TY - GEN
T1 - Action understanding based on a combination of one-versus-rest and one-versus-one multi-classification methods
AU - Liu, Hui
AU - Zheng, Wengming
AU - Sun, Gaopeng
AU - Shi, Yanhua
AU - Leng, Yue
AU - Lin, Pan
AU - Wang, Ruimin
AU - Yang, Yuankui
AU - Gao, Jun Feng
AU - Wang, Haixian
AU - Iramina, Keiji
AU - Ge, Sheng
N1 - Funding Information:
VI. ACKNOWLEDGMENT This work was supported by the National Basic Research Program of China (2015CB351704), the National Nature Science Foundation of China (61473221, 81271659, and 31500881), the Natural Science Foundation of Jiangsu Province of China under Grant (BK20140621), and the Fundamental Research Funds for the Southeast University.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - When people observe the actions of others, they naturally try to understand the underlying intentions. This behavior is called action understanding, and it has an important influence on mental development, language comprehension, and socialization. In this study, we used functional near-infrared spectroscopy (fNIRS) to obtain brain signals related to action understanding and then classified different intentions. Aiming to overcome the drawbacks of traditional multiclass classification methods of one-versus-rest (OVR) and one-versus-one (OVO), in this paper, we propose a new effective method to solve multiclass classification that is a combination of OVR and OVO. Compared with OVO, this new method effectively improved the accuracy of four-class classification from 25% to 48%.
AB - When people observe the actions of others, they naturally try to understand the underlying intentions. This behavior is called action understanding, and it has an important influence on mental development, language comprehension, and socialization. In this study, we used functional near-infrared spectroscopy (fNIRS) to obtain brain signals related to action understanding and then classified different intentions. Aiming to overcome the drawbacks of traditional multiclass classification methods of one-versus-rest (OVR) and one-versus-one (OVO), in this paper, we propose a new effective method to solve multiclass classification that is a combination of OVR and OVO. Compared with OVO, this new method effectively improved the accuracy of four-class classification from 25% to 48%.
UR - http://www.scopus.com/inward/record.url?scp=85047530064&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047530064&partnerID=8YFLogxK
U2 - 10.1109/CISP-BMEI.2017.8302159
DO - 10.1109/CISP-BMEI.2017.8302159
M3 - Conference contribution
AN - SCOPUS:85047530064
T3 - Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
SP - 1
EP - 5
BT - Proceedings - 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
A2 - Li, Qingli
A2 - Wang, Lipo
A2 - Zhou, Mei
A2 - Sun, Li
A2 - Qiu, Song
A2 - Liu, Hongying
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2017
Y2 - 14 October 2017 through 16 October 2017
ER -