Advanced Machine-Learning Methods for Brain-Computer Interfacing.

The brain-computer interface (BCI) connects the brain and the external world through an information transmission channel by interpreting the physiological information of the brain during thinking activities. The effective classification of electroencephalogram (EEG) signals is the key to improving the performance of the system. To improve the classification accuracy of EEG signals in the BCI system, the transfer learning algorithm and the improved Common Spatial Pattern (CSP) algorithm are combined to construct a data classification model. Finally, the effectiveness of the proposed algorithm is verified. The results show that in actual and imagined movements, the accuracy of the left- and right-hand movements at different speeds is higher than when the speeds are the same. The proposed Adaptive Composite Common Spatial Pattern (ACCSP) and Self Adaptive Common Spatial Pattern (SACSP) algorithms have good classification effects on 5 subjects, with an average classification accuracy rate of 83.58 percent, which is an increase of 6.96 percent compared with traditional algorithms. When the training sample size is 10, the classification accuracy of the ACCSP algorithm is higher than that of the traditional CSP algorithm. The improved CSP algorithm combined with transfer learning embodies a good classification effect in both ACCSP and SACSP. Especially, the performance of SACSP mode is better. Combining the improved CSP algorithm proposed with the CSP-based transfer learning algorithm can improve the classification accuracy of the BCI classifier.

To Explore the Potentials of Independent Component Analysis in Brain-Computer Interface of Motor Imagery.

This paper is focused on the experimental approach to explore the potential of independent component analysis (ICA) in the context of motor imagery (MI)-based brain-computer interface (BCI). We presented a simple and efficient algorithmic framework of ICA-based MI BCI (ICA-MIBCI) for the evaluation of four classical ICA algorithms (Infomax, FastICA, Jade, and Sobi) as well as a simplified Infomax (sInfomax). Two novel performance indexes, self-test accuracy and the number of invalid ICA filters, were employed to assess the performance of MIBCI based on different ICA variants. As a reference method, common spatial pattern (CSP), a commonly-used spatial filtering method, was employed for the comparative study between ICA-MIBCI and CSP-MIBCI. The experimental results showed that sInfomax-based spatial filters exhibited significantly better transferability in session to session and subject to subject transfer as compared to CSP-based spatial filters. The online experiment was also introduced to demonstrate the practicability and feasibility of sInfomax-based MIBCI. However, four classical ICA variants, especially FastICA, Jade, and Sobi, performed much worse as compared to sInfomax and CSP in terms of classification accuracy and stability. We consider that conventional ICA-based spatial filtering methods tend to be overfitting while applied to real-life electroencephalogram data. Nevertheless, the sInfomax-based experimental results indicate that ICA methods have a great space for improvement in the application of MIBCI. We believe that this paper could bring forth new ideas for the practical implementation of ICA-MIBCI.

Multiclass Classification of Word Imagination Speech with Hybrid Connectivity Features.

OBJECTIVE: In this study, electroencephalography data of imagined words were classified using four different feature extraction approaches. Eight subjects were recruited for the recording of imagination with five different words, namely; 'go', 'back', 'left', 'right', and 'stop'.

Effect on the classification of motor imagery in EEG after applying anodal tDCS with a 4×1 ring montage over the motor cortex.

Transcranial direct stimulation (tDCS) is a technique for modulating brain excitability that has potential to be used in motor neurorehabilitation by enhancing motor activity, such as motor imagery (MI). tDCS effects depend on different factors, like current density and the position of the stimulating electrodes. This study presents preliminary results of the evaluation of the effect of current density on MI performance by measuring right-hand/feet MI accuracy of classification from electroencephalographic (EEG) measurements after anodal tDCS is applied with a 4×1 ring montage over the right-hand or feet motor cortex. Results suggest that there might be an enhancement of feet MI when tDCS is applied over the right-hand motor cortex, but further evaluation is required. If results are confirmed with a larger sample, the montage could be used to optimize feet MI performance and improve the outcome of MI-based brain-computer interfaces, which are used during motor neurorehabilitation.

Death thoughts and images in treatment-seekers after violent loss.

Violent loss survivors often describe experiencing recurrent imagery about their loved one's death. The Death Imagery Scale assesses 5 kinds of imagery: reenactment, rescue, revenge, reunion, and remorse. We explored the frequency of these forms of imagery and their associations with PTSD, depression, and/or complicated grief (CG) among 130 treatment-seeking survivors who were, on average, 3.5 years postloss. Reenactment, rescue, and remorse imagery were most frequently endorsed, and all forms of imagery were associated with PTSD, depression, and CG. Bereaved parents reported more remorse and reunion imagery than others. Homicide survivors reported more revenge imagery than suicide and accident survivors.

Complexity and familiarity enhance single-trial detectability of imagined movements with electroencephalography.

OBJECTIVE: We sought to determine whether the sensorimotor rhythms (SMR) elicited during motor imagery (MI) of complex and familiar actions could be more reliably detected with electroencephalography (EEG), and subsequently classified on a single-trial basis, than those elicited during relatively simpler imagined actions. METHODS: Groups of healthy volunteers, including experienced pianists and ice hockey players, performed MI of varying complexity and familiarity. Their electroencephalograms were recorded and compared using brain-computer interface (BCI) approaches and spectral analyses. RESULTS: Relative to simple MI, significantly more participants produced classifiable SMR for complex MI. During MI of performance of a complex musical piece, the EEG of the experienced pianists was classified significantly more accurately than during MI of performance of a simpler musical piece. The accuracy of EEG classification was also significantly more sustained during complex MI. CONCLUSION: MI of complex actions results in EEG responses that are more reliably classified for more individuals than MI of relatively simpler actions, and familiarity with actions enhances these responses in some cases. SIGNIFICANCE: The accuracy of SMR-based BCIs in non-communicative patients may be improved by employing familiar and complex actions. Increased sensitivity to MI may also improve diagnostic accuracy for severely brain-injured patients in a vegetative state.

Modified CC-LR algorithm with three diverse feature sets for motor imagery tasks classification in EEG based brain-computer interface.

Motor imagery (MI) tasks classification provides an important basis for designing brain-computer interface (BCI) systems. If the MI tasks are reliably distinguished through identifying typical patterns in electroencephalography (EEG) data, a motor disabled people could communicate with a device by composing sequences of these mental states. In our earlier study, we developed a cross-correlation based logistic regression (CC-LR) algorithm for the classification of MI tasks for BCI applications, but its performance was not satisfactory. This study develops a modified version of the CC-LR algorithm exploring a suitable feature set that can improve the performance. The modified CC-LR algorithm uses the C3 electrode channel (in the international 10-20 system) as a reference channel for the cross-correlation (CC) technique and applies three diverse feature sets separately, as the input to the logistic regression (LR) classifier. The present algorithm investigates which feature set is the best to characterize the distribution of MI tasks based EEG data. This study also provides an insight into how to select a reference channel for the CC technique with EEG signals considering the anatomical structure of the human brain. The proposed algorithm is compared with eight of the most recently reported well-known methods including the BCI III Winner algorithm. The findings of this study indicate that the modified CC-LR algorithm has potential to improve the identification performance of MI tasks in BCI systems. The results demonstrate that the proposed technique provides a classification improvement over the existing methods tested.

Discriminative methods for classification of asynchronous imaginary motor tasks from EEG data.

In this work, two methods based on statistical models that take into account the temporal changes in the electroencephalographic (EEG) signal are proposed for asynchronous brain-computer interfaces (BCI) based on imaginary motor tasks. Unlike the current approaches to asynchronous BCI systems that make use of windowed versions of the EEG data combined with static classifiers, the methods proposed here are based on discriminative models that allow sequential labeling of data. In particular, the two methods we propose for asynchronous BCI are based on conditional random fields (CRFs) and latent dynamic CRFs (LDCRFs), respectively. We describe how the asynchronous BCI problem can be posed as a classification problem based on CRFs or LDCRFs, by defining appropriate random variables and their relationships. CRF allows modeling the extrinsic dynamics of data, making it possible to model the transitions between classes, which in this context correspond to distinct tasks in an asynchronous BCI system. On the other hand, LDCRF goes beyond this approach by incorporating latent variables that permit modeling the intrinsic structure for each class and at the same time allows modeling extrinsic dynamics. We apply our proposed methods on the publicly available BCI competition III dataset V as well as a data set recorded in our laboratory. Results obtained are compared to the top algorithm in the BCI competition as well as to methods based on hierarchical hidden Markov models (HHMMs), hierarchical hidden CRF (HHCRF), neural networks based on particle swarm optimization (IPSONN) and to a recently proposed approach based on neural networks and fuzzy theory, the S-dFasArt. Our experimental analysis demonstrates the improvements provided by our proposed methods in terms of classification accuracy.

Representations in mental imagery and working memory: evidence from different types of visual masks.

Although few studies have systematically investigated the relationship between visual mental imagery and visual working memory, work on the effects of passive visual interference has generally demonstrated a dissociation between the two functions. In four experiments, we investigated a possible commonality between the two functions: We asked whether both rely on depictive representations. Participants judged the visual properties of letters using visual mental images or pictures of unfamiliar letters stored in short-term memory. Participants performed both tasks with two different types of interference: sequences of unstructured visual masks (consisting of randomly changing white and black dots) or sequences of structured visual masks (consisting of fragments of letters). The structured visual noise contained elements of depictive representations (i.e., shape fragments arrayed in space), and hence should interfere with stored depictive representations; the unstructured visual noise did not contain such elements, and thus should not interfere as much with such stored representations. Participants did in fact make more errors in both tasks with sequences of structured visual masks. Various controls converged in demonstrating that in both tasks participants used representations that depicted the shapes of the letters. These findings not only constrain theories of visual mental imagery and visual working memory, but also have direct implications for why some studies have failed to find that dynamic visual noise interferes with visual working memory.

“Cambiar las actitudes con un poco de imaginación”. Efectos del contacto imaginado en los sesgos intergrupales de los niños pequeños / "Changing attitudes with a little imagination": Imagined contact effects on young children's intergroup bias

En esta investigación se ha evaluado un nuevo concepto en psicología social, denominado "contacto imaginado‟, en niños pequeños (n = 123, de 5 a 10 años). A la mitad de la muestra se les pidió que se imaginaran a sí mismos interactuando con un niño con una discapacidad física; la otra mitad no participó en esta actividad (grupo control). En comparación con el grupo control, los niños en la condición "contacto imaginado‟ mostraron posteriormente una reducción del sesgo intergrupal cuando se evaluaban sus actitudes generales y sus valoraciones de cordialidad y aptitudes. El "contacto imaginado‟ también se asoció con un mayor deseo de desarrollar conductas de amistad hacia el niño con discapacidad, pero solo en los participantes de 5 -6 años. Esto apoya parcialmente nuestra hipótesis de que los niños pequeños, quizá como resultado de una falta de experiencia con el exogrupo, se benefician en mayor medida del contacto imaginado. Se discuten las implicaciones para el desarrollo de las actitudes hacia las personas con discapacidad, la teoría del contacto imaginado y el desarrollo de técnicas de reducción de los prejuicios en el aula basadas en el contacto imaginado (AU)

The current research tested a recent development in social psychology, namely "imagined contact‟, among young children (n = 123, 5 to 10 years). Children imagined interacting with a physically disabled child, or did not take part in this activity (the control group). Compared with the control group, children who engaged in "imagined contact‟ subsequently showed reduced intergroup bias in their general attitude and ratings of warmth and competence. Imagined contact also led to more positive intended friendship behavior towards the disabled, but only among 5 – 6 year olds. This provides partial support for our hypothesis that younger children, perhaps as a result of their lack of out-group experience, are more likely to benefit from imagined contact. Implications for the development of attitudes towards the disabled, imagined contact theory and the development of classroom-based prejudice-reduction techniques based on imagined contact are discussed (AU)

Impacto de la interactividad en la identificación con los personajes de ficciones / Impact of interactivity on identification with characters in fiction

Se explora el efecto de la interactividad en la identificación con los personajes de las ficciones audiovisuales. 310 participantes fueron sometidos al visionado de una ficción en una de dos condiciones: 1) interactiva (escogían la trama), y 2) no interactiva (veían la ficción convencionalmente). Luego, completaron un cuestionario con la escala EDI de identificación y empatía con los personajes, de Igartua y Páez. La capacidad de intervenir en la configuración del argumento (la interactividad) afectó a la identificación con los personajes. Los resultados añaden datos sobre psicología de los medios, sobre la interactividad en comunicación y permiten comprender los procesos de empatía e identificación con los personajes (AU)

The effect of interactivity on identification with characters in audiovisual fiction was observed. 310 participants were asked to watch a film in one of these two conditions: 1) interactive (they selected the plot), and 2) non-interactive (they consumed the fiction in a conventional way). After watching the movie, they completed a questionnaire with the EDI scale of identification and empathy with characters, created by Igartua and Paez. The capacity to intervene in the configuration of the plot (interactivity) affected identification with characters. The results provide data about the psychology of media and interactivity in communication and allow us to understand the processes of empathy and identification with characters (AU)

Two types of image generation: evidence from PET.

Is there more than one method whereby people can generate visual mental images? Participants generated images after learning patterns in two ways. In one condition, they memorized descriptions of how segments are arranged to form patterns; in another, they memorized segments and mentally amalgamated them into patterns. In both conditions, identical stimuli cued them to form images while brain activation was monitored using PET. Comparison of the two imagery conditions revealed different activation between hemispheres when images were formed after patterns were learned by mentally combining segments versus when images were formed from stored verbal descriptions. Thus, images can be generated in at least two ways. However, this laterality difference was subtle; the majority of brain areas were activated in common across conditions. This overall similarity is counter to what would be expected if image generation is simply perceptual exploration in the absence of appropriate stimuli, as is posited by perceptual activity theory.

Initial on-line evaluations of the LF-ASD brain-computer interface with able-bodied and spinal-cord subjects using imagined voluntary motor potentials.

Previous research has focused on developing a brain-controlled switch named the low frequency asynchronous switch design (LF-ASD) that is suitable for intermittent control of devices such as environmental control systems, computers, and neural prostheses. On-line implementations of the LF-ASD have shown promising results in response to actual index finger flexions with able-bodied subjects. This paper reports the results of initial on-line evaluations of the LF-ASD brain-controlled switch with both able-bodied subjects and subjects with high-level spinal-cord injuries. This paper has demonstrated that users can activate the LF-ASD switch by imaging movement. In this paper, two able-bodied subjects were able to control the LF-ASD with imagined voluntary movements with hit (true positive) rates above 70% and false positive rates below 3% while two subjects with high-level spinal-cord injuries demonstrated hit rates ranging from 45-48% and false positive rates below 1%.

Intervencao psicoterapeutica na area de cuidados paliativos para ressignificar a dor simbolica da morte de pacientes terminais atraves de relaxamento mental, imagens mentais e espiritualidade / Psychotherapeutic interventions for terminal patients: dealing with meaning of death by relaxation techniques, mental imaging, and spirituality

Em dissertacao de mestrado estudamos qualitativamente a eficacia da intervencao psicoterapeutica para pacientes terminais, desenvolvida por nos atraves da integracao das tecnicas de relaxamento mental e visualizacao de imagens mentais com os elementos que compoem a natureza da espiritualidade, para assim....

Un caso de Síndrome de Diógenes compartido en una pareja de hermanas / A Diogenes Syndrome case shared by both sisters

Se presenta un caso de Síndrome de Diógenes compartido en una pareja de hermanas procedentes del medio rural, que presentan todas las características propias del síndrome: Rechazo del contacto social con reclusión en el domicilio, que está sucio y en condiciones de inhabitabilidad, abandono de su aseo, sin que acepten ningún tipo de ayuda socio-sanitaria. También se reseñan algunas características poco comunes, como la edad, inferior a la media y se discute su importancia (AU)

Feature centrality: naming versus imagining.

Being white is central to whether we call an animal a "polar bear," but it is fairly peripheral to our concept of what a polar bear is. We propose that a feature is central to category naming in proportion to the feature's category validity--the probability of the feature, given the category. In contrast, a feature is conceptually central in a representation of the object to the extent that the feature is depended on by other features. Further, we propose that naming and conceptual centrality are more likely to disagree for features that hold at more specific levels (such as is white, which holds only for the specific category of polar bear) than for features that hold at intermediate levels of abstraction (such as has claws, which holds for all bears). In support of these hypotheses, we report evidence that increasing the abstractness of category features has a greater effect on judgments of conceptual centrality than on judgments of name centrality and that other category features depend more on intermediate-level category features than on specific ones.