|
|
Data Analysis and Clasification from the Brain Activity Detector
Jileček, Jan ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
This thesis aims to implement methods for recording EEG data obtained with the neural activity sensor OpenBCI Ultracortex IV headset. It also describes neurofeedback, methods of obtaining data from the motor cortex for further analysis and takes a look at the machine learning algorithms best suited for the presented problem. Multiple training and testing datasets are created, as well as a tool for recording the brain activity of a headset-wearing test subject, which is being visually presented with cognitive challenges on the screen in front of him. A neurofeedback demo app has been developed, presented and later used for calibration of new test subjects. Next part is data analysis, which aims to discriminate the left and right hand movement intention signatures in the brain motor cortex. Multiple classification methods are used and their utility reviewed.
|
|
|
Convolutional Neural Networks for Emotion Recognition
Jileček, Jan ; Najman, Pavel (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks are used for various tasks, but foremost in machine learning, in which they excel. This work is going to introduce some existing frameworks, other algorithms for recognition and then we describe the training dataset creation and the model for emotion recognition training process. Mentioned model has accuracy of 60%. It is used for emotion statistics retrieval from movie trailers. Model for genre recognition is created from those statistics and then finally used in our application for genre recognition of the input trailer, with best accuracy of 47%.
|
|
|
Data Analysis and Clasification from the Brain Activity Detector
Jileček, Jan ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
This thesis aims to implement methods for recording EEG data obtained with the neural activity sensor OpenBCI Ultracortex IV headset. It also describes neurofeedback, methods of obtaining data from the motor cortex for further analysis and takes a look at the machine learning algorithms best suited for the presented problem. Multiple training and testing datasets are created, as well as a tool for recording the brain activity of a headset-wearing test subject, which is being visually presented with cognitive challenges on the screen in front of him. A neurofeedback demo app has been developed, presented and later used for calibration of new test subjects. Next part is data analysis, which aims to discriminate the left and right hand movement intention signatures in the brain motor cortex. Multiple classification methods are used and their utility reviewed.
|
|
|
Convolutional Neural Networks for Emotion Recognition
Jileček, Jan ; Najman, Pavel (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks are used for various tasks, but foremost in machine learning, in which they excel. This work is going to introduce some existing frameworks, other algorithms for recognition and then we describe the training dataset creation and the model for emotion recognition training process. Mentioned model has accuracy of 60%. It is used for emotion statistics retrieval from movie trailers. Model for genre recognition is created from those statistics and then finally used in our application for genre recognition of the input trailer, with best accuracy of 47%.
|
guest ::
