HIWL: An Unsupervised Learning Algorithm for Indoor Wireless Localization

Author

Li Li ; Wang Yang ; Guojun Wang

Author_Institution

Sch. of Inf. & Eng., Central South Univ., Changsha, China

fYear

2013

fDate

16-18 July 2013

Firstpage

1747

Lastpage

1753

Abstract

An advanced unsupervised learning algorithm for a precise measurement of the local position of an indoor mobile target is proposed. In this work, the indoor wireless localization is addressed with HIWL, an unsupervised learning algorithm based on HMM. The locations of reference nodes and site survey are no longer needed in this algorithm. A sample data process with K-means which helps us produce discrete observation sequences is introduced. Also, a family of equations to compute effective initial parameters of HMM is presented. Experiments show that HIWL can achieve better localization accuracy.

Keywords

hidden Markov models; learning (artificial intelligence); mobile computing; position measurement; HIWL; HMM; K-means; discrete observation sequences; indoor mobile target; indoor wireless localization; local position measurement; sample data process; unsupervised learning algorithm; Accuracy; Hidden Markov models; Mobile handsets; Unsupervised learning; Vectors; Wireless communication; Wireless sensor networks; HMM; unsupervised learning; wireless localization;

fLanguage

English

Publisher

ieee

Conference_Titel

Trust, Security and Privacy in Computing and Communications (TrustCom), 2013 12th IEEE International Conference on

Conference_Location

Melbourne, VIC

Type

conf

DOI

10.1109/TrustCom.2013.217

Filename

6681046