Abstract: The goal of motor image brain computer interface research is to create a link between the central nervous system and a computer or device. The most important signal for brain-computer interface is the electroencephalogram. The aim of this research is to explore a set of effective features from EEG signals, separated into frequency bands, using wave atom sub-bands to discriminate right and left-hand motor imagery signals. Over the transform coefficients, feature vectors are constructed for each frequency range and each transform sub-band, and their classification performances are tested. The method is validated using EEG signals from the BCI competition III dataset IIIa and classifiers such as support vector machine and k-nearest neighbors.
Abstract: The aim of the brain-computer interface studies on electroencephalogram (EEG) signals containing motor imagery is to extract the effective features that will provide the highest possible classification accuracy for the detection of the desired motor movement. However, achieving this goal is difficult as the most suitable frequency band and time frame vary from subject to subject. In this study, the classification success of the two-feature data obtained from raw EEG signals and the coefficients of the multi-resolution analysis method applied to the EEG signals were analyzed comparatively. The method was applied to several EEG channels (C3, Cz and C4) signals obtained from the EEG data set belonging to the publicly available BCI competition III.
Abstract: Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.
Abstract: Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.
Abstract: This study presents a framework for development of a
new generation of therapy robots that can interact with users by
monitoring their physiological and mental states. Here, we focused
on one of the controversial methods of therapy, hypnotherapy.
Hypnosis has shown to be useful in treatment of many clinical
conditions. But, even for healthy people, it can be used as an
effective technique for relaxation or enhancement of memory and
concentration. Our aim is to develop a robot that collects information
about user’s mental and physical states using electroencephalogram
(EEG) and electromyography (EMG) signals and performs costeffective
hypnosis at the comfort of user’s house. The presented
framework consists of three main steps: (1) Find the EEG-correlates
of mind state before, during, and after hypnosis and establish a
cognitive model for state changes, (2) Develop a system that can
track the changes in EEG and EMG activities in real time and
determines if the user is ready for suggestion, and (3) Implement our
system in a humanoid robot that will talk and conduct hypnosis on
users based on their mental states. This paper presents a pilot study in
regard to the first stage, detection of EEG and EMG features during
hypnosis.
Abstract: Fluid intelligence declines along with age, but it can be developed. For this reason, increasing fluid intelligence in young adults can be possible. This study examined the effects of a two-month treadmill exercise program on fluid intelligence. The researcher designed a treadmill exercise program to promote cardiorespiratory fitness. Thirty-eight healthy voluntary students from the Boromarajonani College of Nursing, Chon Buri were assigned randomly to an exercise group (n=18) and a control group (n=20). The experiment consisted of three sessions: The baseline session consisted of measuring the VO2max, electroencephalogram and behavioral response during performed the Raven Progressive Matrices (RPM) test, a measure of fluid intelligence. For the exercise session, an experimental group exercises using treadmill training at 60 % to 80 % maximum heart rate for 30 mins, three times per week, whereas the control group did not exercise. For the following two sessions, each participant was measured the same as baseline testing. The data were analyzed using the t-test to examine whether there is significant difference between the means of the two groups. The results showed that the mean VO2 max in the experimental group were significantly more than the control group (p
Abstract: The P300 from Event related potential (ERP) explains the psycho-physiological phenomenon in human body. The present study aims to identify the differences of amplitude and latency of P300 component from auditory stimuli, between ambiversion and extraversion types of personality. Ambivert (N=20) and extravert (N=20) undergoing ERP recording at the Hospital Universiti Sains Malaysia (HUSM) laboratory. Electroencephalogram data was recorded with oddball paradigm, counting auditory standard and target tones, from nine electrode sites (Fz, Cz, Pz, T3, T4, T5, T6, P3 and P4) by using the 128 HydroCel Geodesic Sensor Net. The P300 latency of the target tones at all electrodes were insignificant. Similarly, the P300 latency of the standard tones were also insignificant except at Fz and T3 electrode. Likewise, the P300 amplitude of the target and standard tone in all electrode sites were insignificant. Extravert and ambivert indicate similar characteristic in cognition processing from auditory task.
Abstract: This paper presents a multiscale information measure of
Electroencephalogram (EEG) for analysis with a short data length.
A multiscale extension of permutation entropy (MPE) is capable of
fully reflecting the dynamical characteristics of EEG across different
temporal scales. However, MPE yields an imprecise estimation due
to coarse-grained procedure at large scales. We present an improved
MPE measure to estimate entropy more accurately with a short
time series. By computing entropies of all coarse-grained time series
and averaging those at each scale, it leads to the modified MPE
(MMPE) which provides an enhanced accuracy as compared to
MPE. Simulation and experimental studies confirmed that MMPE
has proved its capability over MPE in terms of accuracy.
Abstract: An experiment to verify the relationships between
physiological indexes of an e-learner and the presence or absence of an
operation during e-learning is described. Electroencephalogram
(EEG), hemoencephalography (HEG), skin conductance (SC), and
blood volume pulse (BVP) values were measured while participants
performed experimental learning tasks. The results show that there are
significant differences between the SC values when reading with
clicking on learning materials and the SC values when reading without
clicking, and between the HEG ratio when reading (with and without
clicking) and the HEG ratio when resting for four of five participants.
We conclude that the SC signals can be used to estimate whether or not
a learner is performing an active task and that the HEG ratios can be
used to estimate whether a learner is learning.
Abstract: Neural activity in the human brain starts from the
early stages of prenatal development. This activity or signals
generated by the brain are electrical in nature and represent not only
the brain function but also the status of the whole body. At the
present moment, three methods can record functional and
physiological changes within the brain with high temporal resolution
of neuronal interactions at the network level: the
electroencephalogram (EEG), the magnet oencephalogram (MEG),
and functional magnetic resonance imaging (fMRI); each of these has
advantages and shortcomings. EEG recording with a large number of
electrodes is now feasible in clinical practice. Multichannel EEG
recorded from the scalp surface provides very valuable but indirect
information about the source distribution. However, deep electrode
measurements yield more reliable information about the source
locations intracranial recordings and scalp EEG are used with the
source imaging techniques to determine the locations and strengths of
the epileptic activity. As a source localization method, Low
Resolution Electro-Magnetic Tomography (LORETA) is solved for
the realistic geometry based on both forward methods, the Boundary
Element Method (BEM) and the Finite Difference Method (FDM). In
this paper, we review the findings EEG- LORETA about epilepsy.
Abstract: Cerebellar ataxia is a steadily progressive
neurodegenerative disease associated with loss of motor control,
leaving patients unable to walk, talk, or perform activities of daily
living. Direct motor instruction in cerebella ataxia patients has limited
effectiveness, presumably because an inappropriate closed-loop
cerebellar response to the inevitable observed error confounds motor
learning mechanisms. Could the use of EEG based BCI provide
advanced biofeedback to improve motor imagery and provide a
“backdoor” to improving motor performance in ataxia patients? In
order to determine the feasibility of using EEG-based BCI control in
this population, we compare the ability to modulate mu-band power
(8-12 Hz) by performing a cued motor imagery task in an ataxia
patient and healthy control.
Abstract: We present a refined multiscale Shannon entropy for
analyzing electroencephalogram (EEG), which reflects the underlying
dynamics of EEG over multiple scales. The rationale behind
this method is that neurological signals such as EEG possess
distinct dynamics over different spectral modes. To deal with the
nonlinear and nonstationary nature of EEG, the recently developed
empirical mode decomposition (EMD) is incorporated, allowing a
decomposition of EEG into its inherent spectral components, referred
to as intrinsic mode functions (IMFs). By calculating the Shannon
entropy of IMFs in a time-dependent manner and summing them over
adaptive multiple scales, it results in an adaptive subscale entropy
measure of EEG. Simulation and experimental results show that
the proposed entropy properly reveals the dynamical changes over
multiple scales.
Abstract: This work proposes a data-driven multiscale based
quantitative measures to reveal the underlying complexity of
electroencephalogram (EEG), applying to a rodent model of
hypoxic-ischemic brain injury and recovery. Motivated by that real
EEG recording is nonlinear and non-stationary over different
frequencies or scales, there is a need of more suitable approach over
the conventional single scale based tools for analyzing the EEG data.
Here, we present a new framework of complexity measures
considering changing dynamics over multiple oscillatory scales. The
proposed multiscale complexity is obtained by calculating entropies of
the probability distributions of the intrinsic mode functions extracted
by the empirical mode decomposition (EMD) of EEG. To quantify
EEG recording of a rat model of hypoxic-ischemic brain injury
following cardiac arrest, the multiscale version of Tsallis entropy is
examined. To validate the proposed complexity measure, actual EEG
recordings from rats (n=9) experiencing 7 min cardiac arrest followed
by resuscitation were analyzed. Experimental results demonstrate that
the use of the multiscale Tsallis entropy leads to better discrimination
of the injury levels and improved correlations with the neurological
deficit evaluation after 72 hours after cardiac arrest, thus suggesting an
effective metric as a prognostic tool.
Abstract: Electroencephalogram (EEG) is a noninvasive
technique that registers signals originating from the firing of neurons
in the brain. The Emotiv EEG Neuroheadset is a consumer product
comprised of 14 EEG channels and was used to record the reactions
of the neurons within the brain to two forms of stimuli in 10
participants. These stimuli consisted of auditory and visual formats
that provided directions of ‘right’ or ‘left.’ Participants were
instructed to raise their right or left arm in accordance with the
instruction given. A scenario in OpenViBE was generated to both
stimulate the participants while recording their data. In OpenViBE,
the Graz Motor BCI Stimulator algorithm was configured to govern
the duration and number of visual stimuli. Utilizing EEGLAB under
the cross platform MATLAB®, the electrodes most stimulated during
the study were defined. Data outputs from EEGLAB were analyzed
using IBM SPSS Statistics® Version 20. This aided in determining
the electrodes to use in the development of a brain-machine interface
(BMI) using real-time EEG signals from the Emotiv EEG
Neuroheadset. Signal processing and feature extraction were
accomplished via the Simulink® signal processing toolbox. An
Arduino™ Duemilanove microcontroller was used to link the Emotiv
EEG Neuroheadset and the right and left Mecha TE™ Hands.
Abstract: The study of the electrical signals produced by neural
activities of human brain is called Electroencephalography. In this
paper, we propose an automatic and efficient EEG signal
classification approach. The proposed approach is used to classify the
EEG signal into two classes: epileptic seizure or not. In the proposed
approach, we start with extracting the features by applying Discrete
Wavelet Transform (DWT) in order to decompose the EEG signals
into sub-bands. These features, extracted from details and
approximation coefficients of DWT sub-bands, are used as input to
Principal Component Analysis (PCA). The classification is based on
reducing the feature dimension using PCA and deriving the supportvectors
using Support Vector Machine (SVM). The experimental are
performed on real and standard dataset. A very high level of
classification accuracy is obtained in the result of classification.
Abstract: This paper discusses on power spectral density (PSD) characteristics which are extracted from three-dimensional (3D) electroencephalogram (EEG) models. The EEG signal recording was conducted on 150 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, the values of maximum PSD were extracted as features from the model. These features are analyzed using mean relative power (MRP) and different mean relative power (DMRP) technique to observe the pattern among different brain balancing indexes. The results showed that by implementing these techniques, the pattern of brain balancing indexes can be clearly observed. Some patterns are indicates between index 1 to index 5 for left frontal (LF) and right frontal (RF).
Abstract: Brain tumor is inherently serious and life-threatening disease. Brain tumor builds the intracranial pressure in the brain, by shifting the brain or pushing against the skull, and also damaging nerves and healthy brain tissues. This intracranial pressure affects and interferes with normal brain functionality, which results in generation of abnormal electrical activities from brain. With recent development in the medical engineering and instruments, EEG instruments are able to record the brain electric activities with high accuracy, which establishes EEG as a primary tool for diagnosing the brain abnormalities. Research scholars and general physicians, often face difficulty in understanding EEG patterns. This paper presents the EEG patterns associated with brain tumor by combing medicine theory and neurologist experience. Paper also explains the pros-cons of the EEG based brain tumor identification.
Abstract: Real time non-invasive Brain Computer Interfaces have a significant progressive role in restoring or maintaining a quality life for medically challenged people. This manuscript provides a comprehensive review of emerging research in the field of cognitive/affective computing in context of human neural responses. The perspectives of different emotion assessment modalities like face expressions, speech, text, gestures, and human physiological responses have also been discussed. Focus has been paid to explore the ability of EEG (Electroencephalogram) signals to portray thoughts, feelings, and unspoken words. An automated workflow-based protocol to design an EEG-based real time Brain Computer Interface system for analysis and classification of human emotions elicited by external audio/visual stimuli has been proposed. The front end hardware includes a cost effective and portable Emotiv EEG Neuroheadset unit, a personal computer and a set of external stimulators. Primary signal analysis and processing of real time acquired EEG shall be performed using MATLAB based advanced brain mapping toolbox EEGLab/BCILab. This shall be followed by the development of MATLAB based self-defined algorithm to capture and characterize temporal and spectral variations in EEG under emotional stimulations. The extracted hybrid feature set shall be used to classify emotional states using artificial intelligence tools like Artificial Neural Network. The final system would result in an inexpensive, portable and more intuitive Brain Computer Interface in real time scenario to control prosthetic devices by translating different brain states into operative control signals.
Abstract: In this paper we propose a new classification method for automatic sleep scoring using an artificial neural network based decision tree. It attempts to treat sleep scoring progress as a series of two-class problems and solves them with a decision tree made up of a group of neural network classifiers, each of which uses a special feature set and is aimed at only one specific sleep stage in order to maximize the classification effect. A single electroencephalogram (EEG) signal is used for our analysis rather than depending on multiple biological signals, which makes greatly simplifies the data acquisition process. Experimental results demonstrate that the average epoch by epoch agreement between the visual and the proposed method in separating 30s wakefulness+S1, REM, S2 and SWS epochs was 88.83%. This study shows that the proposed method performed well in all the four stages, and can effectively limit error propagation at the same time. It could, therefore, be an efficient method for automatic sleep scoring. Additionally, since it requires only a small volume of data it could be suited to pervasive applications.
Abstract: A technique proposed for the automatic detection
of spikes in electroencephalograms (EEG). A multi-resolution
approach and a non-linear energy operator are exploited. The
signal on each EEG channel is decomposed into three sub bands
using a non-decimated wavelet transform (WT). The WT is a
powerful tool for multi-resolution analysis of non-stationary signal
as well as for signal compression, recognition and restoration.
Each sub band is analyzed by using a non-linear energy operator,
in order to detect spikes. A decision rule detects the presence of
spikes in the EEG, relying upon the energy of the three sub-bands.
The effectiveness of the proposed technique was confirmed by
analyzing both test signals and EEG layouts.