The aim of this paper is to present a system for automatic assigning electroencephalographic (EEG) signals to appropriate classes associated with brain activity. The EEG signals are acquired from a headset consisting of 14 electrodes placed on skull. Data gathered are first processed by the Independent Component Analysis algorithm to obtain estimates of signals generated by primary sources reflecting the activity of the brain. Next, the parameterization process is performed in two ways, i.e. by applying Discrete Wavelet Transform and utilizing an autoencoder network. The resulting sets of parameters are then used for the data clustering and the effectiveness of correct assignment of data into adequate clusters is checked. It occurs that the performance of wavelets- and autoencoders-based parametrization is similar, however in several cases, autoencoders allowed for obtaining a higher mean distance and lower standard deviation than distances provided by the wavelet-based method. Moreover, a supervised classification of signals is performed as a form of benchmarking.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1007/978-3-319-98678-4_47
- Category
- Aktywność konferencyjna
- Type
- materiały konferencyjne indeksowane w Web of Science
- Language
- angielski
- Publication year
- 2018
