Research on semantic segmentation of parents in hybrid rice breeding based on improved DeepLabV3+ network model by WEN Jia, LIANG Xifeng, WANG Yongwei

“…Compared with other mainstream network models and advanced network models, it is found that the accuracy of different parameters of improved DeepLabV3+ network model is improved. …”
Get full text

Federated Learning-Based Credit Card Fraud Detection: A Comparative Analysis of Advanced Machine Learning Models by Zheng Han

“…FedAVG-DWA provides the best performance in different clients’ systems. However, system heterogeneity, communication costs, and data imbalance remain critical. …”
Get full text

Fish feeding behavior recognition model based on the fusion of visual and water quality features by Zheng ZHANG, Bosheng ZOU

“…To better capture the global features of different aggregation levels and the detailed features of feeding behavior, a context-aware local attention mechanism (Cloatt) was introduced in each convolution stage of ConvNeXtV2-T. …”
Get full text

Segmented Frequency-Domain Correlation Prediction Model for Long-Term Time Series Forecasting Using Transformer by Haozhuo Tong, Lingyun Kong, Jie Liu, Shiyan Gao, Yilu Xu, Yuezhe Chen

“…By segmenting the long-term time series and performing discrete Fourier transforms on different segments, we aim to identify frequency-domain correlations between these segments. …”
Get full text

An improved multi-object instance segmentation based on deep learning by Nawaf Alshdaifat, Mohd Azam Osman, Abdullah Zawawi Talib

“…The findings also revealed that in terms of average precision over IoU (AP) threshold measurements using different thresholds, the proposed approach obtained improved results compared to other well-known segmentation approaches. …”
Get full text

A lightweight and efficient gesture recognizer for traffic police commands using spatiotemporal feature fusion by Jun Xiao, Honghan Li, Ji Zhao

“…Initially, keypoints related to traffic police gestures are extracted using the Efficient Progressive Feature Fusion Network (EPFFNet), followed by feature modeling and fusion to enable the recognition network to better learn the temporal characteristics of gestures. Additionally, a convolution network branch and a hybrid attention branch are incorporated to further extract skeleton information from the traffic police gesture data, assign different temporal weights to key frames, and enhance the focus on important channels. …”
Get full text

Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals by Swetha Padmavathi Polisetty, Radhamani Ellapparaj, Karthikeyan M P

“…After data preprocessing to reduce noise and artifacts from EEGs, an 11-layer deep learning model consisting of convolution and LSTM layers with LeakyReLU activation function and different kernel sizes was implemented to automatically extract and classify features. …”
Get full text

Complex Indoor Human Detection with You Only Look Once: An Improved Network Designed for Human Detection in Complex Indoor Scenes by Yufeng Xu, Yan Fu

“…The method proposed in this article combines the spatial pyramid pooling of the backbone with an efficient partial self-attention, enabling the network to effectively capture long-range dependencies and establish global correlations between features, obtaining feature information at different scales. At the same time, the GSEAM module and GSCConv were introduced into the neck network to compensate for the loss caused by differences in lighting levels by combining depth-wise separable convolution and residual connections, enabling it to extract effective features from visual data with poor illumination levels. …”
Get full text

DMSF-YOLO: Cow Behavior Recognition Algorithm Based on Dynamic Mechanism and Multi-Scale Feature Fusion by Changfeng Wu, Jiandong Fang, Xiuling Wang, Yudong Zhao

“…For the problem in multi-scale behavior changes of dairy cows, a multi-scale convolution module (MSFConv) is designed, and some C3k2 modules of the backbone network and neck network are replaced with MSFConv, which can extract cow behavior information of different scales and perform multi-scale feature fusion. …”
Get full text

Twofold dynamic attention guided deep network and noise-aware mechanism for image denoising by Zihao Chen, Alex Noel Joseph Raj, Vijayarajan Rajangam, Wei Li, Vijayalakshmi G.V. Mahesh, Zhemin Zhuang

“…Convolutional neural networks are given extensive attention towards noise removal due to their good performance over traditional denoising algorithms. …”
Get full text

An Edge Recognition Method for Insulator State Based on Multi-dimension Feature Fusion by Dongmei HUANG, Yueqi WANG, Anduo HU, Jinzhong SUN, Shuai SHI, Yuan SUN, Lingfeng FANG

“…And a deep learning network integrating multi-dimension feature extraction is designed, which, by using the ResNet101 as the main feature extraction network, uses the Inception module to build the data pooling layer, and embeds the compression incentive module and convolution attention module to extract features from different dimensions. …”
Get full text

Automatic Disease Detection from Strawberry Leaf Based on Improved YOLOv8 by Yuelong He, Yunfeng Peng, Chuyong Wei, Yuda Zheng, Changcai Yang, Tengyue Zou

“…Furthermore, a parameter-sharing diverse branch block (DBB) sharing head is constructed to improve the model’s target processing ability at different spatial scales and increase its accuracy without adding too much calculation. …”
Get full text

AI-enhanced real-time monitoring of marine pollution: part 1-A state-of-the-art and scoping review by Navya Prakash, Navya Prakash, Oliver Zielinski, Oliver Zielinski

“…This review synthesizes 53 recent studies on Artificial Intelligence applications in marine pollution detection, focusing on different model architectures, sensing technologies and preprocessing methods. …”
Get full text

LPFFNet: Lightweight Prior Feature Fusion Network for SAR Ship Detection by Xiaozhen Ren, Peiyuan Zhou, Xiaqiong Fan, Chengguo Feng, Peng Li

“…In addition, the enhanced ghost convolution (EGConv) is used to generate more reliable gradient information. …”
Get full text

An applied noise model for scintillation-based CCD detectors in transmission electron microscopy by Christian Zietlow, Jörg K. N. Lindner

“…Thus, this paper aims to give an insight into the different noise contributions occurring on such detectors, into their underlying statistics and their correlation. …”
Get full text

Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification by V. Hnatushenko, V. Hnatushenko, V. Hnatushenko, D. Soldatenko

“…To illustrate our method, we use Sentinel-2 remote sensing (RS) images covering a number of regions in Ukraine, and then we create an image dataset of the region and for training and testing make data augmentation. The models with different architectural features were investigated.…”
Get full text

Scmaskgan: masked multi-scale CNN and attention-enhanced GAN for scRNA-seq dropout imputation by You Wu, Li Xu, Xiaohong Cong, Hanxiao Li, Yanli Li

“…Finally, multiple experiments were conducted to evaluate the methods’ performance using seven different data types and scRNA-seq data from ten neuroblastoma samples. …”
Get full text

Multi-Function Working Mode Recognition Based on Multi-Feature Joint Learning by Lei Liu, Minghua Wu, Dongyang Cheng, Wei Wang

“…This hybrid model leverages the local convolution operations of the CNN module to extract local characters from radar pulse sequences, capturing the dynamic patterns of radar waveforms across different modes. …”
Get full text

Crack Detection and Evolution Law for Rock Mass under SHPB Impact Tests by Xie Beijing, Dihao Ai, Yu Yang

“…Secondly, a deep convolution network model named CrackSHPB was designed based on a deep learning algorithm. …”
Get full text

Comparative Analysis of Hybrid Deep Learning Models for Electricity Load Forecasting During Extreme Weather by Altan Unlu, Malaquias Peña

“…This research is divided into two case studies that analyze different combined DL model architectures. Case Study 1 conducts CNN-Recurrent (RNN, LSTM, GRU, BiRNN, BiGRU, and BiLSTM) models with fully connected dense layers, which combine convolution and recurrent neural networks to capture both spatial and temporal dependencies in the data. …”
Get full text