


Volume 20 No 12 (2022)
Download PDF
FPGA Implementation of Area and Power Optimized and High Speed Seizure Detection System using ELM Classification Method
K.R. Radhakrishnan , M. Amalasweena , T. Kesavamurthy
Abstract
In order to diagnose brain abnormalities, electroencephalography (EEG) signals are employed. The
aberrant electrical activation in the nervous system of human which is recorded by these EEG signals defines
the epileptic seizures. Seizure sufferers might die suddenly if these epileptic seizures occur at an inappropriate time.
It is possible to identify and anticipate epileptic seizures by studying these EEG data signals however it is a difficult
process to analyze reliable prediction. As a result, more precise epileptic seizure detection is possible recognition to
hardware and real-time FPGA implementation. Brain rhythms in the delta (0–4Hz) and theta (>4Hz) bands were
studied separately in this approach, which used the band pass fixed impulse responses. In the application of digital
signals processing , multiplication is more priority one its restricted in number and have fixed position on FPGA,
which may cause routing delays and lower bit width of optimized soft IP core. This paper presents that soft
multiplier IP core of Accurate and Approximate Multipliers instead of MCM multiplication was used in every band of
FIR filters and Feature extraction approach and ELM Classification in this suggested study for the reduction of area,
power and delay of the EEG data and for classifying normal or epileptic signals. Finally, this suggested study
compared all parameters on the basis of delay, power and area, and was developed in Verilog HDL and generated in
Xilinx Virtex-5 FPGA.
Keywords
Approximate Computing, Multipliers, FPGA, Electroencephalography (EEG), ELM, Epileptic Seizure, Linear prediction
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.