Study of ABC and PSO algorithms as optimised adaptive noise canceller for EEG/ERP. (2016)

• Record Type: Journal Article
• Authors: Ahirwal, Mitul Kumar; Kumar, Anil; Singh, Girish Kumar
• Is Part Of: International journal of bio-inspired computation. Volume 8:Number 3(2016)
• Page Start: 170
• Page End: 183
• Publication Date: 2016
• Subjects: adaptive noise canceller -- electroencephalograms -- event related potential -- EEG -- ERP -- extraction -- ABC -- artificial bee colony -- particle swarm optimisation -- PSO -- swarm intelligence -- adaptive filters -- biomedical signal processing -- signal-to-noise ratio -- SNR -- correlation -- run time estimation -- mean square error -- kurtosis -- skewness; Biologically-inspired computing -- Periodicals; Computational biology -- Periodicals; 572.0285
• Languages: English
• ISSNs: 1758-0366

Abstract

This paper explores the application of swarm intelligence techniques for optimisation of adaptive filters/noise cancellers used in field of biomedical signal processing. Working, application and results analysis with respect to electroencephalogram/event related potential (EEG/ERP) filtering have been presented from the tutorial perspective. Artificial bee colony (ABC) and particle swarm optimisation (PSO) algorithm have been selected to derive adaptive noise canceller, comparative study and analysis of performance is done among them. Variants of ABC and PSO such as modified rate ABC to control frequency of the perturbation, scaling factor ABC to control magnitude of the perturbation, constant weighted inertia PSO, linear decay inertia PSO, constriction factors inertia PSO, nonlinear inertia PSO, and dynamic inertia PSO has been used. Performance is measured in terms of signal-to-noise ratio, correlation, running time estimation and mean square error. Finally, the quality of resultant ERP is determined with kurtosis and skewness.