Large scale wireless indoor localization by clustering and Extreme Learning Machine

• Main Authors: Xiao, Wendong, Huang, Guang-Bin, Liu, Peidong, Soh, Wee-Seng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Wireless communication systems
• Online Access: https://hdl.handle.net/10356/102198; http://hdl.handle.net/10220/19849; http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6290497&url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel5%2F6269381%2F6289713%2F06290497.pdf%3Farnumber%3D6290497
• Institution: Nanyang Technological University

Due to the widespread deployment and low cost, WLAN has gained more attention for indoor localization recently. However, when we apply these WLAN based localization algorithms to large-scale environments, such as a wireless city, they may encounter the scalability problem due to the huge RSS database. The huge database may cause long response time for the terminal clients if the localization algorithm needs to search the database for the real time localization phase. In this paper, we propose a novel clustering based localization algorithm for large scale area by utilizing Nearest Neighbor (NN) rule and Extreme Learning Machine (ELM). The proposed algorithm has shown competitive advantage in terms of the real time localization efficiency as well as the localization accuracy.