Abstract
Hybrid-modality brain-computer Interfaces (BCIs), which combine motor imagery (MI) bio-signals and steady-state visual evoked potentials (SSVEPs), has attracted wide attention in the research field of neural engineering. The number of channels should be as small as possible for real-life applications. However, most of recent works about channel selection only focus on either the performance of classification task or the effectiveness of device control. Few works conduct channel selection for MI and SSVEP classification tasks simultaneously. In this paper, a multitasking-based multiobjective evolutionary algorithm (EMMOA) was proposed to select appropriate channels for these two classification tasks at the same time. Moreover, a two-stage framework was introduced to balance the number of selected channels and the classification accuracy in the proposed algorithm. The experimental results verified the feasibility of multiobjective optimization methodology for channel selection of hybrid BCI tasks.
Highlights
Brain-computer interface (BCI) develops a communication means between brains and external devices (Alcaide-Aguirre and Huggins, 2014)
Channel selection needs to make a compromise between two objectives: the number of selected channels and classification accuracy. This perfectly coincides with the goal of multiobjective evolutionary algorithms (MOEAs), which is to make a compromise among multiple optimization objectives
The second one aimed to evaluate the effectiveness of Evolutionary Multitasking-Based Multiobjective Optimization Algorithm (EMMOA) by comparing with three widely used multiobjective optimization algorithms, including Non-dominated Sorting Genetic AlgorithmII (NSGA-II) (Deb et al, 2002), Multiobjective Evolutionary Algorithm Based on Decomposition (MOEA/D) (Zhang and Li, 2007), and Multiobjective Particle Swarm Optimization (MOPSO) (Coello et al, 2004)
Summary
Brain-computer interface (BCI) develops a communication means between brains and external devices (Alcaide-Aguirre and Huggins, 2014). Channel selection needs to make a compromise between two objectives: the number of selected channels and classification accuracy This perfectly coincides with the goal of multiobjective evolutionary algorithms (MOEAs), which is to make a compromise among multiple optimization objectives. A multitasking-based multiobjective evolutionary algorithm (EMMOA) is proposed to perform channel selection for MI and SSVEP tasks at the same time. The first stage is based on an evolutionary multitasking mechanism and aims to obtain the Pareto-optimal solutions (PS) for MI and SSVEP tasks by one single population. The second stage constructs a three-objective optimization problem, which used classification accuracy for MI task, classification accuracy for SSVEP task, and the number of selected channels as the optimization objectives.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
