a Master thesis is provided with topic on Multichannel time-series data analysis with deep neural networks,please take a look here http://www.findke.ovgu.de/findke/en/Studies/Theses.html and contact me with email.

 

  • Master’s thesis: Multichannel time-series data analysis with deep neural networks
    Responsible person: Jiahua Xu
    The topic Brain Computer Interface has been highlighted recently with the development of artificial intelligence and computational efficiency in many fields such as motor control, neuron rehabilitation and so on. Machine Learning algorithms play a very important role in training and predicting the brain cognition behaviors for BCI systems, one of them being in the field of deep learning, which has been employed for its high accuracy and implicit feature extraction.

    Here we mainly focus on the multichannel time-series EEG data collected from human beings with a specific task of motor imagery. The thesis shall focus on deep neural networks such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs) to classify EEG data. Neuroscience experts will aid in understanding how the brain responds to different tasks at the sensor or source level. Additionally, the topic provides the opportunity to learn about brain imaging technologies.

    Requirements: As a requirement for this master’s thesis topic, you should be familiar with either Python (we use TensorFlow) or Matlab and have a solid background in Machine Learning. Please send your CV and programming proofs to: jiahua.xu@med.ovgu.de.