APPLICATION OF ARTIFICIAL INTELLIGENCE AND WI-FI SENSING FOR RESIDENTIAL SECURITY MANAGEMENT
Keywords:
Wi‑Fi sensing, LSTM Autoencoder, Intrusion Detection, Channel State Information (CSI)Abstract
The objectives of this research are: 1) to propose an indoor intrusion detection method for residential areas utilizing Wi-Fi Channel State Information (CSI) integrated with artificial intelligence and an adaptive decision threshold; 2) to investigate the model's robustness in cross-environment operations; 3) to determine the optimal installation position to minimize false alarms triggered by pets. This experimental study employed an ESP32 to collect CSI data and utilized an LSTM Autoencoder model, which excels in time-series data analysis. Its unsupervised learning capability significantly reduces the burden of data labeling. Performance was evaluated using Precision, Recall, F1-score, and AUC.
The results revealed that: 1) the proposed method outperformed the baseline models, achieving an F1-score of 0.970 and an AUC of 0.995 in the original environment; 2) the proposed method demonstrated high flexibility and robustness when operating across environments, achieving F1-scores of 0.933 in the living room and 0.923 in the bedroom, respectively; and 3) false alarms from pets were reduced to 2.41% at an installation height of 1.2 meters. These findings indicate the efficacy of the proposed method, highlighting its practical applicability as a reliable residential security system.
Downloads
References
Ergen, T., & Kozat, S. S. (2020). Unsupervised Anomaly Detection With LSTM Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 31(8), 3127–3141.
Espressif Systems. (2025). ESP32-C6-WROOM-1 & ESP32-C6-WROOM-1U Datasheet. Retrieved from https://documentation.espressif.com/esp32-c6-wroom-1_wroom-1u_datasheet_en.pdf
Gorrepati, S. R., Sahoo, A. K., & Udgata, S. K. (2023). WiFi Sensing Model for Intrusion Detection in Smart Home Environment. 2023 IEEE 11th Region 10 Humanitarian Technology Conference (R10-HTC), pp. 329–334. IEEE Gujarat Section. https://doi.org/10.1109/R10-HTC57504.2023.10461789
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
Homayouni, H., Ghosh, S., Ray, I., Gondalia, S., Duggan, J., & Kahn, M. G. (2020). An Autocorrelation-based LSTM-Autoencoder for Anomaly Detection on Time-Series Data. 2020 IEEE International Conference on Big Data (Big Data), pp. 5068–5077. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/BigData50022.2020.9378192
Huang, J., Liu, B., Miao, C., Lu, Y., Zheng, Q., Wu, Y., Liu, J., Su, L., & Chen, C. W. (2023). Phase Anti: An Anti-Interference WiFi-Based Activity Recognition System Using Interference-Independent Phase Component. IEEE Transactions on Mobile Computing, 22(5), 2938–2954.
Jun, K., Lee, D.-W., Lee, K., Lee, S., & Kim, M. S. (2020). Feature Extraction Using an RNN Autoencoder for Skeleton-Based Abnormal Gait Recognition. IEEE Access, 8(1), 19196–19207.
Khanmohammadi, F., & Azmi, R. (2024). Time-Series Anomaly Detection in Automated Vehicles Using D-CNN-LSTM Autoencoder. IEEE Transactions on Intelligent Transportation Systems, 25(8), 9296–9307.
Lee, S., Jin, H., Nengroo, S. H., Doh, Y., Lee, C., Heo, T., & Har, D. (2022). Smart Metering System Capable of Anomaly Detection by Bi-directional LSTM Autoencoder. 2022 IEEE International Conference on Consumer Electronics (ICCE). pp. 1–6. IEEE Consumer Technology Society. https://doi.org/10.1109/ICCE53296.2022.9730398
Lin, Y., Gao, Y., Li, B., & Dong, W. (2020). Revisiting Indoor Intrusion Detection With WiFi Signals: Do Not Panic Over a Pet! IEEE Internet of Things Journal, 7(10), 10437–10449.
Mahmoud, M., Kasem, M., Abdallah, A., & Kang, H. S. (2022). AE-LSTM: Autoencoder with LSTM-Based Intrusion Detection in IoT. 2022 International Telecommunications Conference (ITC-Egypt), pp. 1–6. Air Defense College (ADC). https://doi.org/10.1109/ITC-Egypt55520.2022.9855688
Mekruksavanich, S., & Jitpattanakul, A. (2023). A Lightweight Deep Residual Network for Recognizing Activities in Daily Living Using Channel State Information. 2023 IEEE 14th International Conference on Software Engineering and Service Science (ICSESS), pp. 171–174. Institute of Electrical and Electronics Engineers https://doi.org/10.1109/ICSESS58500.2023.10293055
Moghaddam, M. G., Shirehjini, A. A. N., & Shirmohammadi, S. (2022). A WiFi-based System for Recognizing Fine-grained Multiple-Subject Human Activities. 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pp. 1–6. IEEE Instrumentation and Measurement Society (IMS). https://doi.org/10.1109/I2MTC48687.2022.9806622
Preechakarnjanadit, D., & Taparugssanagorn, A. (2025). Real-Time, Non-Intrusive Fall Detection via Wi-Fi CSI: A Comparative Study of CNN-LSTM, GNN, and Transformer Models. AI, Computer Science and Robotics Technology. Intech Open Journals, 4(1), 1-43.
Ratnam, V. V., Chen, H., Chang, H.-H., Sehgal, A., & Zhang, J. (2024). Optimal Preprocessing of WiFi CSI for Sensing Applications. IEEE Transactions on Wireless Communications, 23(9), 10820–10833.
Wang, Xiangyu, Wang, X., Mao, S., Zhang, J., Periaswamy, S. C. G., & Patton, J. (2022). Adversarial Deep Learning for Indoor Localization With Channel State Information Tensors. IEEE Internet of Things Journal, 9(19), 18182–18194. h
Wang, Xingang, Wang, Y., & Wang, D. (2020). A Real-time CSI-based Passive Intrusion Detection Method. 2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking. pp. 1091–1098. IEEE Computer Society. https://doi.org/10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00163
Wei, Y., Jang-Jaccard, J., Xu, W., Sabrina, F., Camtepe, S., & Boulic, M. (2023). LSTM-Autoencoder-Based Anomaly Detection for Indoor Air Quality Time-Series Data. IEEE Sensors Journal, 23(4), 3787–3800.
Yong, B. X., & Brintrup, A. (2022). Do Autoencoders Need a Bottleneck for Anomaly Detection? IEEE Access, 10(1), 78455–78471.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 UMT-Poly Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
ประกาศลิขสิทธิ์
เนื้อหาและข้อมูลในบทความที่ลงตีพิมพ์ในวารสารวิชาการมหาวิทยาลัยการจัดการและเทคโนโลยีอีสเทิร์น ถือเป็นข้อคิดเห็นและความรับผิดชอบของผู้เขียนบทความโดยตรง ซึ่งกองบรรณาธิการวารสารไม่จำเป็นต้องเห็นด้วยหรือร่วมรับผิดชอบใด ๆ
บทความ ข้อมูล เนื้อหาหรือรูปภาพ ฯลฯ ที่ได้รับการตีพิมพ์ในวารสารวิชาการมหาวิทยาลัยการจัดการและเทคโนโลยีอีสเทิร์น ถือเป็นลิขสิทธิ์ของวารสารวิชาการมหาวิทยาลัยการจัดการและเทคโนโลยีอีสเทิร์น หากบุคคลหรือหน่วยงานใดต้องการนำข้อมูลทั้งหมดหรือบางส่วนไปเผยแพร่ต่อหรือเพื่อกระทำการใด ๆ จะต้องได้รับอนุญาตเป็นลายลักษณ์อักษรจากวารสารวิชาการมหาวิทยาลัยการจัดการและเทคโนโลยีอีสเทิร์นก่อนเท่านั้น
