Search Results

With the increasing importance of machine learning, the privacy and security of training data have become a concern. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant attention for ...

• We construct a blockchain-based federated learning model, select trustworthy aggregation nodes in each training round.
• Cluster based on the linear similarity between local models, and verify the accuracy of each cluster's local model.

For the challenges of low learning efficiency, slow convergence speed and slow inference speed in robot path planning. This paper proposes an improved deep reinforcement learning algorithm for robot path planning. Firstly, the Dueling DQN network ...$$

Graph Convolutional Networks (GCNs) have shown great potential in skeleton-based human action recognition. However, due to the diversity and complexity, modeling human actions as general graphs and capturing discriminative spatial–temporal motion ...

• A robust graph convolution model for skeleton-based action recognition is proposed.
• Multi-sliced spatial–temporal graph realizes multi-granular action modeling.
• Partition strategies optimize the weight-sharing mechanism of graph ...

Graph Convolutional Networks (GCNs) have attracted considerable attention in the realm of human action recognition. However, conventional GCNs-based methods typically struggle to construct adjacency matrices that capture diverse semantics, thus ...

Identifying critical states prior to critical transitions in complex biological processes is essential for disease forecasting and early interventional therapy. Due to the complexity of the underlying mechanisms, the currently proposed methods based on ...

Pronuclei and blastomeres are key structures in early embryonic development, and by localizing these structures simultaneously, the developmental state of the embryo can be assessed more comprehensively. However, there are several unavoidable ...

Display Omitted

• For the first time, we propose a target localization scheme to locate pronuclei and blastomeres in embryo images.
• We use BiFormer to help the network better extract edge, and texture features of pronuclei and blastomeres.
• We use ...

Electroencephalography (EEG) stands as one of the most vital noninvasive tools in neuroscience and clinical practice. Nevertheless, EEG data is highly susceptible to interference from various artifacts, which, in turn, can severely impact the ...

Integrating imaging and genetic data provides a comprehensive approach to analyze brain disorders from different perspectives, which has important implications for the early diagnosis of Alzheimer’s Disease (AD) and the exploration of its ...

The Autonomous Underwater Vehicle (AUV), as an important equipment technology for the development and utilization of marine resources, is cableless, which can reduce the influence of cable disturbance on AUV control. Compared with other types of ...

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition and have achieved promising results. However, current GCN-based methods are limited by their inability to refine semantic-guided joint relations and ...

The accuracy in reduced-order building models affects prediction of energy consumption and indoor air temperature through the quality of control strategies in buildings. The parameter identification in grey-box thermal building models can be influenced ...

Deep learning based fusion mechanisms have achieved sophisticated performance in the field of image fusion. However, most existing approaches focus on learning global and local features but seldom consider to modeling semantic information, which ...

• A semantic perceptive infrared and visible image fusion Transformer (SePT) is devised. The fusion network can achieve better performance, because of the integration of local feature extracting, long-range dependency modeling and semantic ...

Image enhancement is a key step in image pre-processing. To address the problem of low quality and visual effect of images under low illumination conditions, this paper proposes an image enhancement method with hyperbolic oscillation factor and ...

• A slime mold algorithm with quadratic interpolation is proposed (SSMA).
• SSMA outperforms other algorithms in CEC2017 benchmark functions.
• SSMA has better convergence speed and convergence accuracy than other algorithms.
• Image ...

Up-sampling operations are frequently utilized to recover the spatial resolution of feature maps in neural networks for segmentation task. However, current up-sampling methods, such as bilinear interpolation or deconvolution, do not fully consider ...

The superior performances of pre-trained foundation models in various visual tasks underscore their potential to enhance the 2D models' open-vocabulary ability. Existing methods explore analogous applications in the 3D space. However, most of them only ...

Regionalization is the basic feature of cruise shipping network organization. We insist that the cruise networks of Alaska, Hawaii, etc., have developed into a whole with the scaling up of cruise tourism. To prove it, we used complex network analysis ...

Recently, human action recognition has been widely used in the fields of health monitoring, human-robot interaction, medical treatment, and sports. Due to the availability of various wearable devices on the market, we can easily access sensor data for ...

Graph Convolution Networks (GCNs) have become the main-stream framework for skeleton-based action recognition tasks. Aiming at the problem of redundant spatial-temporal feature information and neighborhood constraints obtained in GCNs, we propose a novel ...

Gossen’s First Law, also known as the law of diminishing marginal utility, describes the decreasing marginal utility gained from an increased consumption of a good or service and this is observed in various areas. This paper proposes the ...

• We propose a novel Wavelet-based downsampling module (HWD) for CNNs. To the best of our knowledge, our method is the first attempt to explore feasibility by prohibiting (impeding) information loss in the downsampling stage of DCNNs for the ...

Downsampling operations such as max pooling or strided convolution are ubiquitously utilized in Convolutional Neural Networks (CNNs) to aggregate local features, enlarge receptive field, and minimize computational overhead. However, for a ...