TY - GEN
T1 - Personalized Feature Selection for Wearable EEG Monitoring Platform
AU - Peng, Genchang
AU - Nourani, Mehrdad
AU - Harvey, Jay
AU - Dave, Hina
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - Electroencephalography (EEG) signal monitoring can be applied for many purposes, such as epileptic seizure detection. To design a reliable, wearable EEG monitoring platform for seizure detection in daily use, this paper presents a two-step approach to select a small subset of discriminative features from a few number of channels. In the first step, linear discriminant analysis (LDA) is applied to choose informative channels which have highly-ranked LDA criterion values. Then in the second step, the least absolute shrinkage and selection operator (LASSO) method is adopted to incrementally add features into selection subset. To determine the best number of channels and features for each subject, a personalization technique is utilized by evaluating the classification result of different feature subsets based on support vector machine (SVM) classifier. Experimentation on CHB-MIT database shows that on average, the proposed method selects approximately 3 channels and 7 features, and yields F-1 score of 81% based on SVM evaluation.
AB - Electroencephalography (EEG) signal monitoring can be applied for many purposes, such as epileptic seizure detection. To design a reliable, wearable EEG monitoring platform for seizure detection in daily use, this paper presents a two-step approach to select a small subset of discriminative features from a few number of channels. In the first step, linear discriminant analysis (LDA) is applied to choose informative channels which have highly-ranked LDA criterion values. Then in the second step, the least absolute shrinkage and selection operator (LASSO) method is adopted to incrementally add features into selection subset. To determine the best number of channels and features for each subject, a personalization technique is utilized by evaluating the classification result of different feature subsets based on support vector machine (SVM) classifier. Experimentation on CHB-MIT database shows that on average, the proposed method selects approximately 3 channels and 7 features, and yields F-1 score of 81% based on SVM evaluation.
KW - Feature selection
KW - least absolute shrinkage and selection operator
KW - linear discriminant analysis
KW - personalization.
UR - http://www.scopus.com/inward/record.url?scp=85099603095&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099603095&partnerID=8YFLogxK
U2 - 10.1109/BIBE50027.2020.00069
DO - 10.1109/BIBE50027.2020.00069
M3 - Conference contribution
AN - SCOPUS:85099603095
T3 - Proceedings - IEEE 20th International Conference on Bioinformatics and Bioengineering, BIBE 2020
SP - 380
EP - 386
BT - Proceedings - IEEE 20th International Conference on Bioinformatics and Bioengineering, BIBE 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020
Y2 - 26 October 2020 through 28 October 2020
ER -