Noise Removal from EMG Signal Using Adaptive Enhanced Squirrel Search Algorithm
| Autor: | V. V. K. D. V. Prasad, B. Nagasirisha |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Noise (signal processing) business.industry General Mathematics 0206 medical engineering General Physics and Astronomy Pattern recognition 02 engineering and technology 020601 biomedical engineering Signal Adaptive filter Search algorithm 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Power line interference Noise removal business |
| Zdroj: | Fluctuation and Noise Letters. 19:2050039 |
| ISSN: | 1793-6780 0219-4775 |
| DOI: | 10.1142/s021947752050039x |
| Popis: | Electromyogram (EMG) signals are mostly affected by a large number of artifacts. Most commonly affecting artifacts are power line interference (PLW), baseline noise and ECG noise. This work focuses on a novel attenuation noise removal strategy which is concentrated on adaptive filtering concepts. In this paper, an enhanced squirrel search (ESS) algorithm is applied to remove noise using adaptive filters. The noise eliminating filters namely adaptive least mean square (LMS) filter and adaptive recursive least square (RLS) filters are designed, which is correlated with an ESS. This novel algorithm yields better performance than other existing algorithms. Here the performances are measured in terms of signal-to-noise ratio (SNR) in decibel, maximum error (ME), mean square error (MSE), standard deviation, simulation time and mean value difference. The proposed work has been implemented at the MATLAB simulation platform. Testing of their noise attenuation capability is also validated with different evolutionary algorithms namely squirrel search, particle swarm optimization (PSO), artificial bee colony (ABC), firefly, ant colony optimization (ACO) and cuckoo search (CS). The proposed work eliminates the noises and provides noise-free EMG signal at the output which is highly efficient when compared with existing methodologies. Our proposed work achieves 4%, 40%, 4%, 7%, 9% and 70% better performance than the literature mentioned in the results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|