A5100717541- EEG and Brain-Computer Interfaces
- Advanced Memory and Neural Computing
- Neuroscience and Neural Engineering
- Chemical Synthesis and Analysis
- Gaze Tracking and Assistive Technology
- Supramolecular Self-Assembly in Materials
- Cardiovascular Health and Risk Factors
- Protein Hydrolysis and Bioactive Peptides
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Neural dynamics and brain function
- Consumer Perception and Purchasing Behavior
- Carbohydrate Chemistry and Synthesis
- Fashion and Cultural Textiles
- Supramolecular Chemistry and Complexes
- Bioactive Compounds and Antitumor Agents
- Blockchain Technology Applications and Security
- Neuropeptides and Animal Physiology
- Molecular Sensors and Ion Detection
- Immune Response and Inflammation
- Ethics and Social Impacts of AI
- Aesthetic Perception and Analysis
- 3D Surveying and Cultural Heritage
- Cancer, Stress, Anesthesia, and Immune Response
- Artificial Intelligence in Healthcare
Chinese Academy of Sciences
2018-2025
University of Chinese Academy of Sciences
2018-2025
Beijing Academy of Artificial Intelligence
2021-2025
Institute of Automation
2021-2025
China Mobile (China)
2025
Center for Excellence in Brain Science and Intelligence Technology
2025
Central South University
2024
Institute of Information Engineering
2023
Southern University of Science and Technology
2023
Shandong Institute of Automation
2023
A brain-computer interface (BCI) based on motor imagery (MI) can translate users' subjective movement-related mental state without external stimulus, which has been successfully used for replacing and repairing function. In contrast with studies about decoding methods, less work was reported training users to improve the performance of MI-BCIs. This study aimed develop a novel MI feedback method enhance ability humans use MI-BCI system. this study, an adaptive proposed effectiveness process....
Abstract Objective. Steady-state visual evoked potential (SSVEP)-based brain–computer interfaces (BCIs) have attracted increasing attention due to their high information transfer rate. To improve the performance of SSVEP detection, we propose a bidirectional Siamese correlation analysis (bi-SiamCA) model. Approach . In this model, an long short-term memory-based architecture is designed measure similarity between signal and template in each frequency obtain probability that belongs...
Abstract Objective . A motor imagery-based brain-computer interface (MI-BCI) translates spontaneous movement intention from the brain to outside devices. Multimodal MI-BCI that uses multiple neural signals contains rich common and complementary information is promising for enhancing decoding accuracy of MI-BCI. However, heterogeneity different modalities makes multimodal task difficult. How effectively utilize remains be further studied. Approach In this study, a MI network was proposed....
Multilevel protein structures typically involve polypeptides of sufficient lengths. Here we report the folding and assembly seven short tetrapeptides sharing same types α-, β-, aromatic γ-amino acid residues. These are two sets hybrid peptides, with three members in one set four other, having complementary hydrogen-bonding sequences that were hypothesized to pair into linear H-bonded duplexes. However, instead undergoing anticipated pairing, initially examined oligomers, 1 2a or 2b,...
Abstract Objective. A rapid serial visual presentation (RSVP)-based brain-computer interface (BCI) is an efficient information detection technology through detecting event-related potentials (ERPs) evoked by target stimuli. The BCI system requires a time-consuming calibration process to build reliable decoding model for new user. Therefore, zero-calibration has become important topic in research. Approach. In this paper, we construct RSVP dataset that includes 31 subjects, and propose method...
Connecting basic hydrogen-bonding units with lengthened flexible or rigid linkers generates oligoamide strands that carry new H-bonding sequences and association specificity, leading to H-bonded homo- heteroduplexes constants in the 104 M–1 range chloroform. Computational experimental studies indicate duplexes aromatic adopt bent conformations allow formation of interstrand H-bonds accommodate introduced liners, offering a series units.
A motor imagery (MI)-based brain–computer interface (BCI) is a promising system that can help neuromuscular injury patients recover or replace their abilities. Currently, before one uses MI-BCI, we need to collect large amount of training data train the decoding model, and this process time consuming. When trained with small data, existing methods generally do not perform well in MI tasks. Therefore, it important improve performance short calibration data. In study, propose dynamic weighted...
Artificial Intelligence (AI) is an important driving force for the development and transformation of financial industry. However, with fast-evolving AI technology application, unintentional bias, insufficient model validation, immature contingency plan other underestimated threats may expose company to operational reputational risks. In this paper, we focus on fairness evaluation, one key components Governance, through a quantitative lens. Statistical methods are reviewed imbalanced data...
Molluscs have evolved a primitive but complete neuroendocrine-immune (NEI) system with vast array of neurotransmitters to conduct both humoral and cellular immunomodulation. Previous study has illustrated the immune functions several key neurotransmitters. However, combined effects multiple signaling pathway mediate such immunomodulation not been well understood. In present study, iTRAQ LC-ESI-MS/MS approaches were employed investigate two crucial neurotransmitters, acetylcholine (ACh)...
Motor imagery (MI) based Brain-computer interface (BCI) is a promising BCI paradigm that can help neuromuscular injury patients to recover or replace their motor abilities. However, electroencephalography (EEG) MI-BCI suffers from its long calibration time and low classification accuracy, which restrict application. Thus, it important reduce the of enhance prediction accuracy. In this study, we propose filter bank Wasserstein adversarial domain adaptation framework (FBWADA) uses short amount...
Cardiovascular diseases (CVDs) are currently the leading cause of death worldwide, highlighting critical need for early diagnosis and treatment. Machine learning (ML) methods can help diagnose CVDs early, but their performance relies on access to substantial data with high quality. However, sensitive nature healthcare often restricts individual clinical institutions from sharing train sufficiently generalized unbiased ML models. Federated Learning (FL) is an emerging approach, which offers a...
The short video has gained increasing attention in information sharing and commercial promotions due to the fast development of social platforms. Accompanying, it introduces great requirements for assessing quality videos efficient acquirement propagation. However, existing assessment researches focus on content with five rating scores, limiting a one-dimension simplified criterion. In this paper, we establish novel database dubbed MMSVD-Douyin multi-modal under consideration three...
Objective To investigate the effect of dexmedetomidine postconditioning on acute lung injury (ALI) induced by lipopolysaccharide (LPS) in rats.Methods Fifty male Spragne-Dawley rats,aged 7-8 weeks,weighing 200-250 g,were randomly divided into 5 groups (n =10 each) using a random number table:control group (group C),LPS and with 3 different doses (LD,MD HD groups).ALI was LPS 8 mg/kg injected via caudal vein LPS,LD,MD groups.Dexmedetomidine 5,10 15 μg/kg were intraperitoneally LD,MD...
This study explores the application of computational design aesthetics to conform Chinese aesthetic standards in customized glasses frames. Through quantitative analysis, it examines impact key variables (upper frame position, middle beam height, and lower position) on wearing. The results indicate that achieving a better feeling can be attained when upper is approximately 20% above vertical distance between eyebrow eye, about height frame, or roughly 40% eyelid angle mouth. These findings...
A biologically heuristic map construction and autonomous localization algorithm is proposed inspired by the cognitive mechanism of hippocampal structures to address problems limited accuracy environmental noise interference in simultaneous mapping mobile robots unknown environments. The self-motion information robot external visual landmark were used as inputs build location-aware model from grid cell place model, respectively. extracted combined with location obtained through Hebbian...