TY - GEN
T1 - A Novel Classification Method Based on Adaboost for Electromagnetic Emission Characteristics
AU - Nie, Jing
AU - Yang, Shunchuan
AU - Ren, Qiang
AU - Su, Donglin
N1 - Publisher Copyright:
© 2018 ACES.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - Abundant characteristics information of equipment or systems could be obtained from electromagnetic emission data. In this paper, those characteristics of electromagnetic emission are analyzed via the adaptive boosting (Adaboost) algorithm. Based on the 'basic emission waveform theory', four types of basic fundamental elements, characteristics-harmonic, narrowband and envelope-of complex emission in frequency domain, could be extracted. For taking weights combination patterns to effectively improve the classification performance of a single classifier, high classification accuracy could be achieved by Adaboost algorithm. In our study, 100% precision classification accuracy of three types of characteristics could be obtained using Adaboost with 13 decision tree weak-classifiers. Compared with other classification methods, the Adaboost algorithm used in this paper is the most accurate. The outcomes of this research can be used as a guide in the electromagnetic compatibility design and rectification.
AB - Abundant characteristics information of equipment or systems could be obtained from electromagnetic emission data. In this paper, those characteristics of electromagnetic emission are analyzed via the adaptive boosting (Adaboost) algorithm. Based on the 'basic emission waveform theory', four types of basic fundamental elements, characteristics-harmonic, narrowband and envelope-of complex emission in frequency domain, could be extracted. For taking weights combination patterns to effectively improve the classification performance of a single classifier, high classification accuracy could be achieved by Adaboost algorithm. In our study, 100% precision classification accuracy of three types of characteristics could be obtained using Adaboost with 13 decision tree weak-classifiers. Compared with other classification methods, the Adaboost algorithm used in this paper is the most accurate. The outcomes of this research can be used as a guide in the electromagnetic compatibility design and rectification.
KW - Adaboost
KW - classification
KW - electromagnetic emission characteristics
UR - https://www.scopus.com/pages/publications/85063777201
U2 - 10.23919/ACESS.2018.8669248
DO - 10.23919/ACESS.2018.8669248
M3 - 会议稿件
AN - SCOPUS:85063777201
T3 - 2018 International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2018
BT - 2018 International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2018
Y2 - 29 July 2018 through 1 August 2018
ER -