TY - GEN
T1 - Modeling IoT multi-sensory system
T2 - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
AU - Yang, Chan Yun
AU - Jan, Gene Eu
AU - Samani, Hooman
AU - Yu, Liyu
N1 - Funding Information:
ACKNOWLEDGMENT The corresponding author gratefully acknowledges the financial support of the Ministry of Science and Technology of Taiwan through its grants MOST104-2221-E-305-003 and MOST105-2221-E-305-003.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/27
Y1 - 2017/11/27
N2 - As the emerging development of IoT circumstance, on-line detections or observations of a system states become easier by facilitating its corresponding multi-sensory responses, and thus the description of a system behavior becomes clearer. Abundant on-line multi-channel information from the embedded sensors would be advantageous to the understanding of the system. Though having the information, it is still uneasy to thoroughly assess the integrity behavior of the system without a eligible system identification method. In the study, through a recurrent function approximation by an integrated multiregression of support vector regression (SVR), the identification has been developed and represented as a family of characteristic functions. With the set of characteristic functions, a design of IoT based live interaction of adaptive control or human-machine system could hereafter followed up. The study constructed primarily the SVR based framework of the recurrent multisensor system identification. There are two major contributions of the study: First, an IoT aspect for the discovery of the multiple regression extended from an underlying SVR, second, a technical overcoming in the realization of the recurrent framework of SVR.
AB - As the emerging development of IoT circumstance, on-line detections or observations of a system states become easier by facilitating its corresponding multi-sensory responses, and thus the description of a system behavior becomes clearer. Abundant on-line multi-channel information from the embedded sensors would be advantageous to the understanding of the system. Though having the information, it is still uneasy to thoroughly assess the integrity behavior of the system without a eligible system identification method. In the study, through a recurrent function approximation by an integrated multiregression of support vector regression (SVR), the identification has been developed and represented as a family of characteristic functions. With the set of characteristic functions, a design of IoT based live interaction of adaptive control or human-machine system could hereafter followed up. The study constructed primarily the SVR based framework of the recurrent multisensor system identification. There are two major contributions of the study: First, an IoT aspect for the discovery of the multiple regression extended from an underlying SVR, second, a technical overcoming in the realization of the recurrent framework of SVR.
KW - Multi-sensory system
KW - Multiple regression
KW - Recurrent system identification
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85044236636&partnerID=8YFLogxK
U2 - 10.1109/SMC.2017.8122687
DO - 10.1109/SMC.2017.8122687
M3 - Conference contribution
AN - SCOPUS:85044236636
T3 - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
SP - 689
EP - 694
BT - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
PB - Institute of Electrical and Electronics Engineers (IEEE)
Y2 - 5 October 2017 through 8 October 2017
ER -