Two-dimensional cursor control is an important and challenging issue in EEG-based brain-computer interfaces (BCIs). To address this issue, here we propose a new approach by combining two brain signals including Mu/Beta rhythm during motor imagery P300 potential. In particular, detection mechanism potential are devised integrated such that the user able to use control, respectively, simultaneously, independently, horizontal vertical movements of specially designed graphic interface. A...

Brain-computer interfaces (BCIs) are used to translate brain activity signals into control for external devices. Currently, it is difficult BCI systems provide the multiple independent necessary multi-degree continuous of a wheelchair. In this paper, we address challenge by introducing hybrid that uses motor imagery-based mu rhythm and P300 potential brain-actuated simulated or real The objective greater number commands with increased accuracy user. Our paradigm allows user direction (left...

To control a cursor on monitor screen, user generally needs to perform two tasks sequentially. The first task is move the target screen (termed 2-D movement), and second either select of interest by clicking it or reject that not it. In previous study, we implemented former function in an EEG-based brain-computer interface system using motor imagery P300 potential horizontal vertical movements, respectively. this selection rejection functionality hybrid feature from potential. Specifically,...

Despite rapid advances in the study of brain–computer interfaces (BCIs) recent decades, two fundamental challenges, namely, improvement target detection performance and multidimensional control, continue to be major barriers for further development applications. In this paper, we review progress multimodal BCIs (also called hybrid BCIs), which may provide potential solutions addressing these challenges. particular, improved can achieved by developing that utilize multiple brain patterns,...

In this paper, we present a new web browser based on two-dimensional (2D) brain-computer interface (BCI) mouse, where our major concern is the selection of an intended target in multi-target page. A real-world page may contain tens or even hundreds targets, including hyperlinks, input elements, buttons, etc. case, filter designed system can be used to exclude most those targets no interest. Specifically, user filters interest out by inputting keywords with P300-based speller, while keeps...

Class imbalance is a common issue in the community of machine learning and data mining. The class-imbalance distribution can make most classical classification algorithms neglect significance minority class tend toward majority class. In this article, we propose label enhancement method to solve problem graph manner, which estimates numerical trains inductive model simultaneously. It gives new perspective on based rather than original logical label. We also present an iterative optimization...

A main goal of rehabilitation strategies in humans with spinal cord injury is to strengthen transmission spared neural networks. Although neuromodulatory have targeted different sites within the central nervous system restore motor function following injury, role cortical targets remain poorly understood. Here, we use 180 pairs transcranial magnetic stimulation for ∼30 min over hand representation cortex at an interstimulus interval mimicking rhythmicity descending late indirect (I) waves...

Electroencephalogram (EEG) classification has attracted great attention in recent years, and many models have been presented for this task. Nevertheless, EEG data vary from subject to subject, which may lead the performance of a classifier degrades due individual differences. To collect enough labeled model would address issue, but it is often time-consuming labor-intensive. In paper, we propose new multi-source transfer learning method based on domain adversarial neural network...

Graph-structured data, where nodes exhibit either pair-wise or high-order relations, are ubiquitous and essential in graph learning. Despite the great achievement made by existing learning models, these models use direct information (edges hyperedges) from graphs do not adopt underlying indirect (hidden relations). To address this issue, paper, we propose a general framework named Simplicial Complex Neural (SCN) network, which construct simplicial complex based on so that all can be employed...

Abstract Background The brain area stimulated during repetitive transcranial magnetic stimulation (rTMS) treatment is important in altered states of consciousness. However, the functional contribution M1 region high‐frequency rTMS remains unclear. Objective aim this study was to examine clinical [the Glasgow coma scale (GCS) and recovery scale‐revised (CRS‐R)] neurophysiological (EEG reactivity SSEP) responses vegetative state (VS) patients following traumatic injury (TBI) before after a...

Electroencephalogram (EEG) signals play an important role in brain-computer interface (BCI) applications. Recent studies have utilized transfer learning to assist the task new subject, i.e., target domain, by leveraging beneficial information from previous subjects, source domains. Nevertheless, EEG involve sensitive personal mental and health information. Thus, privacy concern becomes a critical issue. In addition, existing methods mostly assume that portion of subject's data is available...

Recently, there has been an increasing emphasis on applications of pattern recognition and neuroimaging techniques in the effective accurate diagnosis psychiatric or neurological disorders. In present study, we investigated whole-brain resting-state functional connectivity patterns Parkinson's disease (PD), which are expected to provide additional information for clinical treatment this disease. First, computed between each pair 116 regions interest derived from a prior atlas. The most...

Abstract Existing evidence suggests that the default-mode network (DMN) and fronto-pariatal (FPN) play an important role in altered states of consciousness. However, brain mechanisms underlying impaired consciousness specific interactions involved are not well understood. We studied topological properties functional networks using resting-state MRI data acquired from 18 patients (11 vegetative state/unresponsive wakefulness syndrome, VS/UWS, 7 minimally conscious state, MCS) compared these...

Information theoretical-based methods have attracted a great attention in recent years and gained promising results for multilabel feature selection (MLFS). Nevertheless, most of the existing consider heuristic way to grid search important features, they may also suffer from issue fully utilizing labeling information. Thus, are probable deliver suboptimal result with heavy computational burden. In this article, we propose general optimization framework global relevance redundancy (GRRO)...

Interhemispheric interactions through the corpus callosum play an important role in control of bimanual forces. However, extent to which physiological connections between primary motor cortices are modulated during increasing levels force generation intact humans remains poorly understood. Here we studied coherence electroencephalographic (EEG) signals and ipsilateral cortical silent period (iSP), two well-known measures interhemispheric connectivity cortices, unilateral bilateral 10%, 40%,...

This article presents a novel model named Adversarial Auto-encoder Domain Adaptation to handle the recommendation problem under cold-start settings. Specifically, we divide hypergraph into two hypergraphs, i.e., positive and negative one. Below, adopt user for illustration. After achieving apply auto-encoders them obtain embeddings of warm users items. Additionally, employ multi-layer perceptron get called regular embeddings. Subsequently, users, assign pseudo-labels their embeddings,...

Abstract Objective. Deep transfer learning has been widely used to address the nonstationarity of electroencephalogram (EEG) data during motor imagery (MI) classification. However, previous deep approaches suffer from limited classification accuracy because temporal and spatial features cannot be effectively extracted. Approach. Here, we propose a novel end-to-end subject adaptation convolutional neural network (SACNN) handle problem EEG-based MI Our proposed model jointly optimizes three...

Recommendation systems provide personalized service to users and aim at suggesting them items that they may prefer. There is an increasing requirement of next-item recommendation infer a user's next favor item based on his/her historical selection items. In this article, we study the under cold-start situation, where in system share no interaction with new Specifically, seek address problem from perspective zero-shot learning (ZSL), which classifies samples whose classes are unseen during...

Beta event-related spectral perturbation (ERSP), including bilateral movement-related beta desynchronization (MRBD) and post-movement synchronization (PMBS), can be evoked by unilateral speed movement. A potential correlation might exist between power (de)synchronization interhemispheric coherence during movement execution. However, the PMBS phase, existence of coupling effect on it are largely undiscovered. This study aimed to answer this question. In present study, we investigated eight...

Facial recognition is very primary and important in individuals' development the event-related potential based on face such as N170 considered most objective marker of autism, hot difficult point current research. We will explore electrophysiological basis facial with autism without autism. Given link between social impairments, core symptom it also necessary to study correlation P1 components severity functioning In this study, age-matched typically developing children were asked examine...