基于改进 LightGBM 的室内指纹定位算法.

Aiming at the problems of long time and low positioning accuracy of indoor positioning algorithm, an indoor positioning algorithm based on improved LightGBM (light gradient boosting machine) algorithm was proposed. The algorithm first preprocessed the data in the fingerprint database, and removed outliers and outliers through KNN (K-nearest neighborhood ) algorithm to reduce environmental noise interference and improve data reliability. Next, the algorithm divided the sample set into training set and test set, and used LightGBM algorithm to model. At the same time, genetic algorithm was used to adjust the parameters in LightGBM algorithm, and the optimal parameters were found according to the fitness function to obtain the LightGBM + GA (genetic algorithm) coordinate prediction model. Finally, a prediction model was established according to the optimized parameters to realize coordinate prediction. The experimental results show that the algorithm improves the accuracy of WiFi positioning by 0. 1 m compared with XGBoost (extreme gradient boosting,XGBoost) algorithm and 0. 19 m compared with GBDT algorithm. In terms of positioning time, LightGBM + GA algorithm is 5. 10 s faster than GBDT (gradient boosting decision tree) algorithm and 5. 97 s faster than XGBoost algorithm, which has good practicability. [ABSTRACT FROM AUTHOR]

针对室内定位算法在定位时所用时间较长和定位精度较低的问题, 提出了-种基于改进 LightGBM (light gradient boosting machine) 算法的室内定位算法。 该算法首先针对指纹库中的数据进行预处理, 通过 KNN (K-nearest neighborhood) 算法 去除异常点和离群点, 降低环境噪声干扰, 提高数据可靠性。 接下来, 将样本集划分为训练集和测试集, 使用 LightGBM 算法 对进行建模。 同时, 使用遗传算法调整 LightGBM 算法中的参数, 并根据适应度函数寻找最优参数, 得到 LightGBM + GA (genetic algorithm) 坐标预测模型。 最后, 根据优化后的参数建立预测模型实现坐标预测。 实验结果表明, 该算法在 WiFi 定位的 精度上较与极限梯度提升 (extreme gradient boosting, XGBoost) 算法提高 0. 1 m, 相较于 GBDT (gradient boosting decision tree) 算 法提高 0. 19 m, 在定位时间上, LightGBM + GA 算法比 GBDT 算法快 5. 10 s, 比 XGBoost 算法快 5. 97 s, 具有较好的实用性. [ABSTRACT FROM AUTHOR]