Trapped human detection in search and rescue (SAR) scenarios poses a significant challenge in pervasive computing. This study addresses this issue by leveraging machine learning techniques, given their high accuracy. However, accurate identification of trapped individuals is hindered by the curse of dimensionality and noisy data. Particularly in non-line-of-sight (NLOS) situations during catastrophic events, the curse of dimensionality may lead to blind spots due to noise and uncorrelated values in detections. This research focuses on harmonizing information through wireless communication and identifying individuals in NLOS scenarios using ultra-wideband (UWB) radar signals. Employing independent component analysis (ICA) for feature extraction, the study evaluates classification performance using ensemble algorithms on both static and dynamic datasets. The experimental results demonstrate categorization accuracies of 88.37% for static data and 87.20% for dynamic data, highlighting the effectiveness of the proposed approach. Finally, this work can help scientists and engineers make instant decisions during SAR operations.

翻译：在搜索与救援（SAR）场景中，被困人员的检测是普适计算领域面临的一项重大挑战。本研究利用机器学习技术的高精度特性来解决这一问题。然而，维度灾难和噪声数据阻碍了对被困个体的准确识别。特别是在灾难事件中的非视距（NLOS）情况下，维度灾难可能因检测中的噪声和不相关值而导致盲区。本研究聚焦于通过无线通信进行信息协调，并利用超宽带（UWB）雷达信号识别NLOS场景中的个体。研究采用独立成分分析（ICA）进行特征提取，并在静态与动态数据集上使用集成算法评估分类性能。实验结果表明，静态数据的分类准确率达88.37%，动态数据为87.20%，充分证明了所提出方法的有效性。最终，本工作可帮助科学家与工程师在SAR行动中做出即时决策。