang sering membagikan kritik terhadap sesuatu melalui platform media sosial seperti Facebook, Twitter, Instagram, dan lainnya. Sehingga perlu diketahui bagaimana komentar dari pengguna media sosial yang menghasilkan reaksi masyarakat terhadap chatGPT yang dirilis oleh OpenAI. Banyaknya komentar di Twitter menyebabkan sulitnya mengetahui kecenderungan respon masyarakat. Tujuan dari penelitian ini yaitu melakukan analisis sentimen postingan publik di Twitter untuk memberikan wawasan tentang sikap dan persepsi orang tentang suatu peristiwa yang terjadi. Penelitian ini memberikan ilustrasi peran Twitter dalam menampung postingan pengguna Twitter terkait chatGPT. Hasil penelitian ini dapat digunakan oleh pemangku kepentingan untuk menentukan kebijakan dalam penggunaan chatGPT. Penelitian ini menganalisis sebanyak 5.192 postingan tweet bahasa Inggris dan 641 tweet bahasa Indonesia, mulai dari tanggal 27 April hingga 8 Mei 2023. Tanggapan positif, negatif dan netral diolah menggunakan perangkat lunak orange data mining, yaitu tools machine learning, data mining, dan visualisasi data. Hasil menunjukan bahwa chatGPT mendapatkan tanggapan netral berbahasa Inggris dengan nilai sebesar 54,72%, tanggapan positif sebesar 31,64%, dan tanggapan negatif sebesar 13,64%. Hasil analisis sentimen berbahasa Indonesia tidak jauh berbeda, dengan nilai tanggapan netral sebesar 63,96%, tanggapan positif 23,56%, dan tanggapan negatif 12,48%. Sehingga dapat disimpulkan bahwa, rilisnya chatGPT mayoritas publik memberikan tanggapan netral atau tidak terdapat penolakan.AbstractTechnological developments move so fast, followed by the increasingly widespread popularity of social media. Social media platforms can build big-data profiles of users by tracking every activity such as participation, messaging, and website visits. Currently, many people often share criticism of something through social media platforms, such as Facebook, Twitter, Instagram, and others. So it is necessary to know how comments from social media users generate public reactions to chatGPT released by OpenAI. A lot of comments on Twitter make it difficult to know the trend of people's responses. This study aims to analyze the sentiment of public postings on Twitter to provide insight into people's attitudes and perceptions of an event that has occurred. This research illustrates Twitter's role in accommodating Twitter user posts regarding chatGPT. The results of this study can be used by stakeholders in making policies on the use of chatGPT. This study analyzed 5,192 posts in English and 641 tweets in Indonesian from April 27 to May 8, 2023. Positive, negative, and neutral responses were processed using orange data mining software, namely machine learning tools, data mining, and data visualization. The results show that chatGPT received neutral responses in English with a value of 54.72%, positive responses of 31.64%, and negative responses of 13.64%. The results of sentiment analysis in Indonesian were not much different, with neutral responses of 63.96%, positive responses of 23.56%, and negative responses of 12.48%. So it can be concluded that after the release of chatGPT, the majority of the public gave neutral responses or no rejection.

A Machine Learning Approach to Predicting On-Time Graduation in Indonesian Higher Education Pawitra, Mahendra Astu Sanggha; Hung, Hui-Chun; Jati, Handaru
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 9 No. 2 (2024): November 2024
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v9i2.77052

Graduating on schedule is a critical milestone for students in higher education, serving as a key indicator of both institutional effectiveness and student success. This study uses machine learning techniques to predict on-time graduation in Indonesian higher education. A dataset comprising 133 students from an engineering department over four academic years (2019–2023) was analyzed using the CRISP-DM framework. The research employed nine machine learning models, including Random Forest, Logistic Regression, Neural Networks, etc., to identify key predictors of on-time graduation. The result showed that Random Forest outperformed other models by achieving an accuracy of 85% and an AUC of 0.875. Additionally, the study developed a learning analytics dashboard to visualize predictive insights, offering actionable data for educators and administrators. The system's performance was evaluated based on functionality, usability, efficiency, and reliability as the key intersecting factors from ISO/IEC 25010 and WebQEM frameworks, validating its quality and relevance for practical educational use. The result demonstrated high functionality, efficiency, and reliability, and positive usability feedback was received from both students and educators. The findings highlight the top ten important factors, such as cumulative GPA (CGPA), extracurricular involvement, programming, and social science courses, that predict on-time graduation, providing valuable insights for enhancing student outcomes in Indonesian higher education.

Analysis and Development of Project Monitoring Information Systems Using RESTful API Echo Framework at SMK Negeri 2 Klaten Rachelita Embun Safira; Handaru Jati
Journal of Information Technology and Education (JITED) Vol. 1 No. 1 (2023): March 2023
Publisher : Department of Electronics and Informatics Engineering Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jited.v1i1.47

Based on the results of observations, project monitoring activities at SMK N 2 Klaten still use manual methods, so it is less effective to implement. This research aims to (1) streamline the monitoring, guiding, and storing of progress documentation in the SIJA department of SMK N 2 Klaten through designing and developing a project monitoring information system, (2) meet quality standards ISO/IEC 25010. The research was conducted using the Research and Development (R&D) method, developed using the SDLC (System Development Life Cycle) method with the Waterfall model, which consists of the stages of needs analysis, design planning, coding, testing, and management. Quality analysis is done using the ISO/IEC 25010 standard on several aspects, namely (1) functional suitability, (2) usability, (3) performance efficiency, (4) reliability, and (5) portability. The results obtained include: (1) A website-based project monitoring information system developed using the waterfall development model, using the Gorm, Echo, and Vue.js frameworks. (2) The results of testing the quality of the ISO/IEC 25010 system are the functional suitability aspect with a score of 1 (very good), the aspect of use with a proportion of 80% (feasible) with an Alpha Cronbach score of 0.957 (very good), the efficiency of the performance aspects with a score of 99.81% (very good) for performance and 98.9% (very good) for structure, aspect of reliability with a score of 100% (has met), as well as the aspect of portability has been fulfilled because it can be run on various browsers, both desktop and mobile.

Analisis Usability Dengan Metode Heuristic Evaluation Pada Website Paperlust.Co Muhammad Yarjullah Hanif; Handaru Jati; Nurkhamid
Journal of Information Technology and Education (JITED) Vol. 1 No. 2 (2023): September 2023
Publisher : Department of Electronics and Informatics Engineering Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jited.v1i2.76

One of the requirements that a website must meet is good usability or ease to use. Paperlust is a website platform that facilitates designers selling their work to customers who want to print invitations. The percentage of people who visited and made purchases through the Paperlust website during 2018-2020 was 0.26%, which is still below the e-commerce industry average of 2.27%. Although many factors influence this number, usability strongly influences people's decisions to shop on a website. This study aims to analyze the usability of the Paperlust website and propose solutions to the problems found. Usability analysis in this study uses the heuristic evaluation method regarding Nielsen and Tognazzini's usability principles. Five evaluators carried out the evaluation and data collection through observation by evaluators, questionnaires, and interviews. Data analyzes quantitatively by calculating the average severity rating, frequency and percentage of problems found. This study found 86 usability problems with an average severity rating of 2.21, or the majority classified as minor problems. The proposed recommendations are improving consistency, icon conformity, information redundancy, reducing delay, providing feedback, learnability, default conditions, flexibility, information priority, and text readability.

Sentiment and Emotional Analysis of The Public Housing Savings Program (TAPERA) using Orange Data Mining Fadly, Hawangga Dhiyaul; Jati, Handaru
Journal of Applied Informatics and Computing Vol. 9 No. 3 (2025): June 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i3.9297

This study employs a text analysis methodology to assess public perception of the People's Housing Savings Program (TAPERA), by examining 3.078 tweets containing the keyword "tapera" using the Orange Data Mining application with two analytical approaches: the Valence Aware Dictionary and Sentiment Reasoner (VADER) for sentiment analysis and the Profile of Mood States (POMS) for emotional analysis. The sentiment analysis results indicate 1.481 tweets (48,2%) expressed negative sentiment, 830 tweets (27%) were neutral, and 767 tweets (24,8%) conveyed positive sentiment. These findings suggest that although there is a portion of positive responses toward the TAPERA policy, most of the public tends to express dissatisfaction or scepticism about the program. Furthermore, the emotional analysis identified depression as the most dominant emotion expressed by the public, appearing in 2.019 tweets (65,6%), followed by confusion (14,7%) and anger (9,6%). Positive emotions such as vigour and tension were recorded in significantly lower proportions, at 2,9% and 1,8%, respectively. These results illustrate that the public feels frustrated, confused, and anxious regarding the TAPERA policy, with minimal expressions of optimism or enthusiasm. This analysis highlights the need for a more transparent, educational, and data-driven communication approach to enhance public understanding, trust, and participation in the TAPERA policy. Therefore, the government must design more effective outreach strategies to address public concerns and ensure the successful implementation of this program.

Information System Prediction of Room for Rent Price in Yogyakarta Region Based on Website Using Linear Regression Algorithm Cahyana, Cecep Wahyu; Jati, Handaru
Journal of Information Engineering and Technology Vol. 3 No. 1 (2025): March 2025
Publisher : Department of Electronics and Informatics Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jiety.v3i1.1262

This development research was carried out to create a boarding house price prediction information system product that could help the problems of entrepreneurs and boarding house users regarding the determination of boarding prices. This development research was carried out to create a boarding house price prediction information system product that could help the problems of entrepreneurs and boarding house users regarding the determination of boarding prices. The research method used in this development research process is Research and Development with the Waterfall Model method. During the development process, tests were also carried out to determine the quality of the information system developed by referring to the ISO 25010:2011. The results of this research and development process are (1) Linear Regression algorithm as the best Machine Learning model that can make relevant and accurate predictions of boarding house rental prices. (2) A web-based boarding price prediction information system in the Yogyakarta Region was developed using the Waterfall development model and the Flask framework, which can automatically predict the relevant prices of the facilities selected by the user. (3) Test results on the Functional Suitability aspect ensure that all functions in the information system can run properly. The usability aspect produces 86.7% (Very Good category). The Performance Efficiency aspect produces a percentage of 100% (Very Good Performance), and fully loaded web page time is only 0.707 seconds (Good category). The reliability aspect results in a percentage of system resilience of 100% on sessions, pages, and hits in testing.

EDULEXYA: Development of Educational Gamification Application with Interactive Card Media to Improve Learning Outcomes for Children With Dyslexia on The Android Platform Saputra, Apry Aditya; Jati, Handaru
Journal of Information Engineering and Technology Vol. 3 No. 1 (2025): March 2025
Publisher : Department of Electronics and Informatics Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jiety.v3i1.1264

This study addresses the learning challenges faced by children with dyslexia, particularly in writing, spelling, and reading. The objectives are: (1) to analyze user needs and determine suitable application features to support dyslexic children's learning; (2) to design a mobile application, EduLexya, incorporating gamification and interactive card-based multisensory learning methods; and (3) to evaluate the application’s effectiveness in enhancing learning outcomes. Employing a Research and Development (R&D) framework with the Software Development Life Cycle (SDLC) waterfall model, the study involved dyslexic children aged 7–15 years from Somoitan (experimental) and Giriharjo (control) elementary schools. Data collection involved observation, interviews, questionnaires, and pretest-posttest assessments. Statistical analysis included validity, normality, homogeneity, and hypothesis testing via the Independent Samples T-Test. Findings identified essential features—writing, spelling, reading, quizzes, schedules, settings, guides, and feedback. The application was rated highly by material experts (5.00), media experts (4.81), and beta testers (4.81). Posttest results showed a significant improvement in the experimental class (M = 84.37, Sig. 0.000) over the control class (M = 74.33, Sig. 0.043), confirming EduLexya’s effectiveness in improving dyslexic learners’ academic outcomes.

Title

Found 32 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 32 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 32 Documents
Search