The main field of work of this thesis is the detection of seizures using machine learning methods. The data we used came from scalp electroencephalograms (EEGs). This is the
CHB-MIT database, which is available for free, from the PhysioNet platform. In the context of the implementation, the whole
process of data management was examined from their download, the extraction of characteristics (mean, variance, skewness, kurtosis, standard deviation, median, zero crossings,
root mean square, peak to peak, sample entropy, power via PSD in the delta, theta, alpha, beta, gamma frequencies, maximum correlation) from them, their normalization (z-score),
the reduction of dimensions (PCA) by preserving their inherent information, the balancing of epileptic and non-epileptic samples (Cluster Centroids, ADASYN) to training, optimization
(grid search) and classifier implementation (SVM, kNN, Naive Bayes, Decision Trees, Random Forest, LDA, Logistic Regression, Neural Network with LSTM), their evaluation (accuracy,
sensitivity/recall, specificity, precision, F1 score, Matthews correlation coefficient, Cohen's Kappa coefficient) and comparison of results. Three different experiments are
performed either by using the measurements of all the electrodes or part of them. The main difference of our method in relation to the bibliography is that the results of the
generalization of the methods are examined in contrast to the focused ones on each patient that is usually encountered. All of the above is done using Python, which is the most
popular of machine learning applications, and the Jupyter platform.
My thesis is available here.
seizuredetection's Introduction
seizuredetection's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.