Loading...

EEG-based Thought to Text Conversion Via Interpretable Deep Networks

Dastani, Saeed | 2022

67 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56212 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Rabiee, Hamid Reza
  7. Abstract:
  8. With the advancement of technologies related to electroencephalography signals, brain and computer interfaces, the program has received much attention. This report deals with one of the new and important issues in this field, i.e. converting thought into text. In this research, the letters, words, and sentences that a person thinks or utters in his mind are decoded and converted into text based on electroencephalography signals. There is still no credible and credible information in neuroscience about whether the same patterns of neuronal activity occur in the brain when thinking about similar letters or words. However, the remarkable growth and development of deep neural networks has made it possible to extract the most complex patterns from the desired data. But challenges such as the lack of interpretability of deep networks and the breadth and complexity of letters and words and mental patterns have limited the use of these interfaces. Our goal in this research is to provide a machine learning model based on deep networks that can convert thought into text on a limited set of letters or words. Therefore, by making the proposed model interpretable, more patterns and information can be extracted from the process that occurs when thinking in the brain, and we can get closer to the general problem of reading thoughts.
  9. Keywords:
  10. Electroencephalography ; Brain-Computer Interface (BCI) ; Deep Neural Networks ; Interpretability ; Neuroscience ; Thought-to-Text Conversion

 Digital Object List

 Bookmark

...see more