Towards Intelligent Physics Experiments: A Physics-Informed KNN Approach for Projectile Motion Reconstruction Using Tracker Video Analysis in Python

Authors

  • M. Firman Ramadhan Department of Physics Education, Faculty of Education and Teacher Training, Universitas Islam Negeri Mataram, Indonesia
  • M. Taufik Department of Primary School Teacher Education, STKIP Hamzar, Indonesia
  • Muhammad Eka Putra Ramandha Program Studi Pendidikan Guru Madrasah Ibtidaiyah, Fakultas Tarbiyah dan Keguruan Universitas Islam Negeri Mataram, Indonesia
  • Eka Safitri Department of Physics Education, Faculty of Education and Teacher Training, Universitas Islam Negeri Mataram, Indonesia
  • Arya Anggara Department of Physics Education, Faculty of Education and Teacher Training, Universitas Islam Negeri Mataram, Indonesia

DOI:

https://doi.org/10.52434/jpif.v6i1.44010

Keywords:

Physics-Informed KNN, Gerak Parabola, Analisis Video Tracker, Fisika Komputasi, Rekonstruksi Lintasan

Abstract

This study develops a Physics-Informed K-Nearest Neighbors (KNN) approach to reconstruct projectile motion based on experimental data using Tracker video analysis and Python. This study is motivated by the limitations of idealized physical models in representing real experimental conditions, which are influenced by air resistance, measurement noise, and data uncertainty. The research method comprises three main stages: acquisition of parabolic motion data using Tracker, theoretical modeling based on kinematic equations, and trajectory reconstruction using KNN. The results show that Physics-Informed KNN produces trajectories that are closer to the observed data compared to pure physics models. Horizontal motion exhibits the characteristics of uniform linear motion (ULM), while vertical motion forms a parabolic pattern consistent with uniformly accelerated linear motion (UALM). Error analysis indicates that the best performance is achieved at K = 2 with the minimum RMSE value. Based on the experimental dataset analyzed, the integration of machine learning and physical principles shows potential for improving the accuracy of dynamic system reconstruction under realistic experimental conditions.

References

Abror, D., Nasyuha, A. H., Chung, M., Technology, C., & Engineering, I. (2025). KNN Approach to Evaluating the Feasibility of Using Scientific Publications as Final Projects. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(1), 239–247. https://doi.org/10.33395/sinkron.v9i1.14370

Adil, K., & Ahmed, A. (2023). Machine Learning and Deep Learning based Students ’ Grades Prediction. Research Square, 1–18. https://doi.org/10.21203/rs.3.rs-3192793/v1

Aich, J., Mulla, N., Kalita, S., Kaur, N., & Singh, S. (2024). Performance Scrutiny of Price Prediction on Blockchain Technology Using Machine Learning. Journal of Electrical Systems, 20(7), 446–452. https://doi.org/10.52783/jes.3339

Chiha, Z., Péteri, R., Mascarilla, L., Chiha, Z., Péteri, R., Mascarilla, L., Projectile, P., Tennis, T., Chiha, Z., & Renaud, P. (2024). Predicting 3D Projectile Motion in Table Tennis Using Computer Vision and Physics-Informed Neural Network To cite this version : HAL Id : hal-04916281 Predicting 3D Projectile Motion in Table Tennis Using Computer Vision and Physics-Informed Neural Networ. International Conference on Content-Based Multimedia Indexing (CBMI). https://doi.org/10.1109/CBMI62980.2024.10859206

Demidova, L. A. (2021). Two-Stage Hybrid Data Classifiers Based on SVM and kNN Algorithms. Symmetry, 13(615). https://doi.org/ 10.3390/sym13040615

Deng, L. (2024). Multi-level physics informed deep learning for solving partial differential equations in computational structural mechanics. Communications Engineering, 1–12. https://doi.org/10.1038/s44172-024-00303-3

Dermul, N., & Dierckx, H. (2024). Reconstruction of excitation waves from mechanical deformation using physics ‑ informed neural networks. Scientific Reports, 14(16975), 1–16. https://doi.org/10.1038/s41598-024-67597-3

Fatima, N., Riaz, S., Ali, S., Ullah, M., & Kwak, D. (2024). Sensors Faults Classification and Faulty Signals Reconstruction Using Deep Learning. IEEE Access, 12(June), 100544–100558. https://doi.org/10.1109/ACCESS.2024.3425408

Floch, K., & Kossa, A. (2023). SoftwareX Motion Tracker Beta : A GUI based open-source motion tracking application. SoftwareX, 23, 101424. https://doi.org/10.1016/j.softx.2023.101424

Hakkak, A., Torbati, M., & Shiravand, Y. (2026). Learning Nonlinear Motor Control : How Integrating Machine Learning and Nonlinear Dynamics Reveals Structure , Adaptation , and Control in Human Movement. Actuators, 15(166), 1–22. https://doi.org/10.3390/act15030166

Harmening, J. H., & Peitzmann, F. (2024). Effect of network architecture on physics-informed deep learning of the Reynolds-averaged turbulent fl ow fi eld around cylinders without training data. Frontiers in Physics, 12(March), 1–16. https://doi.org/10.3389/fphy.2024.1385381

Hassan, M. El, Mjalled, A., Miron, P., Mönnigmann, M., & Bukharin, N. (2025). Machine Learning in Fluid Dynamics — Physics-Informed Neural Networks ( PINNs ) Using Sparse Data : A Review. Fluids, 10(226), 1–29. https://doi.org/10.3390/fluids10090226

Haywood-alexander, M., Arcieri, G., Kamariotis, A., & Chatzi, E. (2025). Response estimation and system identification of dynamical systems via physics-informed neural networks. In Advanced Modeling and Simulation in Engineering Sciences (Vol. 0123456789). Springer International Publishing. https://doi.org/10.1186/s40323-025-00291-9

Hou, X., Xing, H., Guo, S., Shi, H., & Yuan, N. (2024). applied sciences Design and Implementation of a Model Predictive Formation Tracking Control System for Underwater Multiple Small Spherical Robots. Applied Sciences, 14(294), 1–29. https://doi.org/10.3390/ app14010294

Iaousse, M., Jouilil, Y., Bouincha, M., & Mentagui, D. (2023). A Comparative Simulation Study of Classical and Machine Learning Techniques for Forecasting Time Series Data. International Journal of Online and Biomedical Engineering (IJOE), 19(18), 56–65. https://doi.org/10.3991/ijoe.v19i08.39853

Janjua, M. G., Kaiser, K., Stadelmayer, T., Member, S., Schoenfeldt, S., Issakov, V., & Member, S. (2024). JEDAN : Joint Euclidean Distance and Autoencoder Network for Robust Out-of-Distribution Detection in Radar-Based Hand Gesture Recognition. IEEE Access, 12(November), 196364–196381. https://doi.org/10.1109/ACCESS.2024.3520810

Jeong, J., Ozger, M., & Lee, W. (2024). Compressed Sensing vs . Auto-encoder : On The Perspective of Signal Compression and Restoration. IEEE Access, PP, 1. https://doi.org/10.1109/ACCESS.2024.3366899

Jian, X., Member, G. S., Tay, W. P., & Member, S. (2024). Kernel Based Reconstruction for Generalized Graph. IEEE Transactions on Signal Processing, 72, 2308–2322. https://doi.org/10.1109/TSP.2024.3395021

Jiang, X. Z. R., Tong, C. F. T., & Huang, T. W. P. (2021). Advances in Deep Learning Methods for Visual Tracking : Literature Review and Fundamentals. International Journal of Automation and Computing, 18(June), 311–333. https://doi.org/10.1007/s11633-020-1274-8

Kalesh, D., Merembayev, T., Omirbekov, S., & Amanbek, Y. (2025). Results in Engineering Application of physics-informed neural networks for two-phase flow model with variable diffusion and experimental validation. Results in Engineering, 26(February), 105439. https://doi.org/10.1016/j.rineng.2025.105439

Kardamaki, A., Protoulis, T., Alexandridis, A., & Sarimveis, H. (2026). An explicit model predictive control framework based on physics-informed neural networks. Journal of Process Control, 158(November 2025), 1–16. https://doi.org/10.1016/j.jprocont.2026.103634

Karima, A. A., Mirsa, F. R., Sherliyanti, Y., Puteri, A. Y., & Zainuddin, A. (2023). ( Projectile Motion ) Props Assisted by Tracker Video Analysis to Increase Students ’ Interest in Learning Parabolic Motion Material. Integrasi Merdeka Belajar Di Era Society 5.0 Melalui Inovasi Fisika Dan Pendidikan Fisika Menuju Sustainable Development Goals (SDGs) 2030, 151–160. https://proceeding.unesa.ac.id/index.php/snf/issue/view/42

Knights, V. A., Petrovska, O., & Kljusuri, J. G. (2024). Nonlinear Dynamics and Machine Learning for Robotic Control Systems in IoT Applications. Future Internet, 16(435), 1–23. https://doi.org/10.3390/fi16120435

Kontolati, K., Goswami, S., Karniadakis, G. E., & Shields, M. D. (2024). Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems. Nature Communications, 1–11. https://doi.org/10.1038/s41467-024-49411-w

Lee, J., Park, K., & Jung, W. (2024). Physics-Informed Neural Networks for Cantilever Dynamics and Fluid-Induced Excitation. Applied Sciences, 14(7002), 1–16. https://doi.org/ 10.3390/app14167002

Li, Y. (2024). Physics-Informed Neural Network-Based Nonlinear Model Predictive Control for Automated Guided Vehicle Trajectory Tracking. World Electric Vehicle, 15(460), 1–17. https://doi.org/ 10.3390/wevj15100460

Lytridis, C., Lekova, A., Bazinas, C., Manios, M., & Kaburlasos, V. G. (2020). WINkNN : Windowed Intervals ’ Number kNN Classifier for E ffi cient Time-Series Applications. Mathematics, 8(413), 1–14. https://doi.org/10.3390/math8030413

Mardiyah, S., & Subali, B. (2024). Minat Dan Peningkatan Kemampuan Berpikir Analitik Siswa Melalui Implementasi. Unnes Physics Education Journal, 13(3), 307–316. https://doi.org/10.15294/upej.v13i3.19789

Moon, H., Lee, S., Demeke, W., Ryu, B., & Ryu, S. (2025). Physics-informed neural operators for generalizable and label-free inference of temperature-dependent thermoelectric properties. Npj Computational Materials, 11(272), 1–11. https://doi.org/10.1038/s41524-025-01769-1

Muzelak, M., Skovranek, T., & Ruzicka, M. (2024). Physics-Informed Neural Networks Application To Mass-Spring System Solution. 2024 25th International Carpathian Control Conference (ICCC), 1–4. https://doi.org/10.1109/ICCC62069.2024.10569161

Pagliaro, A., Compagnino, A. A., & Sangiorgi, P. (2025). Advanced AI and Machine Learning Techniques for Time Series Analysis and Pattern Recognition. Applied Sciences, 15(3165), 13–18. https://doi.org/10.3390/app15063165

Paramasivam, K., Mansoor, M., Sindha, R., & Balakrishnan, S. B. (2023). KNN-Based Machine Learning Classifier Used on Deep Learned Spatial Motion Features for Human Action Recognition. Entropy, 25(844), 1–15. https://doi.org/10.3390/ e25060844

Parfenyev, V., Blumenau, M., & Nikitin, I. (2024). Inferring Parameters and Reconstruction of Two-Dimensional Turbulent Flows with Physics-Informed Neural Networks. PLASMA, HYDRO- AND GAS DYNAMICS, 120(8), 627–635. https://doi.org/10.1134/S0021364024602203

Pilar, P., & Om, N. W. (2024). Physics-informed Neural Networks with Unknown Measurement Noise. Proceedings of Machine Learning Research, 242, 235–247. https://proceedings.mlr.press/v242/pilar24a.html

Pulgar, F. J., Charte, F., Rivera, A. J., & Jesus, M. J. (2019). AEkNN : An AutoEncoder kNN – Based Classifier With Built-in Dimensionality Reduction. International Journal OfComputational Intelligence Systems, 12(1), 436–452. https://doi.org/10.2991/ijcis.2018.125905686

Rainio, O. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 1–15. https://doi.org/10.1038/s41598-024-56706-x

Renika, J., Prima, E. C., & Amprasto. (2024). Kinematics analysis on accelerated motion using tracker video analysis for educational purposes. Momentum: Physics Education Journal, 8(1), 23–31. https://doi.org/10.21067/mpej.v8i1.8883

Ryck, T. D. S. M. (2024). Numerical analysis of physics- informed neural networks and related models in physics-informed machine learning. Acta Numerica, 33, 633–713. https://doi.org/10.1017/S0962492923000089

Schmitz, T. (2024). Physics-informed KNN milling stability model with process damping effects. Journal of Manufacturing Processes, 120(June), 1124–1129. https://doi.org/10.1016/j.jmapro.2024.04.090

Seo, J. (2024). Solving real ‑ world optimization tasks using physics ‑ informed neural computing. Scientific Reports, 1–10. https://doi.org/10.1038/s41598-023-49977-3

Souza, D. V., Paula, A., Corte, D., & Sanquetta, C. R. (2020). k -NEAREST NEIGHBOR AND LINEAR REGRESSION IN THE PREDICTION OF THE ARTIFICIAL FORM FACTOR. FLORESTA, 50(3), 1669–1678. https://doi.org/10.5380/rf.v50

Vargas, H., Fabiani, G., Kazantzis, N., Kevrekidis, I. G., & Siettos, C. (2024). Nonlinear discrete-time observers with Physics-Informed Neural Networks. Chaos, Solitons and Fractals, 186(June), 115215. https://doi.org/10.1016/j.chaos.2024.115215

Wong, H. S., Chan, W. X., Li, B. H., & Yap, C. H. (2024). Strategies for multi ‑ case physics ‑ informed neural networks for tube flows : a study using 2D flow scenarios. Scientific Reports, 1–15. https://doi.org/10.1038/s41598-024-62117-9

Wu, R., Wen, X., Yuan, L., & Xu, H. (2023). Spatiotemporal key region transformer for visual tracking. Complex & Intelligent Systems, 9(5), 5865–5879. https://doi.org/10.1007/s40747-023-01040-4

Wu, Y., Sicard, B., & Gadsden, S. A. (2024). Physics-informed machine learning : A comprehensive review on applications in anomaly detection and condition monitoring. Expert Systems With Applications, 255(PC), 124678. https://doi.org/10.1016/j.eswa.2024.124678

Xie, T., Chen, L., Yi, B., Li, S., Leng, Z., Gan, X., & Mei, Z. (2024). Application of the Improved K-Nearest Neighbor-Based Multi-Model Ensemble Method for Runoff Prediction. Water, 16(69), 1–20. https://doi.org/10.3390/ w16010069

Yokota, K., Kurahashi, T., & Abe, M. (2024). Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube. Journal of the Acoustical Society of America, 156(July), 1–15. https://doi.org/10.1121/10.0026459

Yuan, L., Ni, Y., Deng, X., & Hao, S. (2022). A-PINN : Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations. Journal of Computational Physics, 462, 111260. https://doi.org/10.1016/j.jcp.2022.111260

Zahran, M., Medellu, N. C., Sari, I. M., Rizqi, M., & Selamat, M. B. (2024). Implementasi Video Based Laboratory Menggunakan Software Tracker dalam Menentukan Percepatan Gravitasi Bumi di Berbagai Kota di Pulau Sulawesi Indonesia dan Turki. Jurnal Phi: Jurnal Pendidikan Fisika Dan Fisika Terapan, 10(July), 10–17. https://doi.org/10.22373/p-jpft.v10i2.18522

Zapf, B., Haubner, J., Kuchta, M., Ringstad, G., Eide, P. K., & Mardal, K. A. (2022). Investigating molecular transport in the human brain from MRI with physics ‑ informed neural networks. Scientific Reports, 1–12. https://doi.org/10.1038/s41598-022-19157-w

Zhang, W. (2024). A General Method for Solving Differential Equations of Motion Using Physics-Informed Neural Networks. Applied Sciences, 14(7694), 1–15. https://doi.org/10.3390/ app14177694

Zhang, Z., Lin, C., & Wang, B. (2024). Physics ‑ informed shape optimization using coordinate projection. Scientific Reports, 1–12. https://doi.org/10.1038/s41598-024-57137-4

Zou, Z., Meng, X., & Karniadakis, G. E. (2024a). Correcting model misspecification in physics-informed neural networks ( PINNs ). Journal of Computational Physics, 505, 1–26. https://doi.org/10.1016/j.jcp.2024.112918

Zou, Z., Meng, X., & Karniadakis, G. E. (2024b). Uncertainty quantification for noisy inputs-outputs in physics-informed neural networks and neural operators. Computer Methods in Applied Mechanics and Engineering, 433(Part A), 1–34. https://doi.org/10.1016/j.cma.2024.117479

Downloads

Published

2026-06-23

Issue

Vol. 6 No. 1 (2026): June 2026 (in press)

Section

Artikel

License

Copyright (c) 2026 M. Firman Ramadhan, M. Taufik, Muhammad Eka Putra Ramandha, Eka Safitri, Arya Anggara

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.