Wireless Fingerprinting Uncertainty Prediction Based on Machine Learning
Wireless Fingerprinting Uncertainty Prediction Based on Machine Learning
复制标题
基于机器学习的无线指纹不确定性预测
DOI：
10.3390/s19020324
复制
发表时间：
2019-01-02
期刊：
影响因子：
3.9
通讯作者：
El-Sheimy, Naser
中科院分区：
文献类型：
--
作者：
Li, You;Gao, Zhouzheng;El-Sheimy, Naser
虽然无线指纹识别技术已被广泛应用于室内定位，但其性能难以量化。因此，当无线指纹识别解决方案被用作多传感器集成中的位置更新时，准确地设置它们的权重是具有挑战性的。为了缓解这一问题，利用机器学习(ML)技术，通过给定接收信号强度(RSS)的测量来预测无线指纹定位的不确定性。使用了两种最大似然方法，包括基于人工神经网络(ANN)的方法和基于高斯分布(GD)的方法。对预测的位置不确定度进行评估，并将其用于航位推算/无线指纹组合定位扩展卡尔曼滤波(EKF)中的测量噪声设置。室内步行实验结果表明，利用人工神经网络预测无线指纹识别的不确定性是可行的，在综合定位EKF中自适应设置测量噪声是有效的。
Although wireless fingerprinting has been well researched and widely used for indoor localization, its performance is difficult to quantify. Therefore, when wireless fingerprinting solutions are used as location updates in multi-sensor integration, it is challenging to set their weight accurately. To alleviate this issue, this paper focuses on predicting wireless fingerprinting location uncertainty by given received signal strength (RSS) measurements through the use of machine learning (ML). Two ML methods are used, including an artificial neural network (ANN)-based approach and a Gaussian distribution (GD)-based method. The predicted location uncertainty is evaluated and further used to set the measurement noises in the dead-reckoning/wireless fingerprinting integrated localization extended Kalman filter (EKF). Indoor walking test results indicated the possibility of predicting the wireless fingerprinting uncertainty through ANN the effectiveness of setting measurement noises adaptively in the integrated localization EKF.