A5100449229- Complex Network Analysis Techniques
- Nuclear Physics and Applications
- Neural Networks and Applications
- Energy Efficient Wireless Sensor Networks
- Radiation Detection and Scintillator Technologies
- Opportunistic and Delay-Tolerant Networks
- Bayesian Modeling and Causal Inference
- Coastal wetland ecosystem dynamics
- Coastal and Marine Dynamics
- Infrared Target Detection Methodologies
- Mobile Ad Hoc Networks
- CCD and CMOS Imaging Sensors
- Advanced Measurement and Detection Methods
- Optical Systems and Laser Technology
- Network Security and Intrusion Detection
- Opinion Dynamics and Social Influence
- Nuclear reactor physics and engineering
- Distributed Control Multi-Agent Systems
- Air Quality Monitoring and Forecasting
- Neural Networks and Reservoir Computing
- Environmental Quality and Pollution
- Forest ecology and management
- Atomic and Subatomic Physics Research
- Advanced Image Fusion Techniques
- Superconductivity in MgB2 and Alloys
Dalian Medical University
2025
Chengdu University of Technology
2021-2025
China Three Gorges University
2025
Yanshan University
2014-2024
Wenzhou University
2023-2024
Wenzhou University of Technology
2023-2024
Peking University
2024
Changsha University of Science and Technology
2024
Computer Network Information Center
2023
Chinese Academy of Sciences
2023
This paper surveys recent advances in pulse-coupled neural networks (PCNNs) and their applications image processing. The PCNN is a neurology-inspired network model that aims to imitate the information analysis process of biological cortex. In years, many PCNN-derived models have been developed. Research with respect these can be divided into three categories: (1) reduce number manual parameters, (2) achieve better real cortex imitation performance, (3) combine them other methodologies. We...
Since the mid-1990s, X-ray phase contrast imaging (XPCI) has attracted increasing interest in industrial and bioimaging fields due to its high sensitivity weakly absorbing materials gained widespread acceptance. XPCI can simultaneously provide three modalities with complementary information, offering enriched details data. This study proposes an image fusion method that retrieves channels of XPCI. It integrates block features, non-subsampled contourlet transform (NSCT), a spiking cortical...
Abstract: Long non-coding RNA (lncRNA) is a type of distinguished by length exceeding 200 nucleotides. Recent studies indicated that lncRNAs participate in various biological processes, such as chromatin remodeling, transcriptional and post-transcriptional regulation, the modulation cell proliferation, death, differentiation, hence influencing gene expression cellular function. ADAMTS9-AS1, an antisense long situated on human chromosome 3p14.1, has garnered significant interest due to its...
In this paper, we propose an improved phase field model for interface capturing in simulating two-phase incompressible flows. The incorporates a second-order diffusion term, which utilizes nonlinear coefficient to assess the degree of deviation profile from its equilibrium state. particular, analyze scale mobility model, ensure that asymptotically approaches sharp limit as thickness zero. For accurate calculations surface tension, introduce generalized form smoothed Dirac delta functions can...
Neural tangent kernels (NTKs) have been proposed to study the behavior of trained neural networks from perspective Gaussian processes. An important result in this body work is theorem equivalence between a network and kernel regression with corresponding NTK. This allows for an interpretation as special cases regression. However, does hold practice? In paper, we revisit derivation NTK rigorously conduct numerical experiments evaluate theorem. We observe that adding layer updated do not yield...
Long non-coding RNAs (lncRNAs) are a type of RNA with length more than 200 nucleotides. They do not encode proteins but crucial in regulating gene expression and affecting the malignant biological behavior cancer. Small nucleolar host 10 (SNHG10) is novel lncRNA that plays regulatory role many tumors. Several recent studies have shown SNHG10 aberrantly expressed various forms This instability closely related to important tumorigenic processes, such as cell proliferation, migration, invasion,...
The pathophysiology and clinical manifestations of pulmonary embolism are complex, heterogeneous, the disease burden is severe, its prediction diagnosis major challenges. Artificial intelligence (AI) a field computer science that involves development programs complex data analysis designed to replicate human cognitive processes. In recent years, with continuous medical information technology, application AI in treatment diseases has made rapid progress, especially embolism, which mainly...
Early screening of lung nodules is mainly done manually by reading the patient's CT. This approach time-consuming laborious and prone to leakage misdiagnosis. Current methods for nodule detection face limitations such as high cost obtaining large-scale, high-quality annotated datasets poor robustness when dealing with data varying quality. The challenges include accurately detecting small irregular nodules, well ensuring model generalization across different sources. Therefore, this paper...
With the widespread application of Automated Guided Vehicles (AGV) in industrial production and warehouse logistics, challenges they face during operation are becoming increasingly apparent. Currently, path planning problem AGV has become one hot topics academic research. This paper provides an in-depth analysis performance real-world scenarios utilizes grid-based methods to construct a map environment model. Subsequently, detailed movement is conducted, improved pheromone method proposed...
Handheld mobile laser scanning (HMLS) can quickly acquire point cloud data, and has the potential to conduct forest inventory at plot scale. Considering problems associated with HMLS data such as large discreteness difficulty in classification, different classification models were compared order realize efficient separation of stem, branch leaf points from data. First, was normalized ground removed, then neighboring identified according three KNN algorithms eight geometric features...
Abstract In this study, the anti-noise performance of a pulse-coupled neural network (PCNN) was investigated in neutron and gamma-ray ( n − $$\gamma$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>γ</mml:mi> </mml:math> ) discrimination field. The experiments were conducted two groups. first group, radiation pulse signals pre-processed using Fourier filter to reduce original noise signals, whereas second left untouched simulate an extremely high-noise scenario. For each...
Machine learning classifiers have been rarely used for the identification of seafloor sediment types in rapidly changing dredge pits coastal restoration. Our study uses multiple machine to identify Caminada pit eastern part submarine sandy Ship Shoal Louisiana inner shelf United States (USA), and compares performance supervised classification methods. High-resolution bathymetry backscatter data, as well 58 grab samples were collected August 2018, about two years after dredging. Two primary...
Improving the efficiency of current neural networks and modeling them on biological systems have become prominent research directions in recent years. The pulse-coupled network (PCNN) is widely used to mimic computational characteristics human brain computer vision fields. However, PCNN faces limitations such as limited connections, high costs, a lack stochastic properties. This study proposes random-coupled (RCNN) address these limitations. RCNN employs inactivation process, selectively...