In this paper, we investigate machine learning approaches addressing the problem of geolocation. First, we review some classical learning methods to build a radio map. These methods are split in two categories, which we refer to as likelihood-based methods and fingerprinting methods. Then, we provide a novel geolocation approach in each of these two categories. The first proposed technique relies on a semi-parametric Nadaraya–Watson (NW) estimator of the likelihood, followed by a maximum a posteriori (MAP) estimator of the object’s position. The second technique consists in learning a proper metric on the dataset, constructed by means of a Gradient boosting regressor: a k-nearest neighbor algorithm is then used to estimate the position. The proposed methods are compared on two data sets originated from Sigfox network, and an indoor dataset performed in a three-story building. Experiments show the interest of the proposed methods, both in terms of location estimation performance, and ability to build radio maps.

在本文中，我们研究了解决地理位置问题的机器学习方法。首先，我们回顾一些经典的学习方法来构建无线电地图。这些方法分为两类，我们称为基于似然的方法和指纹识别方法。然后，我们针对这两个类别分别提供一种新颖的地理定位方法。首先提出的技术依赖于似然的半参数Nadaraya-Watson（NW）估计器，然后是对象位置的最大后验（MAP）估计器。第二种技术是在数据集上学习适当的度量，该度量是通过梯度提升回归器构造的：然后使用k最近邻算法来估计位置。将该方法与源自Sigfox网络的两个数据集进行了比较，以及在三层建筑中进行的室内数据集。实验表明，无论是在位置估计性能还是在构建无线电地图方面，所提出的方法都具有吸引力。