Feature extraction from printed Persian sub-words using Haar wavelet transform

2011 ◽  
Author(s):  
Samira Nasrollahi Dizajyekan ◽  
Afshin Ebrahimi
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Haar Wavelet ◽  
Haar Wavelet Transform

Novel Model for Automatic Classification of the Epileptic Seizures Using Fast Fourier Series-Haar Wavelet Transform

2021 ◽  
Vol 11 (12) ◽  
pp. 3209-3214
Author(s):  
P. Geetha ◽  
S. Nagarani
Keyword(s):  
Feature Extraction ◽  
Image Segmentation ◽  
Fourier Series ◽  
Wavelet Transform ◽  
Epileptic Seizures ◽  
Medical Application ◽  
Scale Space ◽  
Haar Wavelet ◽  
Sample Length ◽  
Haar Wavelet Transform

The disorder based on neurological can be considered as epilepsy that leads to the recurrent seizures in occurrence. The electronic characteristics of brain can be monitor by the electroencephalogram (EEG). It is most commonly used in the medical application. The function monitoring records can be non linear as well as non stationary functioning. The present work produce a novel methodology, it is depend on Fast Fourier series (FFS) and wavelet transform based on Haar. These methods are used for the various kinds of epileptic seizure the electroencephalogram based signal. The detection of boundary is occur by the representation of scale-space and it also adapted to the image segmentation of the spectrum depends on the FBSE that can be obtained with the electroencephalogram based signal and the purpose of the EWT is also used to attain the narrow sub band based signals. These image segmentation and classification process implementation by FPGA based microprocessor and systems. The FFS-HMT can produce the sub band signal from the Hilbert marginal spectrum it is represented as HMS. The HMS can be used to compute the line length and the entropy characteristics due to the corresponding various kinds of the level based oscillatory of the electroencephalogram signal. Here we apply the selected feature extraction depends on the ranking parallel vector. With the use of an electroencephalogram signal, the robust random forest is utilized to classify selected feature extraction in normal and epileptic participants. The assessment of performance based on classification can be measured in FPGA microprocessor the term of classification accuracy for different sample length of EEG. The current methodology aids neurologists in distinguishing between healthy and epileptic people using electroencephalogram signals.

Sign in / Sign up

Export Citation Format

Share Document