Experiments on Classification of Electroencephalography (EEG) Signals in Imagination of Direction using Stacked Autoencoder
Kenta Tomonaga, Takuya Hayakawa, Jun Kobayashi · Journal of Robotics Networking and Artificial Life · 2017
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.