TY - GEN
T1 - Quantification of pain degree by frequency features of single-chanelled EEG
AU - Kagita, Junichiro
AU - Mitsukura, Yasue
N1 - Funding Information:
This work was supported by MEXT KAKENHI (SCIENTIFIC RESEARCH S) Grant No. YYK7S01.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/1
Y1 - 2018/6/1
N2 - The final aim of this paper is to classify pain degree by only using Electroencephalogram (EEG) measured with single-channel. In clinical care, pain degree is needed for choosing and evaluating treatments, and it is important for clinicians to quantify pain degree as objectively as possible. Pain rating scales such as the Visual Analogue Scales (VAS) are usually used to quantify pain degree, which is only capable of subjective values due to self-report. From that, a method to quantify pain degree objectively has great importance. In this paper, we propose the possibility of quantifying pain degree by only using EEG measured with single-channel. 28 Subjects' EEG is measured while in 2 states; pain-free (VAS score of 0) and pain (VAS score of 3-4). By extracting frequency features from the measured EEG, and classifying using Support Vector Machine (SVM), the subjects in 2 states were classified with the accuracy of 100%. The results show reliability and validity of classifying pain degree using EEG measured with single-channel.
AB - The final aim of this paper is to classify pain degree by only using Electroencephalogram (EEG) measured with single-channel. In clinical care, pain degree is needed for choosing and evaluating treatments, and it is important for clinicians to quantify pain degree as objectively as possible. Pain rating scales such as the Visual Analogue Scales (VAS) are usually used to quantify pain degree, which is only capable of subjective values due to self-report. From that, a method to quantify pain degree objectively has great importance. In this paper, we propose the possibility of quantifying pain degree by only using EEG measured with single-channel. 28 Subjects' EEG is measured while in 2 states; pain-free (VAS score of 0) and pain (VAS score of 3-4). By extracting frequency features from the measured EEG, and classifying using Support Vector Machine (SVM), the subjects in 2 states were classified with the accuracy of 100%. The results show reliability and validity of classifying pain degree using EEG measured with single-channel.
KW - Machine learning
KW - Pain degree
KW - Prefrontal cortex
KW - Signal processing
KW - Single-channeled EEG
UR - http://www.scopus.com/inward/record.url?scp=85048817748&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048817748&partnerID=8YFLogxK
U2 - 10.1109/AMC.2019.8371118
DO - 10.1109/AMC.2019.8371118
M3 - Conference contribution
AN - SCOPUS:85048817748
T3 - Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018
SP - 359
EP - 363
BT - Proceedings - 2018 IEEE 15th International Workshop on Advanced Motion Control, AMC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Workshop on Advanced Motion Control, AMC 2018
Y2 - 9 March 2018 through 11 March 2018
ER -