How to effectively and efficiently extract valid reliable features from high-dimensional electroencephalography (EEG), particularly how fuse the spatial temporal dynamic brain information into a better feature representation, is critical issue in data analysis. Most current EEG studies work task driven manner explore with supervised model, which would be limited by given labels great extent. In this paper, we propose practical hybrid unsupervised deep convolutional recurrent generative...

Affective brain-computer interface based on electroencephalography (EEG) is an important branch in the field of affective computing. However, individual differences EEG emotional data and noisy labeling problem subjective feedback seriously limit effectiveness generalizability existing models. To tackle these two critical issues, we propose a novel transfer learning framework with Prototypical Representation Pairwise Learning ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...

Depression is a major psychological disorder with growing impact worldwide. Traditional methods for detecting the risk of depression, predominantly reliant on psychiatric evaluations and self-assessment questionnaires, are often criticized their inefficiency lack objectivity. Advancements in deep learning have paved way innovations depression detection that fuse multimodal data. This paper introduces novel framework, Audio, Video, Text Fusion-Three Branch Network (AVTF-TBN), designed to...

Determining and decoding emotional brain processes under ecologically valid conditions remains a key challenge in affective neuroscience. The current functional Magnetic Resonance Imaging (fMRI) based emotion studies are mainly on brief isolated episodes of induction, while sustained experience naturalistic environments that mirror daily life experiences scarce. Here we used 12 different 10-minute movie clips as emotion-evoking procedures n = 52 individuals to explore emotion-specific fMRI...

Intense or sustained nociceptor activation, occurring, for example, after skin injury, can induce "central sensitization", i.e. an increased responsiveness of nociceptive neurons in the central nervous system. A hallmark sensitization is mechanical pinprick sensitivity area surrounding injured skin. The aim present study was to identify changes brain activity related this sensitivity. In 20 healthy volunteers, induced using high frequency electrical stimulation forearm (HFS). Mechanical (64...

This study applied a comprehensive electroencephalography (EEG) analysis for movement-related cortical potentials (MRCPs) and event-related desynchronization (ERD) in order to understand brain activity changes during movement preparation execution stage of unilateral wrist extension. Thirty-four healthy subjects completed two potential tests the same sequence. Unilateral extension was involved both as task. Instruction Response Movement (IRM) brisk response task with visual "go" signal,...

Emotions, formed in the process of perceiving external environment, directly affect human daily life, such as social interaction, work efficiency, physical wellness, and mental health. In recent decades, emotion recognition has become a promising research direction with significant application values. Taking advantages electroencephalogram (EEG) signals (i.e., high time resolution) video‐based evoking rich media information), video‐triggered EEG been proven useful tool to conduct...

EEG microstates have been widely adopted to understand the complex and dynamic-changing process in dynamic brain systems, but how are temporally modulated by emotion dynamics is still unclear. An investigation of under video-evoking modulation would provide a novel insight into understanding temporal functional networks.In present study, we postulate that emotional states dynamically modulate microstate patterns, perform an in-depth between video-watching task. By mapping from...

Introduction Inter- and intra-subject variability are caused by the of psychological neurophysiological factors over time across subjects. In application in Brain-Computer Interfaces (BCI), existence inter- reduced generalization ability machine learning models seriously, which further limited use BCI real life. Although many transfer methods can compensate for to some extent, there is still a lack clear understanding about change feature distribution between cross-subject cross-session...

Interleukin (IL)-5 is thought to play an important role in asthmatic bronchial mucosal inflammation and a potential therapeutic target. To investigate the effect of IL-5 on infiltration eosinophils airway vivo, we compared eosinophil counts their activation status airways without after topical instillation recombinant human IL-5. Eight subjects with mild atopic asthma underwent initial bronchoscopy during which control bronchoalveolar lavage (BAL) fluid as well mucosa were obtained, at same...

Abstract Recording oscillatory brain activity holds great promise in pain research. However, experimental results are variable and often difficult to reconcile. Some of these inconsistencies arise from the use hypothesis-driven analysis approaches that (1) do not assess consistency observed responses within across individuals, (2) fully exploit information sampled entire cortex. Here, we address issues by recording electrocorticogram directly surface 12 freely moving rats. Using a...

Background Recently, it was shown that the highly variable after-effect of continuous theta-burst stimulation (cTBS) primary motor cortex (M1) can be predicted by latency motor-evoked potentials (MEPs) recorded before cTBS. This suggests at least part this inter-individual variability is driven differences in neuronal populations preferentially activated transcranial magnetic (TMS). Methods Here, we MEPs, TMS-evoked brain (TEPs) and somatosensory-evoked (SEPs) to investigate effects cTBS...

Recognizing human emotions from complex, multivariate, and non-stationary electroencephalography (EEG) time series is essential in affective brain-computer interface. However, because continuous labeling of ever-changing emotional states not feasible practice, existing methods can only assign a fixed label to all EEG timepoints emotion-evoking trial, which overlooks the highly dynamic signals. To solve problems high reliance on labels ignorance time-changing information, this paper we...

The Common Spatial Pattern (CSP) algorithm is a popular method for efficiently calculating spatial filters. However, several previous studies show that CSP's performance deteriorates especially when the number of channels large compared to small training datasets. As result, it necessary choose an optimal subset whole save computational time and retain high classification accuracy. In this paper, we propose novel heuristic select CSP. CSP procedure applied datasets firstly then channel score...

Machine learning has been increasingly used in decoding brain states from functional magnetic resonance imaging (fMRI). One important application is to classify the levels of pain perception patients' fMRI for clinical assessment. However, huge number features and complex relationships between affect performance classification models heavily. In this article, we introduce a new fuzzy-rule-based hybrid optimization approach dimension reduction multiclassification problems using chaotic map,...

Brain Computer Interface (BCI) inefficiency indicates that there would be 10% to 50% of users are unable operate Motor-Imagery-based BCI systems. Importantly, the almost all previous studieds on were based tests Sensory Motor Rhythm (SMR) feature. In this work, we assessed occurrence with SMR and Movement-Related Cortical Potential (MRCP) features.A pool datasets resting state movements related EEG signals was recorded 93 subjects during 2 sessions in separated days. Two methods, Common...