A5045622740- Fault Detection and Control Systems
- Machine Learning and ELM
- Advanced Algorithms and Applications
- Face and Expression Recognition
- Neural Networks and Applications
- Energy Load and Power Forecasting
- Advanced Decision-Making Techniques
- Hydraulic Fracturing and Reservoir Analysis
- Advanced Computational Techniques and Applications
- Image and Signal Denoising Methods
- Hybrid Renewable Energy Systems
- Industrial Technology and Control Systems
- Stability and Control of Uncertain Systems
- Drilling and Well Engineering
- Machine Fault Diagnosis Techniques
- Advanced MIMO Systems Optimization
- Nanoplatforms for cancer theranostics
- Advanced Sensor and Control Systems
- Anomaly Detection Techniques and Applications
- Rock Mechanics and Modeling
- Energy and Environment Impacts
- Evaluation Methods in Various Fields
- Power Line Inspection Robots
- Iterative Learning Control Systems
- Advanced Graph Neural Networks
Northeastern University
2017-2024
Hebei University of Technology
2006-2024
Union Hospital
2023
Huazhong University of Science and Technology
2023
Hohai University
2022-2023
University of Macau
2020-2023
Shenyang Jianzhu University
2023
Qiqihar Medical University
2022
Children's Hospital of Chongqing Medical University
2022
Chongqing Medical University
2022
Broad learning system (BLS) is a novel neural network with effective and efficient ability. BLS has attracted increasing attention from many scholars owing to its excellent performance. This article proposes weighted (WBLS) based on tackle the noise outliers in an industrial process. WBLS provides unified framework for easily using different methods of calculating penalty factor. Using factor constrain contribution each sample modeling, normal abnormal samples were allocated higher lower...
Videos flow as the mixture of language, acoustic, and vision modalities. A thorough video understanding needs to fuse time-series data different modalities for prediction. Due variable receiving frequency sequences from each modality, there usually exists inherent asynchrony across collected multimodal streams. Towards an efficient fusion asynchronous streams, we need model correlations between elements The recent Multimodal Transformer (MulT) approach extends self-attention mechanism...
Comprehensive Summary Carbon nanodots (CDs) with high photothermal performance are ideal candidates for tumor therapy (PTT). Herein, we investigated the of CDs synthesized from urea and citric acid via solvothermal method in dimethyl sulfoxide (DMSO) at different temperatures. Photothermal conversion efficiency (PCE) up to 61.3% was obtained 150 °C (150‐CDs), which is much better than 180 (180‐CDs). By analyzing morphologies, chemical structures, absorption spectra these CDs, found that...
Abstract Formamidinium (CH(NH 2 ) , FA) lead halide perovskites exhibit excellent optoelectronic properties for the applications of light‐emitting diodes and lasers. However, reported formamidinium bromide (FAPbBr 3 perovskite‐based lasers mainly depend on external feedback or Fabry–Pérot mode cavities suffer from moderate quality ( Q factors. Herein, solution‐processed square quasi‐circular FAPbBr microdisks are developed to achieve room‐temperature naturally facet‐formed whispering gallery...
Aiming at simplifying the network structure of broad learning system (BLS), this article proposes a novel simplification method called compact BLS (CBLS). Groups nodes play an important role in modeling process BLS, and it means that there may be correlation between nodes. The proposed CBLS not only focuses on compactness but also pays closer attention to Learning from idea Fused Lasso Smooth Lasso, uses L1 -regularization term fusion penalize each output weight difference adjacent weights,...
Abstract This study aims to investigate the feasibility of using steel slag aggregate in concrete‐filled tubes by conducting axial compression tests on five groups 10 circular tube (SSCFST) slender columns. The failure mode, load–deformation curve, load–strain bearing capacity, initial stiffness and ductility columns are analyzed. effects replacement ratio slenderness compressive behaviors specimens also quantified. These test results employed verify reliability a finite element model SSCFST...
In this paper, two basic assumptions are introduced: (1) The number and length distribution of fractures in fractured rock mass accordance with the fractal law. (2) Fluid seepage satisfies cubic Based on these assumptions, model parallel radial is established, tensor fracture network which reflects geometric characteristics under kinds derived. influence geometry permeability analyzed, validity accuracy verified by comparing calculated results theoretical physical test. show that coefficient...
Wind energy, a highly popular renewable clean has been increasingly valued by the international community and leaping forward. However, original wind speed signal characterized intermittent fluctuations impose heavy burdens on forecasting of farms. This study proposed method complying with model integrating Variational Mode Decomposition (VMD) Improved Multi-Objective Dragonfly Optimization Algorithm (IMODA). First, VMD was adopted to decompose signal, as an attempt obtain multiple...
Broad learning system (BLS), a novel incremental algorithm, has attracted more and attention application. BLS achieves perfect balance between performance modeling efficiency based on the mean square error (MSE) criterion. However, MSE assumes that random an observed value real is Gaussian distribution, which may be inconsistent to real-world situation. Moreover, distributional assumptions cast doubt generalization validity of built model. In this article, we propose distribution-free for...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> Two-dimensional fast Gabor transform algorithms are useful for real-time applications due to the high computational complexity of traditional 2-D complex-valued discrete (CDGT). This paper presents two block time-recursive DHT-based real-valued (RDGT) and its inverse develops a parallel approach implementation algorithms. The proposed is analyzed compared with that existing CDGT results indicate...
The evolution and distribution of fracture network induced by mining is essential to determine the mechanical properties permeability disturbed rock mass. In this paper, similar material model tests are employed simulate stress variation, cyclic breaking, formation status overlying strata with different loading conditions, properties, process. fractal dimension mining‐induced varied advancing, evolvement laws advancing footage concerned obtained. By establishing relationship between length...
In this paper, the 1-D real-valued discrete Gabor transform (RDGT) proposed in our previous work and its relationship with complex-valued (CDGT) are briefly reviewed. Block time-recursive RDGT algorithms for efficient fast computation of coefficients reconstruction original signal from then developed both critical sampling case oversampling case. Unified parallel lattice structures implementation studied. And computational complexity analysis comparison show that provide a more faster...