Claim Missing Document
Check
Articles

Transforming Physics Learning: Developing AI-Based Interactive Videos to Understand Newton's Laws Hanisa Feranti Hanisa; Sardianto Markos Siahaan
Physics Education Research Journal Vol. 7 No. 2 (2025)
Publisher : Faculty of Science and Education, UIN Walisongo Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21580/perj.2025.7.2.25924

Abstract

This study aims to describe the results of the needs analysis conducted at SMA Negeri 3 Prabumulih as a basis for developing artificial intelligence-based learning videos for differentiated physics learning. Data analysis was carried out using validation sheet data, questionnaires and interviews. This study serves as a preliminary study at the definition stage, where researchers ensure that the products developed meet the needs of teachers and students. The results of the questionnaire as many as 92.3% (150 respondents), stated that they agreed that SMA uses learning videos for every physics material. This is because physics material is learning material that is difficult for students to understand. The results of the description of the assessment data by the media validator on the media in the form of learning videos are in the very good qualification, this is categorized as very good. The trial results show that products that are equipped with practical aspects shown to teachers and students are categorized as very practical. So the level of validity of this learning video media is said to be very valid because it is in the range of 92.82% and the level of practicality of the media in the form of learning videos is 97.28% categorized as very good.
Machine Learning to Predict Climate Change in Coastal Areas of Indonesia Huriyatul Firdausi; Melly Ariska; Sardianto Marcos Siahaan; Hamdi Akhsan; Yenny Anwar; Iin Seprina; Taufiq Taufiq
BULETIN FISIKA Vol. 27 No. 1 (2026): BULETIN FISIKA
Publisher : Departement of Physics Faculty of Mathematics and Natural Sciences, and Institute of Research and Community Services Udayana University, Kampus Bukit Jimbaran Badung Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/BF.2026.v27.i01.p05

Abstract

Indonesia's coastal regions face significant threats from climate change, including rainfall uncertainty, rising temperatures, and sea level rise. This study aims to explore the potential of machine learning algorithms in predicting climate parameter changes in the coastal areas of Minangkabau, Pesawaran, and Maritim Panjang. Daily climatological data obtained from the Meteorology, Climatology, and Geophysics Agency (BMKG) were used as the basis for model training. Three primary algorithms were tested Random Forest, XGBoost, and Long Short-Term Memory (LSTM) selected for their capability to handle complex and temporal data. The research methodology included data preprocessing, model training, cross-validation, and predictive performance evaluation using metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). Preliminary results show that LSTM excels in time series prediction, while XGBoost offers a good balance between speed and accuracy. These findings indicate that machine learning-based approaches have strong potential as decision-support tools for climate change mitigation and adaptation planning in Indonesia’s coastal regions.
Pelatihan Pembuatan Video Animasi Berbantuan Artificial Intelligence untuk Guru SMP Negeri 1 Indralaya Sardianto Markos Siahaan; Muhamad Yusup; Melly Ariska; Taufiq Taufiq; Wardah Amalia
Jurnal Pendidikan dan Pengabdian Masyarakat Vol. 9 No. 2 (2026): Mei
Publisher : FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppm.v9i2.10955

Abstract

Pemanfaatan teknologi Artificial Intelligence (AI) dalam pembuatan media pembelajaran menjadi kebutuhan mendesak bagi guru agar mampu menghadirkan pembelajaran yang kreatif, menarik, dan relevan dengan tuntutan Kurikulum Merdeka. Kegiatan Pengabdian kepada Masyarakat ini bertujuan meningkatkan kompetensi guru SMP Negeri 1 Indralaya dalam membuat video animasi pembelajaran berbantuan AI melalui pelatihan dan pendampingan terstruktur. Metode kegiatan meliputi sosialisasi, pelatihan teknis, workshop pembuatan video, pendampingan implementasi, serta evaluasi pre-test dan post-test. Hasil menunjukkan adanya peningkatan signifikan literasi digital guru dengan nilai N-gain sebesar 0,70 kategori sedang. Dari kegiatan ini, para guru menyatakan membuktikan bahwa integrasi AI membuat proses pembuatan media pembelajaran lebih efektif dan efisien dan meningkatkan kreativitas guru.
The Effectiveness of Web-Based Teaching Materials in Mandarin Subject Mega; Sardianto Markos Siahaan; Somakim
JPP (Jurnal Pendidikan dan Pembelajaran) Vol. 29 No. 1 (2022)
Publisher : Lembaga Pengembangan Pendidikan dan Pembelajaran, Universitas Negeri Malang in Collaboration with Asosiasi Pendidik dan Pengembang Pendidikan Indonesia (APPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aimed to determine the effectiveness of web-based teaching materials about "我的家人"(wǒ de jiā rén, my family)in Mandarin subject. This research employed a mixture of quantitative and qualitative research methods with the Alessi & Trollip development model of planning, design, and development. The subjects of this study were 37 students of management major at MDP University. The trial design in this study used a one-group pretest and posttestdesign. This research's datacollection techniques are interviews, observations, tests, and questionnaires. The researchers utilizedinterviews, observations, tests, and questionnaires to analyzethe data. The research analysison the development of teaching materials can be described as: (1) its validity has been tested after being tested through 3 experts carried out in stages, with an assessment of 93.33%. (2) its practicality has been tested on threestudents byfilling out a questionnaire. Itis obtained an efficient evaluation(91.66%) for each assessor. Thisweb-based teaching material can be used as online collaborative learningby getting an efficient assessment. (3) effectively increaseslearning outcomes between the pretest and posttestscores. In the pretest,the score was dominated in the very poor category, while in the posttest,the score was dominated in the good enough category. Itwas considered effective,reflected in the N-gain score of 56.49% in the medium category
Systematic Literature Review: Analisis Kebutuhan Instrumen Asessmen untuk Mengukur Kemampuan Coding dan Computational Thinking Pada Mahasiswa Pendidikan Fisika Berlianti Mandasari; Sardianto Markos Siahaan; Muhamad Yusup
Jurnal Penelitian Pendidikan IPA Vol 12 No 6 (2026)
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v12i6.15285

Abstract

This study aims to analyze the need for developing assessment instruments to measure coding skills and Computational Thinking (CT) among physics education students through a Systematic Literature Review (SLR). The literature search was conducted through Scopus and Google Scholar databases using systematic filtering procedures following PRISMA guidelines. The inclusion criteria covered studies addressing coding and/or CT in educational contexts, focusing on assessment instruments, providing full-text access, employing clear research methods, and published between 2022 and May 2026. The selection process identified 13422 initial articles, of which only 14 met all inclusion criteria. The findings reveal that studies specifically focusing on assessment instruments for coding and CT are still limited compared with research emphasizing instructional implementation. Most studies focus on Computational Thinking (9 studies), while only 2 studies discuss coding skills, and 3 studies indirectly examine both aspects. Based on educational levels, the studies are distributed across early childhood education (3), primary education (3), secondary education (1), higher education (2), and non-specific contexts (5). These findings indicate that research at the higher education level, particularly related to physics education, remains limited. Furthermore, no standardized instrument has yet been consistently applied to assess these competencies. However, recent developments in project-based assessment, STEM integration, and digital technology utilization demonstrate promising opportunities for more authentic assessment approaches. Therefore, this study highlights the importance of developing structured, valid, and reliable assessment instruments that not only evaluate learning outcomes but also capture students’ thinking processes during learning activities.
Efektivitas Blended Laboratory terhadap Kualitas Laporan Praktikum Fisika Siswa Agung Sugiarto; Hamdi Akhsan; Sardianto Markos Siahaan
JOEAI (Journal of Education and Instruction) Vol. 9 No. 3 (2026): JOEAI (Journal of Education and Instruction)
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/rjte2c87

Abstract

This study aims to analyze differences in the quality of physics practicum reports produced by 8th-grade junior high school students across three learning models: virtual experiments (PhET), real experiments, and blended laboratory. The study employed a quantitative approach using a quasi-experimental, non-equivalent control group design. The participants consisted of 45 students divided into three groups. The assessment instrument was a practicum report rubric covering objectives, procedures, data analysis, result interpretation, and evidence-based conclusions. Data were analyzed using One-Way ANOVA after satisfying the assumptions of normality and homogeneity. The results revealed significant differences among the groups (F(2,42) = 135.813; p < 0.001) with a very large effect size (η² = 0.866). The blended laboratory group achieved the highest scores compared to the other groups.   Keywords: Blended Laboratory, Scientific Communication, Report Quality, PhET Simulation, Physics Practicum