Research Area: Machine Learning
Electroencephalogram (EEG) signal contains vital details regarding electrical actions performed by the brain. Analysis of these signals is important for epilepsy detection. However, analysis of these signals can be tricky in nature and requires human expertise. The human factor can result in subjective and possible erroneous epilepsy detection. To tackle this problem, Machine Learning (ML) algorithms were introduced, to remove the human factor. However, this approach is counterintuitive in nature as it involves using complex features for epilepsy detection. Hence to tackle this problem we have introduced a wavelet based deep learning approach which eliminates the need of feature extraction and also performs significantly better on smaller datasets compared to the present state of the art ML algorithms. To test the robustness of our model we have performed a binary (2-way) and ternary (3-way) classification using our model. It is found that the model is much more accurate than the present state of the art models and since it uses deep learning it also eliminates the need of feature extraction.
Keywords:
Wavelet
Deep Learning
Epilepsy Detection
Electroencephalogram (EEG) signal
Machine Learning (ML)
Author(s) Name: Rohan Akut
Journal name: Health Information Science and Systems
Conferrence name:
Publisher name: Springer
DOI: 10.1007/s13755-019-0069-1
Volume Information: Volume 7, Article number: 8 (2019)
