Low-Cost Wi-Fi CSI Human Presence Detection in Severe NLOS via Automated Cross-Modal Labeling
Journal of Naval Sciences and Engineering · 11.11.2026 · (Advanced Online Publication) · 505-524
DOI: 10.56850/jnse.2056991 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Naval Sciences and Engineering, online erschienen am 11.11.2026. Verfasst von Tolga Nizamoğlu und 1 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Galatasaray University Research Foundation.
Abstract (Originalsprache)
Device-free human presence detection using Wi-Fi Channel State Information (CSI) provides a passive, non-intrusive alternative to traditional indoor surveillance. However, real-world deployment faces severe challenges due to expensive specialized hardware, labor-intensive manual data annotation, and signal attenuation in Non-Line-of-Sight (NLoS) environments. This study presents a low-cost, automated Wi-Fi sensing framework using ESP32-C6 microcontrollers paired with a YOLO-based cross-modal computer vision labeling pipeline. To evaluate feature extraction and accuracy trade-offs, a comprehensive suite of algorithms was benchmarked, comprising classical machine learning baselines (Random Forest, Support Vector Machines, Naïve Bayes, and K-Nearest Neighbors) and deep learning architectures (1D-CNN, 2D-CNN, and an MLP-LSTM hybrid network). The system was evaluated under both Line-of-Sight (LoS) and challenging NLoS conditions through two 18 cm thick reinforced concrete shear walls. In LoS scenarios, Random Forest achieved an offline accuracy of 96.33% using raw, uncompressed CSI data. In severe NLoS conditions, 1D-CNN achieved a validation accuracy of 99.22%, while MLP-LSTM provided superior prediction stability for real-time edge deployment on a Raspberry Pi 5 without GPU acceleration. Furthermore, a leakage-aware temporal split analysis revealed significant performance degradation on chronologically later test data, highlighting the critical impact of temporal non-stationarity in CSI signals. This work demonstrates the feasibility of ultra-low-cost, automated through-wall sensing for indoor security and tactical monitoring applications.
Förderung
- Galatasaray University Research Foundation
Zitieren
APA
Nizamoğlu, T., & Pınarer, O. (2026). Low-Cost Wi-Fi CSI Human Presence Detection in Severe NLOS via Automated Cross-Modal Labeling. Journal of Naval Sciences and Engineering, 505-524. https://doi.org/10.56850/jnse.2056991
Vancouver
Nizamoğlu T, Pınarer O. Low-Cost Wi-Fi CSI Human Presence Detection in Severe NLOS via Automated Cross-Modal Labeling. Journal of Naval Sciences and Engineering. 2026:505-524. doi:10.56850/jnse.2056991
BibTeX
@article{Nizamolu2026,
author = {Nizamoğlu, Tolga and Pınarer, Ozgun},
title = {Low-Cost Wi-Fi CSI Human Presence Detection in Severe NLOS via Automated Cross-Modal Labeling},
journal = {Journal of Naval Sciences and Engineering},
year = {2026},
number = {Advanced Online Publication},
pages = {505--524},
doi = {10.56850/jnse.2056991}
}
EUVIMED