MFSE-TransUNet: A Thyroid Nodule Ultrasound Image Segmentation Network Integrated With Dynamic Feature Calibration and Edge Enhancement by Ye Lu, Jiaojiao Jing, Wenbo Zhang, Yali Kong

Get full text

D²SFormer: Dual Attention-Dynamic Bidirectional Transformer for Semantic Segmentation of Urban Remote Sensing Images by Yi Yan, Jiafeng Li, Jing Zhang, Liuqian Wang, Li Zhuo

“…Finally, the decoder dynamically fuses multiscale features to reconstruct boundaries and suppress artifacts by using a bidirectional feature pyramid network and dynamic upsampling. …”
Get full text

Copula entropy regularization transformer with C2 variational autoencoder and fine-tuned hybrid DL model for network intrusion detection by Srinivas Akkepalli, Sagar K

Get full text

Toward Characterizing Dark Matter Subhalo Perturbations in Stellar Streams with Graph Neural Networks by Peter Xiangyuan Ma, Keir K. Rogers, Ting S. Li, Renée Hložek, Jeremy J. Webb, Ruth Huang, Julian Meunier

Get full text

Multi-node cooperation based robust visible light intelligent positioning by Sicong LIU, Danping SU, Tiankuo WEI, Xianyao WANG

“…Visible light communication is expected to be one of the key alternative technologies for 6G with the advantages of abundant spectrum resources, less susceptibility to electromagnetic pollution and green safety, which also provides a new idea for high-precision indoor positioning.However, the positioning accuracy can be significantly degraded in the harsh indoor environment where LED that can be used as an anchor is insufficient or severely blocked.Therefore, a robust visible light intelligent positioning method based on multi-node cooperation was investigated.Considering the non-line-of-sight propagation of visible light and the dynamic change of user terminal orientation, a cooperative localization mechanism between user terminals was established to obtain mutual information gain and a convolutional-recurrent neural network was designed, and the theoretical analysis of cooperative localization accuracy performance was carried out.Simulation results show that the introduction of the cooperative localization mechanism can effectively improve positioning performance under harsh conditions.…”
Get full text

RHCrackNet: Refined Hierarchical Feature Fusion and Enhancement Network for Pixel-Level Pavement Anomaly Detection by Wenjing Liu, Zhenhua Li, Ji Wang, Qingjie Lu

“…This model incorporates feature fusion modules and feature enhancement modules to dynamically aggregate high-level semantic features with low-level detail features and enhance them through attention mechanisms. …”
Get full text

Efficient Pruning of Detection Transformer in Remote Sensing Using Ant Colony Evolutionary Pruning by Hailin Su, Haijiang Sun, Yongxian Zhao

Get full text

Robust Simplified Modeling of Microgrid in the Context of Constructing New Power Systems by Daxing WANG, Yan Ning, Jingpei WANG, Yang XU, Jun BI, Mingbiao ZHOU, Peng WANG

“…However, amid the analysis of the dynamic characteristics of microgrid-integrated power system, the current equivalent models appear to be not robust enough. …”
Get full text

CoPaD-Mark: A Coded Parallelizable Deep Learning-Based Scheme for Robust Image Watermarking by Andy M. Ramos, Cecilio Pimentel, Daniel P. B. Chaves

“…These convolutions enable dynamic feature extraction by adjusting convolutional filters based on image content. …”
Get full text

Global information aware network with global interaction graph attention for infrared small target detection by Ruimin Yang, Yidan Zhang, Guangshuai Gao, Liang Liao, Chunlei Li

“…Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. …”
Get full text

STCYOLO: Subway Tunnel Crack Detection Model with Complex Scenarios by Jia Zhang, Hui Li, Weidong Song, Jinhe Zhang, Miao Shi

“…To address these challenges, this paper proposes a novel crack detection network named STCYOLO. First, a dynamic snake convolution (DSConv) mechanism is introduced to adaptively adjust the shape and size of convolutional kernels, allowing them to better align with the elongated and irregular geometry of cracks, thereby enhancing performance under challenging lighting conditions. …”
Get full text

Develop an emotion recognition system using jointly connectivity between electroencephalogram and electrocardiogram signals by Javid Farhadi Sedehi, Nader Jafarnia Dabanloo, Keivan Maghooli, Ali Sheikhani

“…We propose a novel method of estimating effective connectivity (EC) to capture the dynamic interplay between the heart and brain during emotions of happiness, disgust, fear, and sadness. …”
Get full text

Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach by Himanshu Choudhary, Arishi Orra, Kartik Sahoo, Manoj Thakur

“…The actions generated by these agents are then fused by employing a convolutional neural network to provide a single risk-adjusted action. …”
Get full text

Median interacted pigeon optimization-based hyperparameter tuning of CNN for paddy leaf disease prediction by Jasmy Davies, S. Sivakumari

“…Furthermore, to extract relevant features from images of rice leaf diseases, Convolutional Neural Networks (CNNs) require efficient hyperparameter tuning. …”
Get full text

Improving robotic grasping accuracy through oriented bounding box detection with YOLOv11-OBB by Vo Duy Cong, Le Hoai Phuong

Get full text

Hybrid TCN-transformer model for predicting sustainable food supply and ensuring resilience by Ibrahim Alrashdi, Rasha M. Abd El-Aziz, Ahmed I. Taloba, Mohammed Farsi

“…Traditional forecasting models, such as ARIMA, LSTM, and GRU, fail to deal with the dynamic fluctuations and long-range correlations. …”
Get full text

Graph Neural Network Classification in EEG-Based Biometric Identification: Evaluation of Functional Connectivity Methods Using Time-Frequency Metric by Roghaieh Ashenaei, Ali Asghar Beheshti Shirazi

“…Integrated with Graph Convolutional Neural Networks (GCNNs), our approach leverages graph-structured FC data for superior classification. …”
Get full text

Node Classification Based on Kolmogorov-Arnold Networks by YUAN Lining, FENG Wengang, LIU Zhao

“…Aiming at the above problems, this paper proposes a fully connected neural model G-KAN based on the Kolmogorov-Arnold network (KAN), which does not require specific activations and explicit node message passing modules. It dynamically learns activations through KAN and introduces a contrastive loss guided by node similarity to implicitly extract the original graph information. …”
Get full text

Facial Beauty Prediction Combining Dual-Branch Feature Fusion With a Stacked Broad Learning System by Junying Gan, Hantian Chen, Wenchao Xu, Huicong Li, Zhenxin Zhuang, Zhen Chen

“…Second, a squeeze-and-excitation (SE) network attention-based connection layer dynamically adjusts feature weights, emphasizing important features and reducing irrelevant ones. …”
Get full text

Lightweight Attention-Based CNN Architecture for CSI Feedback of RIS-Assisted MISO Systems by Anming Dong, Yupeng Xue, Sufang Li, Wendong Xu, Jiguo Yu

“…The core contribution of this work lies in an innovative lightweight feedback architecture that deeply integrates multi-layer convolutional neural networks (CNNs) with attention mechanisms. …”
Get full text