Asymptotically Almost Automorphic Mild Solutions for a Class of Neutral Differential Equations with Delay by YAO Hui-li, LI Xiao-tong, WANG Jing-nan, LI Xue-xin

“…All kinds of differential equations as mathematical models have been built up due to different practical problems，so the problem of studying the existence of various solutions has attracted the attention of mathematical scholars at home and abroad. …”
Get full text

Research on Face Local Attribute Detection Method Based on Improved SSD Network Structure by Qun Luo, Zhendong Liu

“…On this basis, by organically connecting different layers of the SSD network and integrating convolution block attention module, the improved SSD network structure was used to realize face local attribute detection. …”
Get full text

MDA-MIM: a radar echo map prediction model integrating multi-scale feature fusion and dual attention mechanism by HU Qiang, GAO Yating, YIN Binli, QU Lianen

“…Multi-scale feature fusion and a dual attention mechanism were incorporated in MDA-MIM. Dilated convolution was used to extract and integrate multi-scale features. …”
Get full text

A dual path graph neural network framework for dementia diagnosis by Denghui Zhang, Chenxuan Zhu

“…We then performed multi-scale graph convolution to analyze brain connectivity at varying resolutions-from fine-grained to more extensive patterns, and ultimately employed an attention mechanism to enhance features across different domains. …”
Get full text

A raypath-consistent receiver correction in PS converted wave processing through seismic interferometry: New application for tropical zones New application for tropical zones by Andrés Salamanca, Luis Montes

“…This is the first application of the technique in Colombia, initially developed for permafrost zones, with different assumptions and surface complexity; and it resulted in an improved PS converted wave image.…”
Get full text

Adversarial sample generation algorithm for vertical federated learning by Xiaolin CHEN, Daoguang ZAN, Bingchao WU, Bei GUAN, Yongji WANG

“…To adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample generation framework was constructed for the VFL architecture.A white-box adversarial attack in the VFL was implemented by extending the centralized machine learning adversarial sample generation algorithm with different policies such as L-BFGS, FGSM, and C＆amp;W.By introducing deep convolutional generative adversarial network (DCGAN), an adversarial sample generation algorithm named VFL-GASG was designed to address the problem of universality in the generation of adversarial perturbations.Hidden layer vectors were utilized as local prior knowledge to train the adversarial perturbation generation model, and through a series of convolution-deconvolution network layers, finely crafted adversarial perturbations were produced.Experiments show that VFL-GASG can maintain a high attack success while achieving a higher generation efficiency, robustness, and generalization ability than the baseline algorithm, and further verify the impact of relevant settings for adversarial attacks.…”
Get full text

Towards a New Generation of Impulse‐Response Functions for Integrated Earth System Understanding and Climate Change Attribution by Alexander J. Winkler, Carlos A. Sierra

“…Abstract Impulse‐response functions (IRFs) are mathematical functions that represent the response of the coupled carbon‐climate system to different trajectories of fossil‐fuel emissions and land‐use. …”
Get full text

A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES by WU DingHai, WANG HuaiGuang, SONG Bin, ZHANG YunQiang

“…The bearing dataset of Case Western Reserve University which includes different rotational speeds and load is used to verify this method and a good recognition effect has been achieved.…”
Get full text

Packet-level labeling method for fine-grained multi-webpage browsing behavior recognition by GU Yue, CHEN Li, LI Dan, GAO Kaihui

“…This method combined one-dimensional convolutional neural networks with multi-head attention mechanisms to learn both local and global temporal correlation features between different packets within the same webpage. …”
Get full text

Online evaluation method for MMC submodule capacitor aging based on CapAgingNet by Xinlan Deng, Youhan Deng, Liang Qin, Weiwei Yao, Min He, Kaipei Liu

“…Subsequently, the CapAgingNet model is introduced, incorporating key technical modules to enhance performance: the Deep Stem module, which extracts larger receptive fields through multiple convolution layers and mitigates the impact of data sparsity in capacitor aging on feature extraction; the efficient channel attention (ECA) module, utilizing one-dimensional convolution for dynamic weighting to adjust the importance of each channel, thereby enhancing the ability of the model to process high-dimensional features in capacitor aging data; and the multiscale feature fusion (MSF) module, which integrates capacitor aging information across different scales by combining fine-grained and coarse-grained features, thus improving the capacity of the model to capture high-frequency variation characteristics. …”
Get full text

Influence of chronic prenatal hypoxia on the specialized contact apparatus of rat heart ventricles during ontogeny by N. S. Petruk

“…Pairwise comparisons between means of different groups were performed using Student’s t-test where, for each couple of normally distributed populations, the null hypothesis that the means are equal was verified. …”
Get full text

Tomato ripeness detection and fruit segmentation based on instance segmentation by Jinfan Wei, Yu Sun, Yu Sun, Lan Luo, Lingyun Ni, Mengchao Chen, Minghui You, Minghui You, Ye Mu, Ye Mu, He Gong, He Gong

“…The method proposes two innovative modules: the Adaptive and Oriented Feature Refinement module (AOFRM) and the Custom Multi-scale Pooling module (CMPRD) with Residuals and Depth. By deformable convolution and multi-directional asymmetric convolution, the AOFRM module adaptively extracts the shape and direction features of tomatoes to solve the problems of occlusion and overlap. …”
Get full text

ILR-Net: Low-light image enhancement network based on the combination of iterative learning mechanism and Retinex theory. by Mohan Yin, Jianbai Yang

“…Specifically, the network continuously learns local and global features of low-light images across different dimensions and receptive fields to achieve a clear and convergent illumination estimation. …”
Get full text

A Deep Reinforcement Learning Approach for Portfolio Management in Non-Short-Selling Market by Ruidan Su, Chun Chi, Shikui Tu, Lei Xu

“…Moreover, stock spatial interrelation representing the correlation between two different stocks is captured by a graph convolution network based on fundamental data. …”
Get full text

DEFIF-Net: A lightweight dual-encoding feature interaction fusion network for medical image segmentation. by Zhanlin Ji, Shengnan Hao, Quanming Zhao, Zidong Yu, Hongjiu Liu, Lei Li, Ivan Ganchev

“…Additionally, a novel multi-branch ghost module (MBGM) is used in the bottleneck layer of the network to enhance its efficiency in capturing and retaining different types of feature information. Lastly, a novel residual feature enhancement (RFE) decoder is utilized to emphasize boundary features, thereby increasing the network's sensitivity to lesion boundaries. …”
Get full text

Evaluating the Impact of Frequency Decomposition Techniques on LSTM-Based Household Energy Consumption Forecasting by Maissa Taktak, Faouzi Derbel

“…Contemporary approaches like LSTM and GRU networks process raw time series directly, failing to distinguish between distinct frequency components that represent different physical phenomena in household energy usage. …”
Get full text

Review of One-Stage Universal Object Detection Algorithms in Deep Learning by WANG Ning, ZHI Min

“…This paper takes one-stage object detection as the starting point and analyzes and summarizes the mainstream one-stage detection algorithms of the first one-stage object detection algorithm YOLO series (YOLOv1 to YOLOv11, YOLO main improved version), SSD, and DETR series based on Transformer architecture, based on the use of two different architectures: classical convolution and Transformer. …”
Get full text

Improving High-Precision BDS-3 Satellite Orbit Prediction Using a Self-Attention-Enhanced Deep Learning Model by Shengda Xie, Jianwen Li, Jiawei Cai

“…SCINet-SA leverages deep learning to model the temporal characteristics of orbit differences between BDS-3 ultra-rapid and final products. …”
Get full text

Resource Optimization Method Based on Spatio-Temporal Modeling in a Complex Cluster Environment for Electric Vehicle Charging Scenarios by Hongwei Wang, Wei Liu, Chenghui Wang, Kao Guo, Zihao Wang

“…It effectively shifts the load demand from peak periods to valley periods, minimizes the total peak–valley load difference, and significantly improves the security and reliability of the microgrid, thus providing a practical solution for resource allocation in intelligent clusters.…”
Get full text

High-resolution population mapping by fusing remote sensing and social sensing data considering the spatial scale mismatch issue by Peijun Feng, Zheng Ma, Jining Yan, Leigang Sun, Nan Wu, Luxiao Cheng, Dongmei Yan

“…However, the significant scale difference between the regional and grid levels, combined with the simple integration of multi-source data features without considering the spatial dependence of the population, results in lower accuracy. …”
Get full text