File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
  • Find via Find It@HKUL
Supplementary

Article: Using non-negative matrix fact factorization to extract attention-related EEG features

TitleUsing non-negative matrix fact factorization to extract attention-related EEG features
應用非負矩陣分解方法提取注意力相關腦電特征
Authors
KeywordsEEG (腦電)
Neurofeedback (生物反饋治療)
Non-negative matrix factorization (非負矩陣分解)
Artificial neural Network (人工神經網絡)
Issue Date2006
PublisherBiophysical Society of China (中國生物物理學會).
Citation
Acta Biophysica Sinica, 2006, n. 1, p. 67-72 How to Cite?
生物物理學報, 2006, n. 1, p. 67-72 How to Cite?
AbstractThe fundamental of non-negative matrix factorization algorithm was introduced. It is used to extract EEG power spectrum feature. Artificial neural network is employed as classifier. Three level attention mental tasks are designed to test the method. Ten subjects attended the experiment. The classification accuracies indicate that the NMF technique is a powerful feature extractor in high-dimensional feature space. The average classification accuracy of ten subjects achieves 88%, it is higher obviously than that of principal component analysis and direct method. 介紹了非負矩陣分解算法(NMF)的基本原理,給出一種利用NMF進行腦電能量譜特征提取的方法。設計試驗對10個被試在三種不同注意任務中的腦電信號進行特征提取,并采用人工神經網絡作為分類器進行分類測試。結果表明,NMF算法在高維特征空間具有較強的特征選擇能力,其分類正確率明顯高于主分量分析(PCA)方法和直接法,三種意識任務的分類正確率分別達到84.5、88%和86.5。
Persistent Identifierhttp://hdl.handle.net/10722/208405
ISSN

 

DC FieldValueLanguage
dc.contributor.authorLiu, MY-
dc.contributor.authorWang, J-
dc.contributor.authorZheng, CX-
dc.contributor.authorYan, N-
dc.date.accessioned2015-02-25T06:38:38Z-
dc.date.available2015-02-25T06:38:38Z-
dc.date.issued2006-
dc.identifier.citationActa Biophysica Sinica, 2006, n. 1, p. 67-72-
dc.identifier.citation生物物理學報, 2006, n. 1, p. 67-72-
dc.identifier.issn1000-6737-
dc.identifier.urihttp://hdl.handle.net/10722/208405-
dc.description.abstractThe fundamental of non-negative matrix factorization algorithm was introduced. It is used to extract EEG power spectrum feature. Artificial neural network is employed as classifier. Three level attention mental tasks are designed to test the method. Ten subjects attended the experiment. The classification accuracies indicate that the NMF technique is a powerful feature extractor in high-dimensional feature space. The average classification accuracy of ten subjects achieves 88%, it is higher obviously than that of principal component analysis and direct method. 介紹了非負矩陣分解算法(NMF)的基本原理,給出一種利用NMF進行腦電能量譜特征提取的方法。設計試驗對10個被試在三種不同注意任務中的腦電信號進行特征提取,并采用人工神經網絡作為分類器進行分類測試。結果表明,NMF算法在高維特征空間具有較強的特征選擇能力,其分類正確率明顯高于主分量分析(PCA)方法和直接法,三種意識任務的分類正確率分別達到84.5、88%和86.5。-
dc.languageeng-
dc.publisherBiophysical Society of China (中國生物物理學會).-
dc.relation.ispartofActa Biophysica Sinica-
dc.relation.ispartof生物物理學報-
dc.subjectEEG (腦電)-
dc.subjectNeurofeedback (生物反饋治療)-
dc.subjectNon-negative matrix factorization (非負矩陣分解)-
dc.subjectArtificial neural Network (人工神經網絡)-
dc.titleUsing non-negative matrix fact factorization to extract attention-related EEG featuresen_US
dc.title應用非負矩陣分解方法提取注意力相關腦電特征-
dc.typeArticleen_US
dc.identifier.emailYan, N: nyan@hku.hk-
dc.identifier.hkuros183220-
dc.identifier.issue1-
dc.identifier.spage67-
dc.identifier.epage72-
dc.publisher.placeChina (中國)-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats