ECG Artifact Removal of EEG signal using Adaptive Neural Network
- Resource Type
- Conference
- Authors
- Routray, Lipsa; Biswal, Pradyut; Pattanaik, Satya Ranjan
- Source
- 2018 IEEE 13th International Conference on Industrial and Information Systems (ICIIS) Industrial and Information Systems (ICIIS), 2018 IEEE 13th International Conference on. :103-106 Dec, 2018
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Adaptive filters
Electroencephalography
Filtering algorithms
Electrocardiography
Biological neural networks
Information filters
EEG
ECG
ANC
ANN
FLANN
RBFN
LMS
NLMS
FxLMS
- Language
In this paper, we present a filter for de-noising an ECG mixed EEG signal where ECG considered as an artifact and the aim is to remove that ECG signal from the noisy EEG (EEG+ECG) signal. The input to the system is the estimated ECG signal which works on noise cancellation technology to retrieve the original EEG signal. We have taken a one-layered feed forward network known as Functional Link Adaptive Neural Network (FLANN) and a three layered Radial Basis Functional Network (RBFN) for the filter design. For weight updating there are three adaptive algorithms are applied like Least Mean Square (LMS), Normalized Least Mean Square (NLMS) and Filtered Least Mean Square (FxLMS). The results of three algorithms are analyzed.