TY - JOUR
T1 - Measuring concept semantic relatedness through common spatial pattern feature extraction on EEG signals
AU - Calvo, Hiram
AU - Paredes, José Luis
AU - Figueroa-Nazuno, Jesús
N1 - Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2018/8
Y1 - 2018/8
N2 - We study the semantic relationship between pairs of nouns of concrete objects such as “HORSE - SHEEP” and “SWING - MELON” and how this relationship activity is reflected in EEG signals. We collected 18 sets of EEG records; each set containing 150 events of stimulation. In this work we focus on feature extraction algorithms. Particularly, we highlight Common Spatial Pattern (CSP) as a method of feature extraction. Based on these latter, different classifiers were trained in order to associate a set of signals to a previously learned human answer, pertaining to two classes: semantically related, or not semantically related. The results of classification accuracy were evaluated comparing with other four methods of feature extraction, and using classification algorithms from five different families. In all cases, classification accuracy was benefited from using CSP instead of FDTW, LPC, PCA or ICA for feature extraction. Particularly with the combination CSP-Naïve Bayes we obtained the best average precision of 84.63%.
AB - We study the semantic relationship between pairs of nouns of concrete objects such as “HORSE - SHEEP” and “SWING - MELON” and how this relationship activity is reflected in EEG signals. We collected 18 sets of EEG records; each set containing 150 events of stimulation. In this work we focus on feature extraction algorithms. Particularly, we highlight Common Spatial Pattern (CSP) as a method of feature extraction. Based on these latter, different classifiers were trained in order to associate a set of signals to a previously learned human answer, pertaining to two classes: semantically related, or not semantically related. The results of classification accuracy were evaluated comparing with other four methods of feature extraction, and using classification algorithms from five different families. In all cases, classification accuracy was benefited from using CSP instead of FDTW, LPC, PCA or ICA for feature extraction. Particularly with the combination CSP-Naïve Bayes we obtained the best average precision of 84.63%.
KW - CSP
KW - Common spatial pattern
KW - EEG
KW - Electroencephalogram
KW - Emotiv EPOC
KW - Oddball
KW - Semantic concept similarity
KW - Signal classification
UR - http://www.scopus.com/inward/record.url?scp=85045127068&partnerID=8YFLogxK
U2 - 10.1016/j.cogsys.2018.03.004
DO - 10.1016/j.cogsys.2018.03.004
M3 - Artículo
SN - 1389-0417
VL - 50
SP - 36
EP - 51
JO - Cognitive Systems Research
JF - Cognitive Systems Research
ER -