Sasaki Ai-Ichiro
Department of Electronic Engineering and Computer Science, Kindai University, Higashi-Hiroshima 739-2116, Japan.
Sensors (Basel). 2022 Mar 14;22(6):2240. doi: 10.3390/s22062240.
Recently, indoor localization has become an active area of research. Although there are various approaches to indoor localization, methods that utilize artificially generated magnetic fields from a target device are considered to be the best in terms of localization accuracy under non-line-of-sight conditions. In magnetic field-based localization, the target position must be calculated based on the magnetic field information detected by multiple sensors. The calculation process is equivalent to solving a nonlinear inverse problem. Recently, a machine-learning approach has been proposed to solve the inverse problem. Reportedly, adopting the -nearest neighbor algorithm (-NN) enabled the machine-learning approach to achieve fairly good performance in terms of both localization accuracy and computational speed. Moreover, it has been suggested that the localization accuracy can be further improved by adopting artificial neural networks (ANNs) instead of -NN. However, the effectiveness of ANNs has not yet been demonstrated. In this study, we thoroughly investigated the effectiveness of ANNs for solving the inverse problem of magnetic field-based localization in comparison with -NN. We demonstrate that despite taking longer to train, ANNs are superior to -NN in terms of localization accuracy. The -NN is still valid for predicting fairly accurate target positions within limited training times.
近年来，室内定位已成为一个活跃的研究领域。尽管室内定位有多种方法，但在非视距条件下，利用目标设备人工产生的磁场的方法在定位精度方面被认为是最佳的。在基于磁场的定位中，必须根据多个传感器检测到的磁场信息来计算目标位置。计算过程等同于求解一个非线性逆问题。最近，有人提出了一种机器学习方法来解决这个逆问题。据报道，采用k近邻算法（k-NN）能使机器学习方法在定位精度和计算速度方面都取得相当不错的性能。此外，有人提出采用人工神经网络（ANN）代替k-NN可以进一步提高定位精度。然而，人工神经网络的有效性尚未得到证实。在本研究中，我们全面研究了与k-NN相比，人工神经网络解决基于磁场定位逆问题的有效性。我们证明，尽管训练时间较长，但人工神经网络在定位精度方面优于k-NN。在有限的训练时间内，k-NN对于预测相当准确的目标位置仍然有效。
