基於時空特徵之頭皮腦波獨立成分分類

干擾波去除已成為許多腦波訊號應用之重要前置處理步驟，其中著名的方法之一即為獨立主成份分析。透過獨立主成份分析，可將腦波訊號分解成多個獨立成分。接著，如何進一步將這些獨立成分辨識為干擾波或正常波乃是一大關鍵問題，因此各種獨立成分時間或空間特徵相繼被提出來做為辨識依據。本研究主要利用統計檢定探討頭皮腦波獨立成分之四種時域與三種空域特徵對干擾波與正常波分類之鑑別性。此外，應用隨機決策森林、貝氏分類器、最近鄰居法、支持向量機、線性識別分析、邏輯回歸模型等六種著名分類建模方法分別建立干擾波與正常波獨立成分分類模型，並進行分類結果討論與比較。

關鍵字

獨立成分分析；分類；干擾訊號；時間特徵；空間特徵

並列摘要

Artifact removal has been an important preprocessing step in many applications of Electroencephalography (EEG) signals. One of well-known Artifact removal approaches is independent component analysis (ICA). Through the ICA, EEG signals can be decomposed into several independent components. After that, how to identify each independent component as artifact or neural is a key problem. Therefore, several time-domain or spatial-domain features of independent components have been proposed Successively. This study focuses on discussing the discriminability of each of four time-domain features and three spatial-domain features for artifact or neural independent component classification. Moreover, five well-known classification modeling approaches, namely random forests, bayes classifiers, k-nearest neighbors, support vector machines, linear discriminant analysis and logistic regression, are employed to construct pre-ictal and inter-ictal stage classification models, and the corresponding classification results are discussed and compared.

並列關鍵字

independent component analysis ； time-domain features ； spatial-domain features ； Artifact ； classification

參考文獻

[1] A. Mogonon, J. Jovicich, L. Bruzzone and M. Buiatti “ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features” ,Psychophysiology, no.48, P.229–240,2011

[3] L. F. Frølich, T. S. ANDERSEN, and M. MøRUP,” Classification of independent components of EEG into multiple artifact classes”, Psychophysiology, no.52, pp.32–45, 2015

[4] I. Winkler, S. Haufe and and M. Tangermann ”Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals”, Behavioral and Brain Functions ,2011

[5] F.C. Viola, J. Thorne, B. Edmonds,T. Schneider, T. Eichele and S. Debener,” Semi-automatic identification of independent components representing EEG artifact”,Elsevier, Volume 120, Issue 5, Pages 868–877,2009

[7] CARRIE A. JOYCE, IRINA F. GORODNITSKY, and MARTA KUTAS , Automatic removal of eye movement and blink artifacts from EEG data using blind component separation, Psychophysiology, 41 (2004), 313–325

國際替代計量

基於時空特徵之頭皮腦波獨立成分分類

全文下載

主題瀏覽