An affectively driven music generation system is described and evaluated. The system is developed for the intended eventual use in human-computer interaction systems such as brain-computer music interfaces. It is evaluated for its ability to induce changes in a listeners affective state. The affectively-driven algorithmic composition system was used to generate a stimulus set covering 9 discrete sectors of a 2-dimensional affective space by means of a 16 channel feedforward artificial neural network. This system was used to generate 90 short pieces of music with specific affective intentions, 10 stimuli for each of the 9 sectors in the affective space. These pieces were played to 20 healthy participants, and it was observed that the music generation system induced the intended affective states in the participants. This is further verified by inspecting the galvanic skin response recorded from participants.
It is difficult to identify optimal cut-off frequencies for filters used with the common spatial pattern (CSP) method in motor imagery (MI)-based brain-computer interfaces (BCIs). Most current studies choose filter cut-frequencies based on experience or intuition, resulting in sub-optimal use of MI-related spectral information in the electroencephalography (EEG). To improve information utilization, we propose a SincNet-based hybrid neural network (SHNN) for MI-based BCIs. First, raw EEG is segmented into different time windows and mapped into the CSP feature space. Then, SincNets are used as filter bank band-pass filters to automatically filter the data. Next, we used squeeze-and-excitation modules to learn a sparse representation of the filtered data. The resulting sparse data were fed into convolutional neural networks to learn deep feature representations. Finally, these deep features were fed into a gated recurrent unit module to seek sequential relations, and a fully connected layer was used for classification. We used the BCI competition IV datasets 2a and 2b to verify the effectiveness of our SHNN method. The mean classification accuracies (kappa values) of our SHNN method are 0.7426 (0.6648) on dataset 2a and 0.8349 (0.6697) on dataset 2b, respectively. The statistical test results demonstrate that our SHNN can significantly outperform other state-of-the-art methods on these datasets.
Motor imagery (MI) is a popular paradigm for controlling electroencephalogram (EEG) based Brain-Computer Interface (BCI) systems. Many methods have been developed to attempt to accurately classify MI-related EEG activity. Recently, the development of deep learning has begun to draw increasing attention in the BCI research community because it does not need to use sophisticated signal preprocessing and can automatically extract features. In this paper, we propose a deep learning model for use in MI-based BCI systems. Our model makes use of a convolutional neural network based on a multi-scale and channel-temporal attention module (CTAM), which called MSCTANN. The multi-scale module is able to extract a large number of features, while the attention module includes both a channel attention module and a temporal attention module, which together allow the model to focus attention on the most important features extracted from the data. The multi-scale module and the attention module are connected by a residual module, which avoids the degradation of the network. Our network model is built from these three core modules, which combine to improve the recognition ability of the network for EEG signals. Our experimental results on three datasets (BCI competition IV 2a, III IIIa and IV 1) show that our proposed method has better performance than other state-of-the-art methods, with accuracy rates of 80.6%, 83.56% and 79.84%. Our model has stable performance in decoding EEG signals and achieves efficient classification performance while using fewer network parameters than other comparable state-of-the-art methods.
There is a need to efficiently identify time, frequency and spatial locations between which connectivity occurs within the brain. Therefore, a novel, population based, search algorithm is proposed based upon the behaviour of foraging animals. The method is evaluated on a simple grid search problem and on the identification of time-frequency locations of statistically significant phase synchronisation in both synthetic and real EEG. The method is shown to be comparable to a state-of-the-art phase synchronisation identification algorithm in terms of speed while identifying a large proportion of available solutions.
Affective brain–computer interfaces (aBCIs) provide a method for individuals to interact with a computer via their emotions and without needing to move. This chapter will provide an introduction to the concept of aBCIs and their uses in applications such as music therapy and affective computing. We will first review the concept of aBCIs before going on to provide a literature review of the current state-of-the-art research in affective state detection methods and their uses in aBCI. Finally, we will describe a case study; an affective brain–computer music interface (aBCMI) and its potential for use in music therapy. Emerging and established trends in aBCI, such as the use of prefrontal asymmetry measures of affective states, are identified. Additionally, a set of recommendations are provided for researchers seeking to work in the field of aBCI.
Objective.Semantic concepts are coherent entities within our minds. They underpin our thought processes and are a part of the basis for our understanding of the world. Modern neuroscience research is increasingly exploring how individual semantic concepts are encoded within our brains and a number of studies are beginning to reveal key patterns of neural activity that underpin specific concepts. Building upon this basic understanding of the process of semantic neural encoding, neural engineers are beginning to explore tools and methods for semantic decoding: identifying which semantic concepts an individual is focused on at a given moment in time from recordings of their neural activity. In this paper we review the current literature on semantic neural decoding.Approach.We conducted this review according to the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA) guidelines. Specifically, we assess the eligibility of published peer-reviewed reports via a search of PubMed and Google Scholar. We identify a total of 74 studies in which semantic neural decoding is used to attempt to identify individual semantic concepts from neural activity.Main results.Our review reveals how modern neuroscientific tools have been developed to allow decoding of individual concepts from a range of neuroimaging modalities. We discuss specific neuroimaging methods, experimental designs, and machine learning pipelines that are employed to aid the decoding of semantic concepts. We quantify the efficacy of semantic decoders by measuring information transfer rates. We also discuss current challenges presented by this research area and present some possible solutions. Finally, we discuss some possible emerging and speculative future directions for this research area.Significance.Semantic decoding is a rapidly growing area of research. However, despite its increasingly widespread popularity and use in neuroscientific research this is the first literature review focusing on this topic across neuroimaging modalities and with a focus on quantifying the efficacy of semantic decoders.
The last few decades have seen a rapid change in our understanding of the epidemiology of bipolar disorder, which has only recently started to achieve major research attention. This article reviews recent developments. In addition to electronic searches using MEDLINE and PsycLIT, references from articles were identified, major journals hand searched, and major textbooks of psychiatry and epidemiology reviewed. Studies may have overestimated the prevalence of mania, and underestimated incidence. The incidence of mania may be increasing in recent generations, but the data remain inconclusive. Age at onset of mania is earlier than previously believed, and there are gender differences in epidemiology and clinical course. Ethnic differences in epidemiology and clinical course of bipolar disorder are highlighted. Comorbid alcohol and substance abuse are common in patients suffering from bipolar disorder and are associated with a more severe clinical course and a worse outcome. Urban living and lower socioeconomic and single marital status may be risk factors for developing bipolar disorder.
Mild Cognitive Impairment (MCI) indicates a high risk for conversion to dementia and a clinical diagnosis of Alzheimer's disease (AD). Memory impairment is one of the cognitive domains indicating higher risk for conversion to AD. We expected different network of activation for the working memory task between the two groups. The groups were 12 MCI subjects and age-matched 20 health controls (HC). The task design was a delay-match-to-sample and it was analyzed as event related design. There were 3 runs of 5 minutes, 34 sec each. The brain activation maps were computed for corrected performed trials. The coherent default network was measured using a 7 minute resting scan. Brain activation was measured using functional magnetic resonance imaging with a TR = 2 sec. Statistical comparisons were performed at p < 0.05 level, corrected for multiple comparisons. Both groups activated a wide network in the visual striate and extrastriate areas, middle temporal cortices, parietal lobe and frontal areas. During the working memory task there was deactivation of the default network. In the encoding phase of the task, there was higher activation in the HC compared to MCI in left fusiform gyrus and middle temporal gyrus. The MCI group had higher activation compared to HC in the right fusiform gyrus, superior temporal gyrus, middle and medial frontal gyrii and the left hemisphere in precuneus, parahippocampal and fusiform gyrii, and superior frontal gyrus. In the recall phase the HC had higher activation compared to MCI in right hemisphere: posterior cingulate, inferior, medial and superior frontal gyrii whereas in the left hemisphere: cingulate gyrus, fusiform gyrus, precuneus, medial and superior frontal gyrii. The MCI in the recall phase had higher activation compared to HC in the left inferior, middle and superior temporal gyrii and inferior frontal gyrus. The resting default network in the resting scan matched the suppressed default network during the working memory scan. The activation differences between groups indicate compensatory mechanisms within the MCI group for the effects of the putative AD neuropathology.
A fully automated and online artifact removal method for the electroencephalogram (EEG) is developed for use in brain-computer interfacing (BCI). The method (FORCe) is based upon a novel combination of wavelet decomposition, independent component analysis, and thresholding. FORCe is able to operate on a small channel set during online EEG acquisition and does not require additional signals (e.g., electrooculogram signals). Evaluation of FORCe is performed offline on EEG recorded from 13 BCI particpants with cerebral palsy (CP) and online with three healthy participants. The method outperforms the state-of the-art automated artifact removal methods Lagged Auto-Mutual Information Clustering (LAMIC) and Fully Automated Statistical Thresholding for EEG artifact Rejection (FASTER), and is able to remove a wide range of artifact types including blink, electromyogram (EMG), and electrooculogram (EOG) artifacts.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cpath d='M200 752.362h200v300H200z' style='fill:%23fff;fill-opacity:1;stroke:none' transform='translate(0 -752.362)'/%3e%3cpath d='M400 752.362h200v300H400z' style='fill:%23ff883e;fill-opacity:1;stroke:none' transform='translate(0 -752.362)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)