A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity by Guangwen Peng, Yingbing Liu, Cong Xiao, Wenying Du, Changjiang Xiao

Subjects: Get full text

Efficient Gearbox Fault Diagnosis Based on Improved Multi-Scale CNN with Lightweight Convolutional Attention by Bin Yuan, Yaoqi Li, Suifan Chen

Subjects: “…dynamic convolutional kernel…”
Get full text

Dynamic Gesture Recognition and Interaction of Monocular Camera Based on Deep Learning by SUNBo wen, YU Feng

Get full text

HyperTransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Hyperspectral Image Classification by Xin Dai, Zexi Li, Lin Li, Shuihua Xue, Xiaohui Huang, Xiaofei Yang

“…Specifically, the proposed HyperTransXNet comprises three key modules: (1) a Hybrid Spatial-Spectral Module (HSSM) that captures the refined local spectral-spatial features and models global spectral correlations by combining depth-wise dynamic convolution with frequency-domain attention; (2) a Mixture-of-Experts Routing (MoE-R) module that adaptively fuses multi-scale features by dynamically selecting optimal experts via Top-K sparse weights; and (3) a Spatial-Spectral Tokens Enhancer (SSTE) module that ensures causality-preserving interactions between spectral bands and spatial contexts. …”
Get full text

Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies by Seyed Hamed Haghshenas, Mia Naeini

“…Dynamic State Estimation is a crucial task in power systems. …”
Get full text

Image Classification Model Based on Contrastive Learning With Dynamic Adaptive Loss by Quandeng Gou, Jingxuan Zhou, Zi Li, Fangrui Zhang, Yuheng Ren

“…Most existing mainstream image classification models use the Convolutional Neural Network (CNN), the Transformer, or a combination of both as the backbone. …”
Get full text

A text classification method by integrating mobile inverted residual bottleneck convolution networks and capsule networks with adaptive feature channels by Tao Jin, Jiaming Liu

“…A Capsule Network is designed to adaptively adjust the importance of different feature channels, including N-gram convolutional layers, selective kernel network layers, primary capsule layers, convolutional capsule layers, and fully connected capsule layers, aiming to enhance the model’s ability to capture semantic information of text across different feature channels. …”
Get full text

Dynamics of Lemon Crop Production in Tambo Grande, Piura: Implementation of Convolutional Neural Networks and Analysis of Risk Management Associated with Thermal Climatic Phenomena by Luis Meneses, Mirtha Ortega, Misael Rivas, Piero Fernández, Antonio Angulo

“…This study uses satellite indices (NDVI and NDWI) and convolutional neural networks (CNNs, specifically AlexNet) to analyze crop dynamics and health during extreme events. …”
Get full text

STAGE framework: A stock dynamic anomaly detection and trend prediction model based on graph attention network and sparse spatiotemporal convolutional network. by Ming Shi, Roznim Mohamad Rasli, Shir Li Wang

“…This framework offers an innovative solution for stock prediction, adapting to the complex dynamics of real-world markets.…”
Get full text

Research on Detection of Icing Cover Transmission Lines Under Different Weather Conditions Based on Wide-Field Dynamic Convolutional Network LDKA-NET by Xinsheng Dong, Yuanhao Wan, Yongcan Zhu, Chao Ji

Subjects: “…expectation maximization dynamic convolutional attention…”
Get full text

Attention Adaptive Temporal Graph Convolutional Network for Long-Term Seasonal Sea Surface Temperature Forecasting by Ling Xiao, Peihao Yang, Yuxue Wang, Sheng Li, Baoqin Chen

Get full text

LO-MLPRNN: A Classification Algorithm for Multispectral Remote Sensing Images by Fusing Selective Convolution by Xiangsuo Fan, Yan Zhang, Yong Peng, Qi Li, Xianqiang Wei, Jiabin Wang, Fadong Zou

Subjects: Get full text

MDPruner: Meta-Learning Driven Dynamic Filter Pruning for Efficient Object Detection by Lingyun Zhou, Xiaoyong Liu

“…Filter pruning is a potent technique for diminishing the computational demands of Convolutional Neural Networks (CNNs), while effectively retaining model performance in image categorization tasks. …”
Get full text

Research on the roadheader cutting control system based on convolutional neural network and fuzzy PID by LI Yingna, CUI Yanping, AN Boshuo, LIU Baijian, JIN Jianwei

Subjects: Get full text

Stability-Optimized Graph Convolutional Network: A Novel Propagation Rule with Constraints Derived from ODEs by Liping Chen, Hongji Zhu, Shuguang Han

Subjects: Get full text

Enhanced Wind Power Forecasting Using Graph Convolutional Networks with Ramp Characterization and Error Correction by Xin He, Yichen Ma, Jiancang Xie, Gang Zhang, Tuo Xie

Subjects: Get full text

Graph convolution-based adaptive feature fusion method for MRI brain tumor segmentation by Ye ZHANG, Muqing ZHANG, Xuegang YUAN, Datian NIU

Subjects: “…computer neural network; brain tumor segmentation; 3d u-net; graph convolution inference bottleneck layer; dynamic snake convolution; adaptive spatial feature fusion…”
Get full text

Dynamic Path Flow Estimation Using Automatic Vehicle Identification and Probe Vehicle Trajectory Data: A 3D Convolutional Neural Network Model by Can Chen, Yumin Cao, Keshuang Tang, Keping Li

“…Dynamic path flows, referring to the number of vehicles that choose each path in a network over time, are generally estimated with the partial observations as the input. …”
Get full text

WSDC-ViT: a novel transformer network for pneumonia image classification based on windows scalable attention and dynamic rectified linear unit convolutional modules by Yu Gu, Haotian Bai, Meng Chen, Lidong Yang, Baohua Zhang, Jing Wang, Xiaoqi Lu, Jianjun Li, Xin Liu, Dahua Yu, Ying Zhao, Siyuan Tang, Qun He

“…Specifically, the network integrates a scalable self-attention mechanism that decouples the query, key, and value dimensions to reduce computational overhead and improve contextual learning, while an interactive window-based attention module further strengthens long-range dependency modeling. Additionally, a convolution-based module equipped with a dynamic ReLU activation function is embedded within the transformer encoder to capture fine-grained local details and adaptively enhance feature expression. …”
Get full text

DualDyConvNet: Dual-Stream Dynamic Convolution Network via Parameter-Efficient Fine-Tuning for Predicting Motor Prognosis in Subacute Stroke by Yunjeong Jang, Joohye Jeong, Yun Kwan Kim, Da-Hye Kim, Wanjoo Park, Laehyun Kim, Yun-Hee Kim, Minji Lee

Subjects: Get full text