Semi-supervised learning for mobile robot localization using wireless signal strengths
Authors:
- 1 September 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
This paper proposes a new semi-supervised machine learning for localization. It improves localization efficiency by reducing efforts needed to calibrate labeled training data by using unlabeled data, where training data come from received signal strengths of a wireless communication link. The main idea is to treat training data as spatio-temporal data. We compare the proposed algorithm with the state-of-art semi-supervised learning methods. The algorithms are evaluated for estimating the unknown location of a smartphone mobile robot. The experimental results show that the developed learning algorithm is the most accurate and robust to the varying amount of training data, without sacrificing the computation speed.Keywords
This publication has 17 references indexed in Scilit:
- Target Localization in Wireless Sensor Networks Using Online Semi-Supervised Support Vector RegressionSensors, 2015
- Distributed estimation using online semi‐supervised particle filter for mobile sensor networksIET Control Theory & Applications, 2015
- Online estimation using semi-supervised least square SVR2014
- Fingerprint-based location tracking with Hodrick-Prescott filtering2014
- Combining classification and regression for WiFi localization of heterogeneous robot teams in unknown environments2012
- Laplacian Embedded Regression for Scalable Manifold RegularizationIEEE Transactions on Neural Networks and Learning Systems, 2012
- Tracking Mobile Users in Wireless Networks via Semi-Supervised ColocalizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Semi-supervised Laplacian regularized least squares algorithm for localization in wireless sensor networksComputer Networks, 2011
- Semi-Supervised Learning on Riemannian ManifoldsMachine Learning, 2004
- On Adjusting the Hodrick-Prescott Filter for the Frequency of ObservationsReview of Economics and Statistics, 2002