User Tools

Site Tools


projects:year5:16.02

This is an old revision of the document!


16.02 - Patient Specific Framework for Biomedical Signal Management

Project - Summary

Objectives Bioelectric measurements convey information about the function of the underlying organ or tissue. Despite the difference and complexity of the patterns in the cells' electrical activity, they may superficially appear to have a same phenotype. Therefore, the study of such signals is an interesting choice of medical experts for diagnosis and treatment. Identifying the underlying dynamics of physiological events using bioelectric signals is crucial to understand their functions. This provides discriminant characteristics for detecting the interest event from the background activity.

In this project, our focus is to use Electroencephalography (EEF) recordings to detect seizure events automatically based on nonlinear dynamics. This is a hot topic in epilepsy research community since diagnosis is still preformed by visual inspection. The tedious screening of long-term EEG recordings gives rise to the importance of automatic seizure detection methods. Thus, we propose a seizure detection system. For validating the proposed method, we use two publicly available datasets (CHB-MIT [1] [2] and University Hospital of Bonn dataset [3]).

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Moncef Gabbouj PI moncef.gabbouj@tuni.fi +358 (400) 736613 Tampere University
Serkan Kiranyaz Co-PI Not available Not available Tampere University
Morteza Zabihi Student Not available Not available Tampere University

Project - Impact and Uses/Benefits

A supervised camera invariant color constancy algorithm is immediately applicable to camera industry. with such method, the dependency on unsupervised methods somewhat general but inferior performance can be eliminated. Moreover, the need of training a machine for each specific camera is also unnecessary thanks to color-conversion approach. With this method, one can only train a color constancy algorithm for one camera and immediately apply this CNN for other methods. The only need is the color conversion pre-processing step which loads almost no computational complexity on top of the color constancy algorithm. Although since this method is also supervised, one needs the camera spectral sensitivity of the cameras used. This information is very easy to be obtained compared to the very heavy task of collecting a new database of each camera and training a network for each camera.

Project - Deep Dive

Project - Documents

[n/a: No match]
projects/year5/16.02.1566337332.txt.gz · Last modified: 2019/08/20 16:42 by sally.johnson