Loading...

Switching Kalman Filter and Its Application in State Detection in Brain Signals

Rezaei Dastjerdehei, Mohammad Reza | 2021

315 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54172 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shamsollahi, Mohammad Bagher
  7. Abstract:
  8. There are several methods for EEG state detection, and there are still many challenges. Switching Kalman Filter (SKF) is a suitable approach for state detection, which has been used in various applications such as QRS detection in ECG signal, apnea detection using ECG signal, and also hand path detection using EEG signal. Our goal here is to use Switching Kalman Filter (SKF) in order to detect changes in EEG signal, and in particular in sleep. In other words, we want to detect Sleep Stages. Here, detecting Sleep Stages will help doctors diagnose and treat diseases. There is a Kalman Model for each Stages of Sleep in SKF, that I model it with a AR model. In addition, SKF switch is a state variable which is related to each stages of sleep, and it is based on Hidden Markov Model (HMM). The SKF switch can be applied in different parts. We can apply this to the observation matrix, or we can apply this switch to the state matrix, or we can apply it to both. In this project, we want to find the changes of sleep stages by the the SKF switch. Here, we will test our algorithm in the three modes: Simulation with artificial data, Simulation with pseudo-real data, and real data. For real data, we consider two modes, Subject-based and Leave one subject out. Finally, we get 83.76% accuracy for the Subject-based mode, and 82.71 accuracy for Leave one subject out
  9. Keywords:
  10. Switching Kalman Filter ; Detection ; Electroencephalography ; Sleep Quality ; State Detection ; Sleep Stages

 Digital Object List

 Bookmark

No TOC