Open AccessBio‐inspired evolutionary computing approach for distributed active noise control problem
Author(s) -
Kukde Ruchi,
Panda Ganapati,
Manikandan M. Sabarimalai
Publication year - 2020
Publication title -
cognitive computation and systems
Language(s) - English
Resource type - Journals
ISSN - 2517-7567
DOI - 10.1049/ccs.2019.0030
Subject(s) - active noise control , noise (video) , computer science , noise control , convergence (economics) , scheme (mathematics) , swarm behaviour , particle swarm optimization , noise reduction , algorithm , artificial intelligence , mathematics , mathematical analysis , economics , image (mathematics) , economic growth
In this study, a distributed active noise control (DANC) system for spatial noise control in a network of acoustic sensor nodes based on the behavioural traits of felines is presented. An unified strategy based on incremental co‐operative learning and cat swarm intelligence is proposed for noise mitigation in spatial region. The hybrid nature of the proposed incremental cat swarm optimisation (ICSO) algorithm provides efficient noise control without prior estimation of multiple secondary paths. In the developed ICSO‐based DANC scheme, the individual sensor nodes communicate the intermediate solutions using incremental mode of cooperation to attain overall global noise mitigation over the distributed network. The performance of the proposed ICSO based DANC scheme is validated for tonal, broadband and practical air conditioner noise control test scenarios. Evaluation results show that the proposed system achieves faster convergence with computational efficiency of over 36% and ∼2–9 dB improvement in noise cancellation for different noise cases and acoustic environments over genetic algorithm and particle swarm optimisation based DANC counterparts.