HUMAN MOVEMENT IDENTIFICATION USING WI-FI WITH CHANNEL STATE INFORMATION
Abstract
This research describes the development of a system for the identification of movements using physical information from the Wi-Fi signal, such as amplitude and phase, known as Channel State Information (CSI). Data is captured in a controlled environment using a Raspberry Pi 4 microcomputer with custom firmware and components for the emission and transmission of Wi-Fi signals. Subsequently, the data is classified using Machine Learning models, such as SVM, Random Forest, and KNN. The experimental results demonstrate the capability of the system to detect movements, indicating that CSI is a non-intrusive alternative for movement identification, superior to traditional monitoring methods using images or audio.
Author Biographies
Graduanda em Engenharia da Computação pela Universidade de Araraquara - UNIARA.
Prof. Dr. na Universidade de Araraquara - UNIARA.
Docente na Universidade de Araraquara - UNIARA. Doutora em Alimentos e Nutrição pela UNESP (FCFAR).
References
DAMODARAN, Neena et al. Device free human activity and fall recognition using WiFi channel state information (CSI). CCF Transactions on Pervasive Computing and Interaction, v. 2, p. 1–17, 2020. DisponÃvel em: https://link.springer.com/article/10.1007/s42486-020-00027-1 Acesso em: 23 fev. 2025. DOI: https://doi.org/10.1007/s42486-020-00027-1
GRINGOLI, Francesco et al. Free your CSI: A channel state information extraction platform for modern Wi-Fi chipsets. In: Proceedings of the 13th International Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization. 2019. p. 21-28. DisponÃvel em: https://dl.acm.org/doi/10.1145/3349623.3355477 Acesso em: 20 mar. 2025. DOI: https://doi.org/10.1145/3349623.3355477
IBM. O que é aprendizado supervisionado? [S. l.]: IBM, s. d. DisponÃvel em: https://www.ibm.com/br-pt/think/topics/supervised-learning Acesso em: 8 set. 2025.
IBM. O que é inteligência artificial (IA)? [S. l.]: IBM, s. d.(b). DisponÃvel em: https://www.ibm.com/br-pt/think/topics/artificial-intelligence Acesso em: 27 ago. 2025.
IMBALANCED-LEARN DEVELOPERS. Imbalanced-learn documentation, [S. l.], 14 ago. 2025. DisponÃvel em: https://imbalanced-learn.org/stable/ Acesso em: 28 set. 2025.
KUROSE, James F.; ROSS, Keith W. Redes de computadores e a internet: uma abordagem top-down. 8. ed. Porto Alegre: Pearson, 2021.
MA, Yongsen; ZHOU, Gang; WANG, Shuangquan. WiFi sensing with channel state information: A survey. ACM Computing Surveys (CSUR), v. 52, n. 3, p. 1–36, 2019. DisponÃvel em: https://dl.acm.org/doi/abs/10.1145/3310194 Acesso em: 25 maio 2025. DOI: https://doi.org/10.1145/3310194
SCHULZ, Matthias; WEGEMER, Daniel; HOLLICK, Matthias. Nexmon: The C-based Firmware Patching Framework. DisponÃvel em: https://nexmon.org Acesso em: 20 mar. 2025.
TANENBAUM, Andrew S.; FEAMSTER, Nick; WETHERALL, David. Redes de computadores. 6. ed. Porto Alegre: AMGH, 2021.
THE NUMPY DEVELOPERS. NumPy v2.0 Manual. [S. l.]: The Numpy Developers, 2024. DisponÃvel em: https://numpy.org/doc/stable/ Acesso em: 8 set. 2025.
THE PANDAS DEVELOPMENT TEAM. pandas 2.2.2 documentation. [S. l.]: The Pandas Development Team, 2024. DisponÃvel em: https://pandas.pydata.org/docs/ Acesso em: 8 set. 2025.
THE SCIKIT-LEARN DEVELOPERS. scikit-learn 1.5 documentation. [S. l.]: The Scikit-Learn Developers, 2024. DisponÃvel em: https://scikit-learn.org/stable/ Acesso em: 8 set. 2025.
TRINDADE, Eduardo FabrÃcio Gomes; DE ALMEIDA, Felipe Silveira; PEREIRA JUNIOR, Lourenço Alves Pereira. Além do Sinal: Autenticação BiofÃsica com Wi-Fi CSI e Raspberry Pi. In: Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais (SBSeg). SBC, 2024. p. 32-47. DisponÃvel em: https://sol.sbc.org.br/index.php/sbseg/article/download/30015/30014/ Acesso em: 05 fev. 2025. DOI: https://doi.org/10.5753/sbseg.2024.241787
WANG, Yuxi; WU, Kaishun; NI, Lionel M. Wifall: Device-free fall detection by wireless networks. IEEE Transactions on Mobile Computing, v. 16, n. 2, p. 581–594, 2016. DisponÃvel em: https://ieeexplore.ieee.org/abstract/document/7458186 Acesso em: 11 mar. 2025. DOI: https://doi.org/10.1109/TMC.2016.2557792
WANG, Zhu et al. Wi-Fi CSI-based behavior recognition: From signals and actions to activities. IEEE Communications Magazine, v. 56, n. 5, p. 109–115, 2018. DisponÃvel em: https://ieeexplore.ieee.org/abstract/document/8360860 Acesso em: 5 fev. 2025. DOI: https://doi.org/10.1109/MCOM.2018.1700144
License
Copyright (c) 2025 RECIMA21 - Revista CientÃfica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veÃculo de divulgação, seguindo os padrões nacionais e internacionais de publicação.Â