Experiments on classification of electroencephalography (EEG) signals in imagination of direction using Stacked Autoencoder

DOI DOI 機関リポジトリ 機関リポジトリ (HANDLE) オープンアクセス
  • Tomonaga Kenta
    Department of Systems Design and Informatics, Kyushu Institute of Technology
  • Hayakawa Takuya
    Department of Systems Design and Informatics, Kyushu Institute of Technology
  • Kobayashi Jun
    Department of Systems Design and Informatics, Kyushu Institute of Technology

説明

This paper presents classification methods for electroencephalography (EEG) signals in imagination of direction measured by a portable EEG headset. In the authors' previous studies, principal component analysis extracted significant features from EEG signals to construct neural network classifiers. To improve the performance, the authors have implemented a Stacked Autoencoder (SAE) for the classification. The SAE carries out feature extraction and classification in a form of multi-layered neural network. Experimental results showed that the SAE outperformed the previous classifiers.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ