A Fingerprint Method for Indoor Localization Using Autoencoder Based Deep Extreme Learning Machine
A Fingerprint Method for Indoor Localization Using Autoencoder Based Deep Extreme Learning Machine
复制标题
DOI：
10.1109/lsens.2017.2787651
复制
发表时间：
2018-03-01
影响因子：
2.8
通讯作者：
Ghorashi, Seyed Ali
中科院分区：
文献类型：
--
作者：
Khatab, Zahra Ezzati;Hajihoseini, Amirhosein;Ghorashi, Seyed Ali
近年来，随着室内环境中基于位置服务的需求不断增长，基于指纹的室内定位引起了广泛的研究兴趣。指纹定位方法基于无线传感器网络中接收信号强度 (RSS) 的工作原理。此方法使用来自可用发射器传感器的 RSS 测量值，这些测量值由带有内部传感器的智能手机收集。在本文中，我们提出了一种新颖的算法，该算法利用深度学习、极限学习机和自动编码器的高级提取特征来提高特征提取和分类中的定位性能。此外，由于指纹数据库需要更新（由于环境的动态性质），我们还增加了训练数据的数量，以逐步提高定位性能。仿真结果表明，该方法通过使用自动编码器提取的高级特征并增加训练数据的数量，显着提高了定位性能。
By growing the demand for location based services in indoor environments in recent years, fingerprint based indoor localization has attracted much research interest. The fingerprint localization method works based on received signal strength (RSS) in wireless sensor networks. This method uses RSS measurements from available transmitter sensors, which are collected by a smart phone with internal sensors. In this article, we propose a novel algorithm that takes advantage of deep learning, extreme learning machines, and high level extracted features by autoencoder to improve the localization performance in the feature extraction and the classification. Furthermore, as the fingerprint database needs to be updated (due to the dynamic nature of environment), we also increase the number of training data, in order to improve the localization performance, gradually. Simulation results indicate that the proposed method provides a significant improvement in localization performance by using high level extracted features by autoencoder and increasing the number of training data.