Indoor localization systems with higher precision and integrity are being highly demanded because of their numerous applications in superstores, smart homes, smart cities, elderly care, and disaster management. Although there are many technologies for indoor positioning e.g., Wireless Fidelity (Wi-Fi), Bluetooth Low Energy (BLE), and Radio-Frequency Identification (RFID), the high precision localization is still challenging because of the multipath effect and non-line of sight propagation of radio waves in complex indoor environment. This research proposes an explainable indoor localization (EIL) method for higher precision and integrity in IPS. The proposed localization method considered received signal strength indicator (RSSI) from BLE devices for predicting their precise locations. A recursive continuous Wavelet transform (R-CWT) method is proposed to extract discriminative features from the beacon signals for efficient localization. The extracted features are then fed to the extreme gradient boosting machine for the accurate classification of indoor positions. Moreover, to ensure integrity in indoor position classification, the Shapley additive explanations (SHAP) method is introduced to interpret the results obtained from the gradient boosting machine. The proposed method (EIL) precisely localize BLE devices within 1.5 m in a superstore environment with an accuracy of 98.04% which is much higher than the reported accuracies in existing studies.

由于在超市、智能家居、智慧城市、养老和灾害管理等领域的大量应用，对精度和完整性更高的室内定位系统的需求越来越大。尽管室内定位技术有多种，例如无线保真（Wi-Fi）、低功耗蓝牙（BLE）和射频识别（RFID）等，但由于多径效应和非线性，高精度定位仍然具有挑战性无线电波在复杂室内环境中的视线传播。本研究提出了一种可解释的室内定位 (EIL) 方法，以提高 IPS 中的精度和完整性。所提出的定位方法考虑了来自 BLE 设备的接收信号强度指示器 (RSSI)，以预测它们的精确位置。提出了一种递归连续小波变换 (R-CWT) 方法来从信标信号中提取鉴别特征以进行有效定位。然后将提取的特征馈送到极端梯度增强机，以对室内位置进行准确分类。此外，为了确保室内位置分类的完整性，引入了 Shapley 附加解释 (SHAP) 方法来解释从梯度提升机获得的结果。所提出的方法 (EIL) 在超市环境中精确定位 1.5 m 以内的 BLE 设备，准确率为 98.04%，远高于现有研究报告的准确度。然后将提取的特征馈送到极端梯度增强机，以对室内位置进行准确分类。此外，为了确保室内位置分类的完整性，引入了 Shapley 附加解释 (SHAP) 方法来解释从梯度提升机获得的结果。所提出的方法 (EIL) 在超市环境中精确定位 1.5 m 以内的 BLE 设备，准确率为 98.04%，远高于现有研究报告的准确度。然后将提取的特征馈送到极端梯度增强机，以对室内位置进行准确分类。此外，为了确保室内位置分类的完整性，引入了 Shapley 附加解释 (SHAP) 方法来解释从梯度提升机获得的结果。所提出的方法 (EIL) 在超市环境中精确定位 1.5 m 以内的 BLE 设备，准确率为 98.04%，远高于现有研究报告的准确度。