Comparisons Between Motor Area Eeg and All-Channels Eeg for Two Algorithms in Motor Imagery Task Classification

Siuly, Siuly; Li, Yan; Wen, Peng

doi:10.4015/s1016237214500409

Cited by 12 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses 10-fold cross-validation [22,23,33] process to assess the performance of the proposed approach. In 10-fold cross-validation procedure, a data set is partitioned into 10 mutually exclusive subsets (folds) of approximately equal size and the method is repeated 10 times.…”

Section: Performance Evaluationmentioning

confidence: 99%

Detection of motor imagery EEG signals employing Naïve Bayes based learning process

2016

View full text Add to dashboard Cite

The objective of this study is to develop a reliable and robust analysis system that can automatically detect motor imagery (MI) based electroencephalogram (EEG) signals for the development of brain-computer interface (BCI) systems. The detection of MI tasks provides an important basis for designing a communication way between brain and computer in creating devices for people with motor disabilities. This paper presents a synthesis approach based on optimum allocation system and Naive Bayes (NB) algorithm for detecting mental states based on EEG signals. In this study, an optimal allocation (OA) is introduced to discover the most effective representatives with minimal variability from a large number of MI based EEG data and the NB classifier is employed on the extracted features for discriminating the MI signals. The feasibility and effectiveness of the proposed method is demonstrated by analyzing the results and its success on two public benchmark datasets. The results indicate that the proposed approach outperforms the most recently reported five methods and achieves 0.64%-20.90% improvement on average accuracy. The performances of this proposed approach implies that it can be reliably used to detect EEG based MI activity and can be a promising avenue for EEG based BCI applications.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Detection of motor imagery EEG signals employing Naïve Bayes based learning process

2016

View full text Add to dashboard Cite

show abstract

“…Siuly et al [ 47 ] conducted a comparative analysis for 18 and 118 channels motor imagery dataset IVa and IVb using two classification algorithms. Their study concludes that 118 channel results outperform 18 channels in terms of classification outcomes.…”

Section: Resultsmentioning

confidence: 99%

“…Dataset IVb has a maximum gain of 16.6% and 47.1% for FFNN and SVM classifiers, respectively. It accredits the significance of using 118 channels for SDI features and advocates the channel comparison study performed by Siuly et al [ 47 ]. One interesting observation is made that subject “ay” of dataset IVa has above 90% classification accuracy for all channel combinations and classifiers.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Motor and Mental Imagery EEG in Two and Multiclass Subject-Dependent Tasks Using Successive Decomposition Index

Sadiq

Yuan

et al. 2020

Sensors

View full text Add to dashboard Cite

The development of fast and robust brain–computer interface (BCI) systems requires non-complex and efficient computational tools. The modern procedures adopted for this purpose are complex which limits their use in practical applications. In this study, for the first time, and to the best of our knowledge, a successive decomposition index (SDI)-based feature extraction approach is utilized for the classification of motor and mental imagery electroencephalography (EEG) tasks. First of all, the public datasets IVa, IVb, and V from BCI competition III were denoised using multiscale principal analysis (MSPCA), and then a SDI feature was calculated corresponding to each trial of the data. Finally, six benchmark machine learning and neural network classifiers were used to evaluate the performance of the proposed method. All the experiments were performed for motor and mental imagery datasets in binary and multiclass applications using a 10-fold cross-validation method. Furthermore, computerized automatic detection of motor and mental imagery using SDI (CADMMI-SDI) is developed to describe the proposed approach practically. The experimental results suggest that the highest classification accuracy of 97.46% (Dataset IVa), 99.52% (Dataset IVb), and 99.33% (Dataset V) was obtained using feedforward neural network classifier. Moreover, a series of experiments, namely, statistical analysis, channels variation, classifier parameters variation, processed and unprocessed data, and computational complexity, were performed and it was concluded that SDI is robust for noise, and a non-complex and efficient biomarker for the development of fast and accurate motor and mental imagery BCI systems.

show abstract

“…3. Channel selection is the first step to reduce the computational burden and avoid data redundancy that in turns helps better classification of signals [34,35,36]. Not all BCI involves all the frequency bands to be analyzed.…”

Section: Literature Review On Components Of Mi-based Bcimentioning

confidence: 99%

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Rahman¹,

Joadder²

2017

Appl. Theory Comput. Technol.

View full text Add to dashboard Cite

Motor Imagery (MI) is a voluntary modulation of brain signals for specific action without real limb movement. It is essential to classify MI signal to design a brain computer interface (BCI). BCI involves a number of signal processing steps, and a lot of techniques have been developed for each step. There can be numerous combinations of these techniques at different steps that can be employed to design a BCI. This work focuses on MI-based BCI using EEG signal and reviews the existing techniques. More importantly, a detailed comparative study is performed to explore the important combinations of methods by comparing their performance quantitatively. Often a method, which performs very good in one combination, can be bad performer in other combinations and it is a dilemma for the researchers to select appropriate methods for their desired BCI application.In our performance analysis, we have systematically included the variations of methods in each step of BCI such that it gives idea to BCI researchers how each method in one step fits best with specific combinations of methods in other steps. We have shown that how much each step is sensitive towards overall performance of the BCI system.We hope that this work helps, especially for new researchers, to provide a better guideline for designing more efficient BCI system.

show abstract

Comparisons Between Motor Area Eeg and All-Channels Eeg for Two Algorithms in Motor Imagery Task Classification

Cited by 12 publications

References 28 publications

Detection of motor imagery EEG signals employing Naïve Bayes based learning process

Detection of motor imagery EEG signals employing Naïve Bayes based learning process

Identification of Motor and Mental Imagery EEG in Two and Multiclass Subject-Dependent Tasks Using Successive Decomposition Index

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Contact Info

Product

Resources

About