scholarly journals Unity and diversity in working memory load: Evidence for the separability of the executive functions updating and inhibition using machine learning

2018 ◽  
Author(s):  
Tanja Krumpe ◽  
Christian Scharinger ◽  
Wolfgang Rosenstiel ◽  
Peter Gerjets ◽  
Martin Spüler
Keyword(s):  
Machine Learning ◽  
Working Memory ◽  
Executive Functions ◽  
Memory Load ◽  
Brain Computer Interface ◽  
Theoretical Models ◽  
Computer Interface ◽  
Support Vector ◽  
Learning Approaches ◽  
Eeg Data

AbstractObjectiveAccording to current theoretical models of working memory (WM), executive functions (EFs) like updating, inhibition and shifting play an important role in WM functioning. The models state that EFs highly correlate with each other but also have some individual variance which makes them separable processes. Since this theory has mostly been substantiated with behavioral data like reaction time and the ability to execute a task correctly, the aim of this paper is to find evidence for diversity (unique properties) of the EFs updating and inhibition in neural correlates of EEG data by means of using brain-computer interface (BCI) methods as a research tool. To highlight the benefit of this approach we compare this new methodology to classical analysis approaches.MethodsAn existing study has been reinvestigated by applying neurophysiological analysis in combination with support vector machine (SVM) classification on recorded electroenzephalography (EEG) data to determine the separability and variety of the two EFs updating and inhibition on a single trial basis.ResultsThe SVM weights reveal a set of distinct features as well as a set of shared features for the two EFs updating and inhibition in the theta and the alpha band power.SignificanceIn this paper we find evidence that correlates for unity and diversity of EFs can be found in neurophysiological data. Machine learning approaches reveal shared but also distinct properties for the EFs. This study shows that using methods from brain-computer interface (BCI) research, like machine learning, as a tool for the validation of psychological models and theoretical constructs is a new approach that is highly versatile and could lead to many new insights.

scholarly journals Interpreting neural decoding models using grouped model reliance

2019 ◽  
Author(s):  
Simon Valentin ◽  
Maximilian Harkotte ◽  
Tzvetan Popov
Keyword(s):  
Machine Learning ◽  
Working Memory ◽  
Memory Load ◽  
Memory Task ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Neural Decoding ◽  
Working Memory Load ◽  
Eeg Data

AbstractThe application of machine learning algorithms for decoding psychological constructs based on neural data is becoming increasingly popular. However, there is a need for methods that allow to interpret trained decoding models, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0–9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. Present results confirm previous findings in so far, as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and particularly topography varied considerably between individuals, pointing to more pronounced inter-individual differences than reported previously.Author summaryModern machine learning algorithms currently receive considerable attention for their predictive power in neural decoding applications. However, there is a need for methods that make such predictive models interpretable. In the present work, we address the problem of assessing which aspects of the input data a trained model relies upon to make predictions. We demonstrate the use of grouped model-reliance as a generally applicable method for interpreting neural decoding models. Illustrating the method on a case study, we employed an experimental design in which a comparably small number of participants (10) completed a large number of trials (972) over multiple electroencephalography (EEG) recording sessions from a Sternberg working memory task. Trained decoding models consistently relied on alpha frequency activity, which is in line with existing research on the relationship between neural oscillations and working memory. However, our analyses also indicate large inter-individual variability with respect to the relation between activity patterns and working memory load in frequency and topography. Taken together, we argue that grouped model reliance provides a useful tool to better understand the workings of (sometimes otherwise black-box) decoding models.

Practical Artifact Removal Brain-Computer Interface System

2014 ◽  
pp. 265-277
Author(s):  
Wei-Yen Hsu
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Support Vector ◽  
Artifact Removal ◽  
Eeg Data ◽  
Interface System ◽  
Electroencephalogram Eeg ◽  
Bci System

In this chapter, a practical artifact removal Brain-Computer Interface (BCI) system for single-trial Electroencephalogram (EEG) data is proposed for applications in neuroprosthetics. Independent Component Analysis (ICA) combined with the use of a correlation coefficient is proposed to remove the EOG artifacts automatically, which can further improve classification accuracy. The features are then extracted from wavelet transform data by means of the proposed modified fractal dimension. Finally, Support Vector Machine (SVM) is used for the classification. When compared with the results obtained without using the EOG signal elimination, the proposed BCI system achieves promising results that will be effectively applied in neuroprosthetics.

scholarly journals Statistical Feature Extraction and Classification using Machine Learning Techniques in Brain-Computer Interface

2020 ◽  
Vol 9 (3) ◽  
pp. 1754-1758
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Brain Computer Interface ◽  
Essential Feature ◽  
Average Energy ◽  
Machine Learning Techniques ◽  
Computer Interface ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Learning Techniques

Brain Computer Interface is a paralyzed system. This system is used for direct communication between brain nerves and computer devices. BCI is an imagery movement of the patients who are all unable to communicate with the people. In EEG signals feature extraction plays an important role. Statistical based features are essential feature being used in machine learning applications. Researchers mainly focus on the filters and feature extraction techniques. In this paper data are collected from the BCI Competition III dataset 1a. Statistical features like minimum, maximum, standard deviation, variance, skewnesss, kurtosis, root mean square, average, energy, contrast, correlation and Homogeneity are extracted. Classification is done using machine learning techniques such as Support Vector Machine, Artificial Neural Network and K-Nearest Neighbor. In the proposed system 90.6% accuracy is achieved

scholarly journals Unity and diversity in working memory load: Evidence for the separability of the executive functions updating and inhibition using machine learning

2018 ◽  
Vol 139 ◽  
pp. 163-172 ◽  
Author(s):  
Tanja Krumpe ◽  
Christian Scharinger ◽  
Wolfgang Rosenstiel ◽  
Peter Gerjets ◽  
Martin Spüler
Keyword(s):  
Machine Learning ◽  
Working Memory ◽  
Executive Functions ◽  
Memory Load ◽  
Working Memory Load

scholarly journals Electroencephalogram with Machine Learning for Estimation of Mental Confusion Level

2019 ◽  
Vol 9 (2) ◽  
pp. 761-765
Keyword(s):  
Machine Learning ◽  
Concentration Level ◽  
Brain Computer Interface ◽  
Quantitative Measure ◽  
Threshold Value ◽  
Machine Learning Algorithms ◽  
Computer Interface ◽  
Eeg Data ◽  
The Brain ◽  
Bci System

Estimating the mental state of an individual is crucial to many applications. A quantitative measure of the confusion one faces while doing a task can be useful in determining which subtask is the most difficult. This paper thus aims to develop an algorithm to estimate the confusion score using EEG signals collected using a Neurosky Mindwave Headset. Also, a full contextual audio based confusion score is generated to improve the system's resilience. In this paper, the final algorithm is used to propose an EEG based system to enable the UI/UX testing which can help in confusion estimation and thus provide a qualitative means to measure the attention and concentration level of people which can be extended to various applications. The raw EEG data collected from the device was used to calculate the confusion score using various Machine Learning algorithms. This brain computer interface (BCI) system can be extended for calculating the confusion score of a person which can be used for various applications such as teaching, child health monitoring, suicide prevention, mental health analysis etc. The brain computer interface thus calculates the confusion score and based on the threshold value of the attention and concentration level it performs certain actions such as sending messages and alerts to emergency contacts. This is further extended to solve the problem of Usability testing in Human Computer Interaction.

An Auditory Brain-Computer Interface Based on Dichotic Listening Paradigm

2014 ◽  
Vol 1030-1032 ◽  
pp. 2360-2363
Author(s):  
Hai Juan Gao ◽  
Lei Wang ◽  
Ping Wang
Keyword(s):  
Dichotic Listening ◽  
Brain Computer Interface ◽  
Sound Stimulus ◽  
Computer Interface ◽  
Support Vector ◽  
Detection Accuracy ◽  
Latency Range ◽  
Multiple Electrodes ◽  
Eeg Data ◽  
The Subject

This study proposes a novel auditory brain–computer interface (BCI) based on dichotic listening paradigm, which allows the subject to select a target from two different sound stimulus sequences played in each ear. EEG data from 6 subjects has shown that the amplitude of N200 and P300 elicited by target was significantly higher than that of non-target ones. We found the N2ac component: a negativity wave in the N2 latency range at anterior contralateral electrodes. The target detection accuracy was assessed by support vector machine (SVM). The accuracy based on multiple electrodes is higher than a single electrode. The dichotic listening paradigm can be used for binary-class of brain-computer interface system.

Artefacts Removal to Detect Visual Evoked Potentials in Brain Computer Interface Systems

2019 ◽  
Vol 41 ◽  
pp. 91-103 ◽  
Author(s):  
Hamidreza Abbaspour ◽  
Nasser Mehrshad ◽  
Seyyed Mohammad Razavi ◽  
Luca Mesin
Keyword(s):  
Brain Computer Interface ◽  
Computer Interface ◽  
Support Vector ◽  
Automated Method ◽  
Processing Step ◽  
Eeg Data ◽  
Potential Applications ◽  
Scalp Electroencephalogram ◽  
Electrode Connection ◽  
Visual Evoked

The interference of artefacts with evoked scalp electroencephalogram (EEG) responses is a problem in event related brain computer interface (BCI) system that reduces signal quality and interpretability of user's intentions. Many strategies have been proposed to reduce the effects of non-neural artefacts, while the activity of neural sources that do not reflect the considered stimulation has been neglected. However discerning such activities from those to be retained is important, but subtle and difficult as most of their features are the same. We propose an automated method based on a combination of a genetic algorithm (GA) and a support vector machine (SVM) to select only the sources of interest. Temporal, spectral, wavelet, autoregressive and spatial properties of independent components (ICs) of EEG are inspected. The method selects the most distinguishing subset of features among this comprehensive fused set of information and identifies the components to be preserved. EEG data were recorded from 12 healthy subjects in a visual evoked potential (VEP) based BCI paradigm and the corresponding ICs were classified by experts to train and test the algorithm. They were contaminated with different sources of artefacts, including electromyogram (EMG), electrode connection problems, blinks and electrocardiogram (ECG), together with neural contributions not related to VEPs. The accuracy of ICs classification was about 88.5% and the energetic residual error in recovering the clean signals was 3%. These performances indicate that this automated method can effectively identify and remove main artefacts derived from either neural or non-neural sources while preserving VEPs. This could have important potential applications, contributing to speed and remove subjectivity of the cleaning procedure by experts. Moreover, it could be included in a real time BCI as a pre-processing step before the identification of the user’s intention.

Sign in / Sign up

Export Citation Format

Share Document