ANALYSIS OF OBJECT MOTION USING SMARTPHONE SENSOR DATA AND ARTIFICIAL INTELLIGENCE: A NEW APPROACH IN PHYSICS EDUCATION
Keywords:
Physics education, object motion, smartphone sensors, artificial intelligence, accelerometer, data analysis, real-time modeling, inquiry-based learning, educational technology, motion trackingAbstract
This study explores a novel approach to teaching physics by integrating smartphone sensor data with artificial intelligence (AI) tools to analyze the motion of physical objects. Modern smartphones are equipped with built-in accelerometers, gyroscopes, and magnetometers, which can record motion-related data with high precision. By combining these sensor outputs with AI-driven analysis platforms, students can visualize, model, and interpret real-world physical motion in classroom settings. The research highlights how this methodology fosters active learning, develops analytical thinking, and bridges theoretical physics with practical experimentation. The proposed approach not only increases student engagement but also introduces AI literacy within physics education.
References
OpenAI. (2023). GPT-4 Technical Report.
Hecht, E. (2016). Physics: Algebra/Trigonometry-Based. Cengage Learning.
Sokoloff, D. R. & Thornton, R. K. (2004). "RealTime Physics: Active Learning Laboratories." Physics Education, 39(6), 498–505.
Böhmer, M. et al. (2020). "Smartphone-Based Data Collection in Physics Education Using Phyphox." European Journal of Physics, 41(3), 035703.
UNESCO. (2021). Artificial Intelligence and the Futures of Learning.
Kim, H., & Lim, C. (2021). "Integration of AI in Science Classrooms: Implications for STEM Pedagogy." Journal of Educational Technology & Society, 24(2), 56–68.
Yuldashev, M. (2022). "Mobile Technologies in Physics Teaching." Uzbek Journal of Science Education, 4(1), 22–28.
Phyphox.org. (2023). Physics Phone Experiments Toolbox.
