赖朝安,龙漂.基于高斯过程回归和WiFi指纹的室内定位方法[J].电子测量与仪器学报,2021,35(2):186-193 |
基于高斯过程回归和WiFi指纹的室内定位方法 |
Indoor localization method based on gaussian process regression and WiFi fingerprint |
|
DOI: |
中文关键词: WiFi指纹定位 高斯过程回归 误差修正模型 定位精度 |
英文关键词:WiFi fingerprint positioning Gaussian process regression error correction model positioning accuracy |
基金项目:广东省自然科学基金(2018A030313079)、广东省软科学项目(2019A101002006)资助 |
|
|
摘要点击次数: 1121 |
全文下载次数: 6 |
中文摘要: |
为了提高室内定位的准确性,同时降低现场勘测的成本,提出了基于高斯过程回归和WiFi指纹的室内定位方法。首先,在离线阶段,采用高斯过程回归模型(GPR)来扩展WiFi指纹数据库,即通过对不同的GPR核函数进行训练,得到最佳的GPR预测模型,进而利用有限的已知数据预测未知区域的信号强度(RSS)。然后,在指纹匹配阶段中,根据离线阶段得到的RSS数据库,分别使用加权最邻近算法(WKNN)、最大似然估计算法(MLE)、和多层神经网络(MLP)对未知点进行定位。其中,为进一步提高定位精度,提出了误差修正模型,并应用到不同的定位算法中。实验结果表明,kRBF+kMatern+kRQ的核函数组合是最佳的GPR预测模型,平均RSS估计误差为459 dBm;与原始勘测地图实现的定位结果比较,基于GPR的定位算法具有更高的定位精度,其中GPR WKNN算法的定位精度最高,其80%的定位误差为132 m,表明了使用GPR扩展地图预测位置的准确性和有效性,同时其能满足商品推荐与物资动态管理、应急救援、智慧停车、传染病患跟踪等新型应用场景对定位精度的高要求。 |
英文摘要: |
In order to improve the accuracy of indoor positioning and reduce the cost of on site investigation, an indoor localization method based on Gaussian process regression and WiFi fingerprint is proposed. Firstly, during the offline phase, Gaussian process regression model (GPR) is used to expand the WiFi fingerprint database. In other words, by training different GPR kernel functions, the best GPR prediction model is obtained, and then the signal strength (RSS) of unknown region is predicted by using the limited known data. Then in the fingerprint matching stage, the weighted nearest neighbor algorithm (WKNN), maximum likelihood estimation (MLE) and multi layer perceptron (MLP) methods are used to locate the unknown points according to the RSS database obtained in the offline phase. Specifically, in order to further improve the positioning accuracy, an error correction model is proposed and applied to the above different positioning algorithms. The experimental results show that the kernel function combination of kRBF+kMatern+kRQ is the best GPR prediction model, and the average RSS estimation error is 459 dBm. In addition, compared with the results which is obtained by using the original survey map, the location algorithm based on GPR has higher positioning accuracy. Among them, the GPR WKNN algorithm has the highest positioning accuracy, with 80% positioning error of 132 m. The above results indicate that the method of using GPR to expand the map and further predict the location is accurate and effective, and can meet the high requirements of positioning accuracy in new application scenarios such as commodity recommendation and material dynamic management, emergency rescue, intelligent parking, infectious disease tracking and so on. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|