Difference between revisions of "Self Aware Epilepsy Monitoring"
From iis-projects
(→Project Description) |
(→Project Description) |
||
Line 8: | Line 8: | ||
The self-aware part of the system will be implemented in a way where the quality of the data is assessed before feeding it into a classifier: if the system is certain of good quality data that should be easy to classify, a more simple and energy-efficient classifier is used; if, instead, input data guarantee low confidence, a more complex classifier can be employed. | The self-aware part of the system will be implemented in a way where the quality of the data is assessed before feeding it into a classifier: if the system is certain of good quality data that should be easy to classify, a more simple and energy-efficient classifier is used; if, instead, input data guarantee low confidence, a more complex classifier can be employed. | ||
− | The resulting model/s will then be implemented on a real microcontroller and | + | The resulting model/s will then be implemented on a real microcontroller, and performance and power measurements will be performed. |
===Status: Available=== | ===Status: Available=== |
Revision as of 15:13, 14 January 2022
Contents
Introduction
Epilepsy is a central nervous system disorder in which brain activity becomes abnormal, causing seizures or periods of unusual behavior, sensations, and sometimes loss of awareness. The golden diagnostic standard is represented by Electroencephalography (EEG) systems, which unfortunately are cumbersome and can make patients uncomfortable because of perceived stigmatization. Thus, both patients and caregivers would benefit from the availability of wearable long-term EEG monitoring devices. These long-term EEG monitoring devices must be robust to different noises or artifacts, which can be either external disturbances or movement of the patient that taints the EEG signal.
Project Description
In this project, the student will work on designing and implementing a self-aware machine learning model to be used in a wearable system for real-time detection of epileptic seizures. The self-aware part of the system will be implemented in a way where the quality of the data is assessed before feeding it into a classifier: if the system is certain of good quality data that should be easy to classify, a more simple and energy-efficient classifier is used; if, instead, input data guarantee low confidence, a more complex classifier can be employed.
The resulting model/s will then be implemented on a real microcontroller, and performance and power measurements will be performed.
Status: Available
- Looking for Semester and Master Project Students
- Supervision: Thorir Mar Ingolfsson, Andrea Cossettini, Simone Benatti
Character
- 20% literature review
- 80% Implementation
Literature
- [1]F. Forooghifar et. al., A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection