Robust Indoor RF Signal LOS Classification: An Exploit of Modulation and Beamforming

作     者：Zhang, Tingwei Kalathas, Paris Wang, Guangxin Liu, Huaping 

作者机构：Oregon State Univ Sch Elect Engn & Comp Sci Corvallis OR 97331 USA 

出 版 物：《IEEE INTERNET OF THINGS JOURNAL》 (IEEE Internet Things J.)

年 卷 期：2025年第12卷第9期

页      面：12723-12734页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：IP networks Accuracy Machine learning Symbols Convolutional neural networks Real-time systems Channel impulse response Quadrature amplitude modulation Probability density function Phase shift keying Beamforming indoor positioning line-of-sight (LOS) classification signal processing 

摘      要：Indoor positioning systems (IPS) have gained significant attention in research due to the growing need for reliable location-based services in indoor settings where global navigation satellite systems are unreliable or unavailable. A major challenge in developing dependable IPS lies in accurately classifying line-of-sight (LOS) and non-LOS (NLOS) propagation conditions, which heavily influence positioning accuracy. Existing solutions often demand high-computational resources or are constrained by specific assumptions about the environment, limiting their broad applicability. This article proposes a novel mechanism that leverages the histogram characteristic of the signal phase in common signal modulation methods like quadrature amplitude modulation and phase shift keying to differentiate between LOS and NLOS conditions. We posit that the phase modulation forms a distinctive pattern in the histogram, serving as a reliable identifier for LOS/NLOS classification. Our approach s effectiveness is validated through a series of experiments, demonstrating up to 100% real-time accuracy in LOS/NLOS identifications, resilience to noise, extensive operational range, and free of computing-intensive machine learning models.