TY - GEN
T1 - Extreme learning machine with dead zone and its application to WiFi based indoor positioning
AU - Lu, Xiaoxuan
AU - Yu, Chengpu
AU - Zou, Han
AU - Jiang, Hao
AU - Xie, Lihua
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014
Y1 - 2014
N2 - Extreme learning machine (ELM) as an emergent technology has shown its good performance in regression applications as well as in large dataset classification applications. It has been broadly embedded in many applications due to its fast speed of computation and accuracy. How to make good use of machine learning techniques in Indoor Positioning System (IPS) is a hot research topic in recent years. Some existing IPSs have already adopted ELM, but it suffers from signal variation and environmental dynamics in indoor settings. In this paper, extreme learning machine with dead zone (DZ-ELM) is proposed to address this problem. The consistency of this approach should be applied is studied. Simulations are also conducted to compare the performance of DZ-ELM and ELM. Lastly, real-world experimental results show that the proposed algorithm can not only provide higher accuracy but also improve the repeatability of IPSs.
AB - Extreme learning machine (ELM) as an emergent technology has shown its good performance in regression applications as well as in large dataset classification applications. It has been broadly embedded in many applications due to its fast speed of computation and accuracy. How to make good use of machine learning techniques in Indoor Positioning System (IPS) is a hot research topic in recent years. Some existing IPSs have already adopted ELM, but it suffers from signal variation and environmental dynamics in indoor settings. In this paper, extreme learning machine with dead zone (DZ-ELM) is proposed to address this problem. The consistency of this approach should be applied is studied. Simulations are also conducted to compare the performance of DZ-ELM and ELM. Lastly, real-world experimental results show that the proposed algorithm can not only provide higher accuracy but also improve the repeatability of IPSs.
UR - http://www.scopus.com/inward/record.url?scp=84927737130&partnerID=8YFLogxK
U2 - 10.1109/ICARCV.2014.7064376
DO - 10.1109/ICARCV.2014.7064376
M3 - Conference contribution
AN - SCOPUS:84927737130
T3 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
SP - 625
EP - 630
BT - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
Y2 - 10 December 2014 through 12 December 2014
ER -