Department of Information, Communications, and Electronics Engineering, The Catholic University of Korea, Bucheon-si 14662, Korea.
Center for Distance and Virtual Learning, University of Hyderabad, Hyderabad 500046, India.
Sensors (Basel). 2022 Sep 2;22(17):6629. doi: 10.3390/s22176629.
Location-based indoor applications with high quality of services require a reliable, accurate, and low-cost position prediction for target device(s). The widespread availability of WiFi received signal strength indicator (RSSI) makes it a suitable candidate for indoor localization. However, traditional WiFi RSSI fingerprinting schemes perform poorly due to dynamic indoor mobile channel conditions including multipath fading, non-line-of-sight path loss, and so forth. Recently, machine learning (ML) or deep learning (DL)-based fingerprinting schemes are often used as an alternative, overcoming such issues. This paper presents an extreme gradient boosting-based ML indoor localization scheme, simply termed as XGBLoc, that accurately classifies (or detects) the positions of mobile devices in multi-floor multi-building indoor environments. XGBLoc not only effectively reduces the RSSI dataset dimensionality but trains itself using structured synthetic labels (also termed as relational labels), rather than conventional independent labels, that classify such complex and hierarchical indoor environments well. We numerically evaluate the proposed scheme on the publicly available datasets and prove its superiority over existing ML or DL-based schemes in terms of classification and regression performance.
基于位置的室内应用需要为目标设备提供可靠、准确且低成本的位置预测。广泛可用的 Wi-Fi 接收信号强度指示 (RSSI) 使其成为室内定位的合适候选者。然而，由于包括多径衰落、非视距路径损耗等在内的动态室内移动信道条件，传统的 Wi-Fi RSSI 指纹方案表现不佳。最近，基于机器学习 (ML) 或深度学习 (DL) 的指纹方案常被用作替代方案，以克服这些问题。本文提出了一种基于极端梯度提升 (XGBoost) 的 ML 室内定位方案，简称 XGBLoc，可在多楼层多建筑物的室内环境中准确地对移动设备的位置进行分类 (或检测)。XGBLoc 不仅有效地降低了 RSSI 数据集的维数，而且还使用结构化的合成标签 (也称为关系标签) 进行训练，而不是传统的独立标签，从而很好地对这种复杂和分层的室内环境进行分类。我们在公开可用的数据集上对所提出的方案进行了数值评估，并证明了其在分类和回归性能方面优于现有的基于 ML 或 DL 的方案。
