Uzunidis, D.; Kasnesis, P.; Patrikakis, C.Z.; Mitilineos, S.A. Machine Learning-Based Human Life Detection behind Walls Exploiting a UWB Radar Sensor. Preprints2024, 2024030271. https://doi.org/10.20944/preprints202403.0271.v1
APA Style
Uzunidis, D., Kasnesis, P., Patrikakis, C.Z., & Mitilineos, S.A. (2024). Machine Learning-Based Human Life Detection behind Walls Exploiting a UWB Radar Sensor. Preprints. https://doi.org/10.20944/preprints202403.0271.v1
Chicago/Turabian Style
Uzunidis, D., Charalampos Z. Patrikakis and Stelios A. Mitilineos. 2024 "Machine Learning-Based Human Life Detection behind Walls Exploiting a UWB Radar Sensor" Preprints. https://doi.org/10.20944/preprints202403.0271.v1
Abstract
The existence of low-cost and accurate tools that can equip the First Responders (FRs) to detect trapped victims and provide insights about their health condition in the aftermath of a disaster, is imperative. To address the problem of detecting trapped victims behind walls or debris, we have developed a tool that exploits an Ultra-Wide Band (UWB) radar sensor for data collection and Machine Learning (ML) algorithms for data analysis. To evaluate the efficacy of our approach, we collected data from nine humans, both in standing and lying down positions. Next, we applied various ML algorithms to the collected dataset for two discrete sub-tasks that are of interest from an FR’s perspective. The first task is the detection of the victim’s presence, where the algorithms attained more than 95% accuracy and F1-Score. The second task is the estimation of the distance between the radar sensor and the victim, where the tool showed an average error of less than 40 cm.
Keywords
human detection; First Responders; Machine Learning; aftermath crisis management; search and rescue; ultra-wideband radar sensors
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.