Evolutionary feature selection and electrode reduction for EEG classification

Atyabi, Adham; Luerssen, Martin H.; Fitzgibbon, Sean P.; Powers, David

doi:10.1109/cec.2012.6256130

Cited by 22 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study of EEG, dimension reduction can be applied on both feature and/or channel dimensions. Atyabi et al [27] investigated the impact of evolutionary approaches such as Genetic Algorithm, Random Search, and PSO for feature and channel reduction among which the PSO-based feature reduction approach showed better overall generalizability. Atyabi et al [12] proposed 99% reduction through simultaneous reduction of feature and channel sets using a PSO-based approach with two layer swarm structure called PSO-DR.…”

Section: Pso Dimension Reduction (Pso-dr)mentioning

confidence: 99%

Reducing training requirements through evolutionary based dimension reduction and subject transfer

et al. 2017

Self Cite

View full text Add to dashboard Cite

Training Brain Computer Interface (BCI) systems to understand the intention of a subject through Electroencephalogram (EEG) data currently requires multiple training sessions with a subject in order to develop the necessary expertise to distinguish signals for different tasks. Conventionally the task of training the subject is done by introducing a training and calibration stage during which some feedback is presented to the subject. This training session can take several hours which is not appropriate for on-line EEG-based BCI systems. An alternative approach is to use previous recording sessions of the same person or some other subjects that performed the same tasks (subject transfer) for training the classifiers. The main aim of this study is to generate a methodology that allows the use of data from other subjects while reducing the dimensions of the data. The study investigates several possibilities for reducing the necessary training and calibration period in subjects and the classifiers and addresses the impact of i) evolutionary subject transfer and ii) adapting previously trained methods (retraining) using other subjects data. Our results suggest reduction * Corresponding author to 40% of target subject data is sufficient for training the classifier. Our results also indicate the superiority of the approaches that incorporated evolutionary subject transfer and highlights the feasibility of adapting a system trained on other subjects.

show abstract

Section: Pso Dimension Reduction (Pso-dr)mentioning

confidence: 99%

Reducing training requirements through evolutionary based dimension reduction and subject transfer

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…As far as the authors' knowledge is concerned, although PSO has been employed to address various issues in BCI applications such as feature selection [21][22][23][24], source localization [25,26], change point detection [27] and adaptive signal filtering [28,29], it has only been employed as static classifier, in which PSO has mostly been utilized as training algorithm for the neural classifier. PSO-based RBFNN [30] and PSO-based recurrent NN [31] are examples of these hybrid dynamic classifiers.…”

Section: Related Workmentioning

confidence: 99%

An incremental framework for classification of EEG signals using quantum particle swarm optimization

Hassani

Lee

2014

2014 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applicati

View full text Add to dashboard Cite

Classification of electroencephalographic (EEG) signals is a sophisticated task that determines the accuracy of thought pattern recognition performed by computer-brain interface (BCI) which, in turn, determines the degree of naturalness of the interaction provided by that system. However, classifying the EEG signals is not a trivial task due to their nonstationary characteristics. In this paper, we introduce and utilize incremental quantum particle swarm optimization (IQPSO) algorithm for incremental classification of EEG data stream. IQPSO builds the classification model as a set of explicit rules which benefits from semantic symbolic knowledge representation and enhanced comprehensibility. We compared the performance of IQPSO against ten other classifiers on two EEG datasets. The results suggest that IQPSO outperforms other classifiers in terms of classification accuracy, precision and recall.

show abstract

“…Several recent studies combined these algorithms together, adopting a given algorithm's strong point to complement another's weakness. In so doing, a number of hybrid methods have emerged, including GA-PSO (Atyabi et al, 2012), ACO-GA (Nemati et al, 2009), ACO-neural networks (Sivagaminathan and Ramakrishnan, 2007), PSO-catfish (Chuang et al, 2011), etc. Moreover, there also exist several approaches that have embedded local search procedures (Kabir et al, 2011;Oh et al, 2004).…”

Section: Taxonomy Of Algorithmsmentioning

confidence: 99%

Nature inspired feature selection meta-heuristics

Diao

Shen

2015

Artif Intell Rev

View full text Add to dashboard Cite

This is the author accepted manuscript. The final version is available from Springer via http://dx.doi.org/10.1007/s10462-015-9428-8Many strategies have been exploited for the task of feature selection, in an effort to identify more compact and better quality feature subsets. A number of evaluation metrics have been developed recently that can judge the quality of a given feature subset as a whole, rather than assessing the qualities of individual features. Effective techniques of stochastic nature have also emerged, allowing good quality solutions to be discovered without resorting to exhaustive search. This paper provides a comprehensive review of the most recent methods for feature selection that originated from nature inspired meta-heuristics, where the more classic approaches such as genetic algorithms and ant colony optimisation are also included for comparison. A good number of the reviewed methodologies have been significantly modified in the present, in order to systematically support generic subset-based evaluators and higher dimensional problems. Such modifications are carried out because the original studies either work exclusively with certain subset evaluators (e.g., rough set-based methods), or are limited to specific problem domains. A total of ten different algorithms are examined, and their mechanisms and work flows are summarised in an unified manner. The performance of the reviewed approaches are compared using high dimensional, real-valued benchmark data sets. The selected feature subsets are also used to build classification models, in an effort to further validate their efficacies.authorsversionPeer reviewe

show abstract

Evolutionary feature selection and electrode reduction for EEG classification

Cited by 22 publications

References 16 publications

Reducing training requirements through evolutionary based dimension reduction and subject transfer

Reducing training requirements through evolutionary based dimension reduction and subject transfer

An incremental framework for classification of EEG signals using quantum particle swarm optimization

Nature inspired feature selection meta-heuristics

Contact Info

Product

Resources

About