A5101777490- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Face and Expression Recognition
- Emotion and Mood Recognition
- Image and Signal Denoising Methods
- ECG Monitoring and Analysis
- Neural Networks and Applications
- Advanced Clustering Algorithms Research
- Context-Aware Activity Recognition Systems
- Advanced Computing and Algorithms
- Time Series Analysis and Forecasting
- Functional Brain Connectivity Studies
- Glaucoma and retinal disorders
- Machine Fault Diagnosis Techniques
- Non-Invasive Vital Sign Monitoring
- Bayesian Methods and Mixture Models
- Heart Rate Variability and Autonomic Control
- Neuroscience and Neuropharmacology Research
- Acupuncture Treatment Research Studies
- Ophthalmology and Eye Disorders
- Anomaly Detection Techniques and Applications
- Epilepsy research and treatment
- Spectroscopy and Chemometric Analyses
- Traditional Chinese Medicine Studies
- Autoimmune Neurological Disorders and Treatments
University of Shanghai for Science and Technology
2020-2024
Shijiazhuang University
2024
Tourism College of Zhejiang
2020
Shanghai Normal University
2011-2019
Nanchang University
2011
Liaoning University of Technology
2009
Hunan University of Technology
2007
Institute of Space and Astronautical Science
1998
The selection of an appropriate wavelet is essential issue that should be addressed in the wavelet-based filtering electrocardiogram (ECG) signals. Since entropy can measure features uncertainty associated with ECG signal, a novel comprehensive criterion Ecom based on multiple criteria related to and energy proposed this paper search for optimal base specific signal. Taking account decomposition capability wavelets similarity information between decomposed coefficients analyzed integrates...
Due to high dimensionality and multiple variables, unsupervised classification of multivariate time series (MTS) involves more challenging problems than those univariate ones. Unlike the vectorization a feature matrix in traditional clustering algorithms, an pattern recognition scheme based on data is proposed for MTS samples this paper. To reduce computational load consumption, novel variable-based principal component analysis (VPCA) first devised reduction samples. Afterward, spatial...
A novel approach is presented in this paper to address the limitations of virtual machine technology, active kernel heuristic killing and behaviour technology computer network virus defence. The proposed method provides data mining specifically Object-Oriented Analysis (OOA) mining, detect deformed unknown viruses by analyzing sequence Win API calls PE files. Experimental results showcase Data Mining-based Antivirus (DMAV) system's superiority over existing scanning software multiple...
The Electrocardiogram (ECG) is a valuable signal recording the heart's electrical activity. filtering quality of ECG signals directly affects medical diagnosis. Since wavelet analysis can provide both time and frequency information, many nonlinear thresholding methods based on transform denoising have been applied to noise reduction signals. However, most these threshold shrinkage functions cannot adapt different due fixed transition curve threshold. Therefore, novel genetic optimized...
Many actuators and sensors made by smart materials have hysteresis feature which is a complex nonlinear phenomenon with multivalued mapping. Accurate identification of pattern in those helpful for improving the modeling control strategies systems. In this paper, general framework clustering hysteretic time series developed on basis tensor decomposition. First, high-dimensional multivariate data objects are transformed into three-order tensors. Then multilinear principal component analysis...
Without sufficient prior knowledge the identification of optimal cluster numbers is a difficult problem for unsupervised clustering. Since fuzzy entropy essential measuring information sets, combined index (CFE) developed searching best number clusters kb. The CFE involves compactness and separation both in data space membership space. partition sets evaluated by ratio symmetric cross subset pairs to average entropies clusters. most appropriate specific set determined maximum index. In order...
On the basis of wavelet theory, a novel Adaptive thresholding method (AWT) is proposed for ECG signal enhancement. The best base filtering can be automatically obtained through cross correlation coefficient and energy to entropy ratio. variable universal threshold (VarUniversal) applied different decomposition level so as suppress diverse noise. To achieve smooth cut-off transition, an identical shrinkage function (IcoShrinkage) also adopted in AWT according its coefficients with hard soft...
Most of the electroencephalogram (EEG) emotion recognitions are conducted in linear Euclidean space. However, it is difficult to accurately describe nonlinear characteris-tics multivariate EEG signals. Comparatively, Riemannian manifold a space which features can be analyzed more thoroughly. Therefore, inspired by geographical knowledge, an recognition methodology based on geomorphological (GFRM) proposed. Firstly, terms Wasserstein scalar curvature, automatic search strategy developed...
Due to the absence of a gold standard for threshold selection, brain networks constructed with inappropriate thresholds risk topological degradation or contain noise connections. Therefore, graph neural (GNNs) exhibit weak robustness and overfitting problems when identifying networks. Furthermore, existing studies have predominantly focused on strongly coupled connections, neglecting substantial evidence from other intricate systems that highlight value weakly Consequently, potential remains...
Activity recognition using smartphone provides a ubiquitous and unobtrusive way for people to realize health monitor ambient assisted living. Since human activities has characteristics of high complexity diversity, the accurate identification activity greatly depends on appropriate features extracted from limited signals efficiency pattern approaches. An unsupervised classification scheme based wavelet packet transform (WPT) half-cosine fuzzy clustering (HFC) is proposed in this paper...
With the fast development of human-machine interface technology, emotion recognition has attracted more and attentions in recent years. Compared to other physiological experimental signals frequently used recognition, EEG are easy record but not disguise. However, because high dimensionality data diversity human emotions, feature extraction classification still difficult. In this paper, we propose deep forest with multi-scale window (MSWDF) identify emotions. Deep Forest is an integrated...
Flaxseed can provide synergistic health benefits which are attributed to its enriched bioactive substances such as alpha-linolenic acid (ALA), flaxseed gums, protein and lignan. The research on the advantages of including anti-inflammation, anti-cancer, antioxidant, antidiabetic etc., have been confirmed. Generally, be consumed directly a whole or milled form. At present, in order improve nutritive values food products, functional additive, has incorporated into many staple products....
Chinese traditional medicine (CTM) plays an important role in illness treatment and medicare for a long time due to its safety, effectiveness, low-cost no obvious side effects. However, the meridian theory, fundamental theory of CTM, has mainly depended on empirical methods up now. In this paper, feature extraction method system through ECG signals measured at acupoints is presented. The measurement was firstly implemented two meridians 10 volunteers. Afterwards, were decomposed by wavelet...