Deep learning methods for electroencephalogram (EEG) spike detection
This project is about developing novel deep learning methods for detecting abnormalities in time series. Specifically, we will consider the problem of detecting spikes in the EEG of patients of epilepsy as well as recurrent neural networks. We will also analyze the EEG of healthy subjects, as a base...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/71063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | This project is about developing novel deep learning methods for detecting abnormalities in time series. Specifically, we will consider the problem of detecting spikes in the EEG of patients of epilepsy as well as recurrent neural networks. We will also analyze the EEG of healthy subjects, as a baseline. This project was concluded on April 2017 and it was found that long short term memory networks work decently well in the spike detection of epileptic spikes. Tuned parameters were also presented in this report. |
|---|