Pattern classification to optimize the performance of Transcranial Doppler Ultrasonography-based brain machine interface

Liu, Jie; Mamun, Khondaker A.; Chau, Tom

doi:10.1016/j.patrec.2015.07.020

Cited by 17 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each regression model was built using a subset of input features (28 rs-FC features, 28 Δ rs-FC features and 8 behavioral measures as described by ANALYSES I, II and III) through a feature selection procedure. A forward sequential feature selection (SFS) was helpful in reducing the dimensions of the original data for better interpretation of features involved (He et al, 2013 ; Lu et al, 2015 ). This method searches for a subset of features that optimally models a given outcome.…”

Section: Methodsmentioning

confidence: 99%

Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning

et al. 2018

View full text Add to dashboard Cite

The primary goal of this work was to apply data-driven machine learning regression to assess if resting state functional connectivity (rs-FC) could estimate measures of behavioral domains in stroke subjects who completed brain-computer interface (BCI) intervention for motor rehabilitation. The study cohort consisted of 20 chronic-stage stroke subjects exhibiting persistent upper-extremity motor deficits who received the intervention using a closed-loop neurofeedback BCI device. Over the course of this intervention, resting state functional MRI scans were collected at four distinct time points: namely, pre-intervention, mid-intervention, post-intervention and 1-month after completion of intervention. Behavioral assessments were administered outside the scanner at each time-point to collect objective measures such as the Action Research Arm Test, Nine-Hole Peg Test, and Barthel Index as well as subjective measures including the Stroke Impact Scale. The present analysis focused on neuroplasticity and behavioral outcomes measured across pre-intervention, post-intervention and 1-month post-intervention to study immediate and carry-over effects. Rs-FC, changes in rs-FC within the motor network and the behavioral measures at preceding stages were used as input features and behavioral measures and associated changes at succeeding stages were used as outcomes for machine-learning-based support vector regression (SVR) models. Potential clinical confounding factors such as age, gender, lesion hemisphere, and stroke severity were included as additional features in each of the regression models. Sequential forward feature selection procedure narrowed the search for important correlates. Behavioral outcomes at preceding time-points outperformed rs-FC-based correlates. Rs-FC and changes associated with bilateral primary motor areas were found to be important correlates of across several behavioral outcomes and were stable upon inclusion of clinical variables as well. NIH Stroke Scale and motor impairment severity were the most influential clinical variables. Comparatively, linear SVR models aided in evaluation of contribution of individual correlates and seed regions while non-linear SVR models achieved higher performance in prediction of behavioral outcomes.

show abstract

Section: Methodsmentioning

confidence: 99%

Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…For this reason, along with their simplicity, this kind of classifiers is one of the most popular ones [31], [32], [33], [34].…”

Section: Naive Bayes Classification Methodsmentioning

confidence: 99%

Texture Classification based on Spectral Analysis and Haralick Features

Valentin

Albuquerque

et al. 2016

View full text Add to dashboard Cite

In this work we discuss a method to classify a set of texturized images based on the extraction of their Haralick Features. This kind of Classification is capable of providing texture-based measurements (such as contrast or correlation) and use them as main parameters to classify the same type of patterns in other images. In order to improve the classification success ratio a spectral analysis of the textures and, therefore, the use of filters, before the classification step, is proposed here. In this work the classification success has been evaluated using Mean and Canny filters. On the other hand, the Principal Component Analysis is used to optimize the features extracted for the patterns on each image, before introduced into the classifier. With this method the classifying success ratio for the KTH-TIPS subset and 10,000 different permutations was increased-in averagefrom 72.28% to 84.25%.

show abstract

“…The motor cortex generates the movement of arms and legs. The motor cortex consists of three parts-primary motor cortex, premotor cortex, and supplementary motor area [22]. Locating on the frontal lobe of the brain, the primary motor cortex is one of the essential brain areas that are necessary for motor function.…”

Section: Functional Areas Of Brainmentioning

confidence: 99%

“…Finding of this study show that nominated optimum neural synchronization associated with inter-hemispheric connectivity and has the potential to give users control signal to supplement adaptive brain-machine 105 interface (BMI). J. Lu et al [22] investigated the prospect of ameliorating performance in a Transcranial Doppler ultrasonography (TCD) based BCI. They used the structures and classifiers that are computationally suitable for online application by running an offline investigation of TCD recordings.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Motor Imagery Tasks from Multi-Channel EEG Data for Brain-Computer Interface Applications

Miah

Rahman

Muhammod

et al. 2020

Preprint

View full text Add to dashboard Cite

The classification of motor imagery electroencephalogram (MI-EEG) is a pivotal part of the biosignal classification in the brain-computer interface (BCI) applications. Currently, this bio-engineering based technology is being employed by researchers in various fields to develop cutting edge applications. The classification of real-time MI-EEG signal is the core computing and challenging task in these applications. It is well-known that the existing classification methods are not so accurate due to the high dimensionality and dynamic behaviors of the real-time EEG data. To improve the classification performance of real-time BCI applications, this paper presents a clustering-based ensemble technique and a developed brain game that distinguishes different human thoughts. At first, we have gathered the brain signals, extracted and selected informative features from these signals to generate training and testing sets. After that, we have constructed several classifiers using Artificial Neural Network (ANN), Support Vector Machine (SVM), naïve Bayes, Decision Tree (DT), Random Forest, Bagging, AdaBoost and compared the performance of these existing approaches with suggested clustering-based ensemble technique. On average, the proposed ensemble technique improved the classification accuracy of roughly 5 to 15% compared to the existing methods. Finally, we have developed the targeted * Corresponding author Email address: dewanfarid@cse.uiu.ac.bd (Dewan Md. Farid) brain game employing our suggested ensemble technique. In this game, realtime EEG signal classification and prediction tabulation through animated ball are controlled via threads. By playing this game, users can control the movements of the balls via the brain signals of motor imagery movements without using any traditional input devices. All relevant codes are available via open repository at: https://github.com/mrzResearchArena/MI-EEG. Keywords: Brain Computer Interface (BCI); Brain Machine Interface (BMI); Brain Engineering; Motor Imagery Electroencephalogram (MI-EEG); Motor Cortex; Clustering; Ensemble Learning. 45 are not so accurate due to the high dimensionality and dynamic behaviors of the real-time EEG data [19, 20]. Sometimes, the signals are biased with artifacts and noise due to the low conductivity of the electrodes with the scalp [1]. The objective of this paper is to extend our prior works and ameliorates the classification performance by handling multiple electrodes/ neurons data at the same 50 time. The proposed clustering-based ensemble technique clustered the dataset 3 based on the position of the electrodes so that each cluster represents dissimilar information. It also selects the model dynamically based on the electrode locations to classify real-time EEG data. We have constructed several classifiers using Artificial Neural Network (ANN), Support Vector Machine (SVM), naïve 55Bayes, Decision Tree, Random Forest, Bagging, AdaBoost and compared the performance of these existing approaches with the suggested technique. We also developed a brai...

show abstract

Pattern classification to optimize the performance of Transcranial Doppler Ultrasonography-based brain machine interface

Cited by 17 publications

References 31 publications

Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning

Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning

Texture Classification based on Spectral Analysis and Haralick Features

Prediction of Motor Imagery Tasks from Multi-Channel EEG Data for Brain-Computer Interface Applications

Contact Info

Product

Resources

About