Evaluation of the real-time indoor location and motion direction estimation system applying DNN to RSSI Fingerprints of BLE beacons
Evaluation of the real-time indoor location and motion direction estimation system applying DNN to RSSI Fingerprints of BLE beacons
复制标题
将 DNN 应用于 BLE 信标 RSSI 指纹的实时室内位置和运动方向估计系统的评估
DOI：
10.1109/gcce50665.2020.9291986
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
T. Kitagawa
中科院分区：
文献类型：
--
作者：
Kaito Echizenya;K. Kondo;T. Kitagawa
我们研究了一种同时检测在室内行走的行人的位置和行进方向的方法。来自多个低功耗蓝牙信标的接收信号强度指示器的多个时间实例，在行人携带的智能手机上检测到，并在八个方向中的任何一个方向移动，用于训练深度神经网络来估计该智能手机的位置和运动方向。我们比较了 RSSI 插值和未插值时的估计精度。没有插值的位置估计精度下降了 40.5%，移动方向估计精度下降了 26.9%，表明需要某种形式的插值。
We investigated a method to detect the position and direction of travel of a pedestrian walking indoors simultaneously. Multiple time instances of Received Signal Strength Indicator from multiple Bluetooth Low Energy beacons, detected on smartphones carried by pedestrians moving in any of eight directions, are used to train a Deep Neural Network to estimate the location and direction of motion of this smartphone. We compare the estimation accuracy when the RSSIs were interpolated, and when they were not. The position estimation accuracy without interpolation decreased by 40.5% and the moving direction estimation accuracy decreased by 26.9%, suggesting some form of interpolation is required.