Emotion processing has been a focus of research in psychology and neuroscience for some decades. ... more Emotion processing has been a focus of research in psychology and neuroscience for some decades. While the evoked neural markers in human brain activations in response to different emotions have been reported, the temporal dynamics of emotion processing has received less attention. Differences in processing speeds, that depend on emotion type, have not been determined. Furthermore, behavioral studies have found that the right side of the human face expresses emotions more accurately than the left side. Therefore, accounting for both the content of the emotion and the visual angle of presentation from the perspective of the viewer, here we have investigated variability in the discrimination of happy and sad faces when the visual angle of presentation was Positive (right side of the face) compared to Negative (left side of the face). Furthermore, the temporal dynamics involved in processing happy and sad emotions have been compared. Regardless of visual angle, happy emotions were proc...
The motor imagery (MI) based BCI uses cortical activations resulting from MI tasks to create a di... more The motor imagery (MI) based BCI uses cortical activations resulting from MI tasks to create a direct communication link between human brain and computing devices. Its major advantage is that it can facilitate a self-paced natural communication channel between the user and assistive systems as well as has potential to support motor recovery in post-stroke paralysis. However, several factors such as non-stationary brainwaves, and time-varying electrode characteristics and mental states, may degrade its performance significantly [1]. Additionally, some subjects are not so good in performing MI, categorised as having BCI aphasia but do improve with practice. Also, in motor recovery applications, initial moderate performance of novice stroke sufferers may cause frustration and impede recovery. To account for these performance degrading effects, recently we have undertaken investigations in primarily in three main areas: signal processing, multi-sensor integration, and applications invol...
Previous studies have demonstrated that musical deviants (syntactically irregular chords) elicit ... more Previous studies have demonstrated that musical deviants (syntactically irregular chords) elicit event related potentials/fields with negative polarity; specifically, the early right anterior negativity and the right anterior temporal negativity responses with peak latencies at ~200 ms and ~350 ms, respectively, post stimulus onset. Here, we investigated differences in the neural dynamics of the auditory perceptual system of individuals with music training compared to those with no music training. Magnetoencephalography was used to examine the neural response to a deviant sound when the auditory system was primed using stimulus entrainment to evoke an auditory gamma-band response between 31 Hz and 39 Hz, in 2 Hz steps. Participants responded to the harmonic relationship between the entrainment stimulus and the subsequent target stimulus. Gamma frequencies carry stimulus information; thus, the paradigm primed the auditory system with a known gamma frequency and evaluated any improvem...
Dementia is a collection of symptoms associated with impaired cognition and impedes everyday norm... more Dementia is a collection of symptoms associated with impaired cognition and impedes everyday normal functioning. Dementia, with Alzheimer's disease constituting its most common type, is highly complex in terms of etiology and pathophysiology. A more quantitative or computational attitude towards dementia research, or more generally in neurology, is becoming necessary - Computational Neurology. We provide a focused review of some computational approaches that have been developed and applied to the study of dementia, particularly Alzheimer's disease. Both mechanistic modeling and data-drive, including AI or machine learning, approaches are discussed. Linkage to clinical decision support systems for dementia diagnosis will also be discussed.
References o We have explored an application of the empirical mode decomposition (EMD) based filt... more References o We have explored an application of the empirical mode decomposition (EMD) based filtering method for enhancing performance of wrist movements in brain-computer interface (BCI). o The proposed method identifies a combination of IMFs whose maximum frequency falls in the low frequency band (<8 Hz). o It has provided improvement in the accuracy with sample entropy feature to classify multi direction wrist movement signals as compared to BCI competition winners.
Objective. Magnetoencephalography (MEG) based brain–computer interface (BCI) involves a large num... more Objective. Magnetoencephalography (MEG) based brain–computer interface (BCI) involves a large number of sensors allowing better spatiotemporal resolution for assessing brain activity patterns. There have been many efforts to develop BCI using MEG with high accuracy, though an increase in the number of channels (NoC) means an increase in computational complexity. However, not all sensors necessarily contribute significantly to an increase in classification accuracy (CA) and specifically in the case of MEG-based BCI no channel selection methodology has been performed. Therefore, this study investigates the effect of channel selection on the performance of MEG-based BCI. Approach. MEG data were recorded for two sessions from 15 healthy participants performing motor imagery, cognitive imagery and a mixed imagery task pair using a unique paradigm. Performance of four state-of-the-art channel selection methods (i.e. Class-Correlation, ReliefF, Random Forest, and Infinite Latent Feature Se...
A brain–machine interface (BMI) is a biohybrid system intended as an alternative communication ch... more A brain–machine interface (BMI) is a biohybrid system intended as an alternative communication channel for people suffering from severe motor impairments. A BMI can involve either invasively implanted electrodes or non-invasive imaging systems. The focus in this chapter is on non-invasive approaches; EEG-based BMI is the most widely investigated. Event-related de-synchronization/ synchronization (ERD/ERS) of sensorimotor rhythms (SMRs), P300, and steady-state visual evoked potential (SSVEP) are the three main cortical activation patterns used for designing an EEG-based BMI. A BMI involves multiple stages: brain data acquisition, pre-processing, feature extraction, and feature classification, along with a device to communicate or control with or without neurofeedback. Despite extensive research worldwide, there are still several challenges to be overcome in making BMI practical for daily use. One such is to account for non-stationary brainwaves dynamics. Also, some people may initial...
Computerized clinical decision support systems can help to provide objective, standardized, and t... more Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on the group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer’s disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and k-Nearest Neighbor (kNNreg) for regression and Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbor (kNNclass) for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predicti...
Emotion processing has been a focus of research in psychology and neuroscience for some decades. ... more Emotion processing has been a focus of research in psychology and neuroscience for some decades. While the evoked neural markers in human brain activations in response to different emotions have been reported, the temporal dynamics of emotion processing has received less attention. Differences in processing speeds, that depend on emotion type, have not been determined. Furthermore, behavioral studies have found that the right side of the human face expresses emotions more accurately than the left side. Therefore, accounting for both the content of the emotion and the visual angle of presentation from the perspective of the viewer, here we have investigated variability in the discrimination of happy and sad faces when the visual angle of presentation was Positive (right side of the face) compared to Negative (left side of the face). Furthermore, the temporal dynamics involved in processing happy and sad emotions have been compared. Regardless of visual angle, happy emotions were proc...
The motor imagery (MI) based BCI uses cortical activations resulting from MI tasks to create a di... more The motor imagery (MI) based BCI uses cortical activations resulting from MI tasks to create a direct communication link between human brain and computing devices. Its major advantage is that it can facilitate a self-paced natural communication channel between the user and assistive systems as well as has potential to support motor recovery in post-stroke paralysis. However, several factors such as non-stationary brainwaves, and time-varying electrode characteristics and mental states, may degrade its performance significantly [1]. Additionally, some subjects are not so good in performing MI, categorised as having BCI aphasia but do improve with practice. Also, in motor recovery applications, initial moderate performance of novice stroke sufferers may cause frustration and impede recovery. To account for these performance degrading effects, recently we have undertaken investigations in primarily in three main areas: signal processing, multi-sensor integration, and applications invol...
Previous studies have demonstrated that musical deviants (syntactically irregular chords) elicit ... more Previous studies have demonstrated that musical deviants (syntactically irregular chords) elicit event related potentials/fields with negative polarity; specifically, the early right anterior negativity and the right anterior temporal negativity responses with peak latencies at ~200 ms and ~350 ms, respectively, post stimulus onset. Here, we investigated differences in the neural dynamics of the auditory perceptual system of individuals with music training compared to those with no music training. Magnetoencephalography was used to examine the neural response to a deviant sound when the auditory system was primed using stimulus entrainment to evoke an auditory gamma-band response between 31 Hz and 39 Hz, in 2 Hz steps. Participants responded to the harmonic relationship between the entrainment stimulus and the subsequent target stimulus. Gamma frequencies carry stimulus information; thus, the paradigm primed the auditory system with a known gamma frequency and evaluated any improvem...
Dementia is a collection of symptoms associated with impaired cognition and impedes everyday norm... more Dementia is a collection of symptoms associated with impaired cognition and impedes everyday normal functioning. Dementia, with Alzheimer's disease constituting its most common type, is highly complex in terms of etiology and pathophysiology. A more quantitative or computational attitude towards dementia research, or more generally in neurology, is becoming necessary - Computational Neurology. We provide a focused review of some computational approaches that have been developed and applied to the study of dementia, particularly Alzheimer's disease. Both mechanistic modeling and data-drive, including AI or machine learning, approaches are discussed. Linkage to clinical decision support systems for dementia diagnosis will also be discussed.
References o We have explored an application of the empirical mode decomposition (EMD) based filt... more References o We have explored an application of the empirical mode decomposition (EMD) based filtering method for enhancing performance of wrist movements in brain-computer interface (BCI). o The proposed method identifies a combination of IMFs whose maximum frequency falls in the low frequency band (<8 Hz). o It has provided improvement in the accuracy with sample entropy feature to classify multi direction wrist movement signals as compared to BCI competition winners.
Objective. Magnetoencephalography (MEG) based brain–computer interface (BCI) involves a large num... more Objective. Magnetoencephalography (MEG) based brain–computer interface (BCI) involves a large number of sensors allowing better spatiotemporal resolution for assessing brain activity patterns. There have been many efforts to develop BCI using MEG with high accuracy, though an increase in the number of channels (NoC) means an increase in computational complexity. However, not all sensors necessarily contribute significantly to an increase in classification accuracy (CA) and specifically in the case of MEG-based BCI no channel selection methodology has been performed. Therefore, this study investigates the effect of channel selection on the performance of MEG-based BCI. Approach. MEG data were recorded for two sessions from 15 healthy participants performing motor imagery, cognitive imagery and a mixed imagery task pair using a unique paradigm. Performance of four state-of-the-art channel selection methods (i.e. Class-Correlation, ReliefF, Random Forest, and Infinite Latent Feature Se...
A brain–machine interface (BMI) is a biohybrid system intended as an alternative communication ch... more A brain–machine interface (BMI) is a biohybrid system intended as an alternative communication channel for people suffering from severe motor impairments. A BMI can involve either invasively implanted electrodes or non-invasive imaging systems. The focus in this chapter is on non-invasive approaches; EEG-based BMI is the most widely investigated. Event-related de-synchronization/ synchronization (ERD/ERS) of sensorimotor rhythms (SMRs), P300, and steady-state visual evoked potential (SSVEP) are the three main cortical activation patterns used for designing an EEG-based BMI. A BMI involves multiple stages: brain data acquisition, pre-processing, feature extraction, and feature classification, along with a device to communicate or control with or without neurofeedback. Despite extensive research worldwide, there are still several challenges to be overcome in making BMI practical for daily use. One such is to account for non-stationary brainwaves dynamics. Also, some people may initial...
Computerized clinical decision support systems can help to provide objective, standardized, and t... more Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on the group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer’s disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and k-Nearest Neighbor (kNNreg) for regression and Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbor (kNNclass) for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predicti...
Uploads
Papers