Deficiency of IL-7R attenuates abdominal aortic aneurysms in mice by inhibiting macrophage polarization towards M1 phenotype through the NF-κB pathway by Shengnan Xu, Xueyu Han, Yi Yu, Chuan Qu, Bo Yang, Bo Shen, Xin Liu

“…Result We demonstrated that IL-7R was elevated in mice with AAAs. Blocking IL-7R can inhibit the formation of AAAs and reduce aortic dilatation, elastic layer degradation, and inflammatory cell infiltration. …”
Get full text

Smart Car Damage Assessment Using Enhanced YOLO Algorithm and Image Processing Techniques by Muhammad Remzy Syah Ramazhan, Alhadi Bustamam, Rinaldi Anwar Buyung

“…This study proposes an enhanced YOLOv9 network tailored to detect six types of car damage. The enhancements include the convolutional block attention module (CBAM), applied to the backbone layer to enhance the model’s ability to focus on key damaged regions, and the SCYLLA-IoU (SIoU) loss function, introduced for bounding box regression. …”
Get full text

Key method of digitization of power distribution panel with artificial intelligence identification for power communication network by LIU Lin, YANG Zhimin, HUANG Qiang, YANG Jingwei, CHEN Yitong

“…Secondly, an improved YOLOv5 network was introduced for the task of icon detection. By integrating ConvNext Block and bidirectional feature pynamid network (Bi-FPN) structures, the recognition accuracy for small targets, such as status lights, was significantly enhanced. …”
Get full text

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

“…First, adopting a DL approach improves the object's detection in the enhanced ResNet (residual neural network) and connects it with the convolution layer for each ResNet block. …”
Get full text

Research on herd sheep facial recognition based on multi-dimensional feature information fusion technology in complex environment by Fu Zhang, Fu Zhang, Xiaopeng Zhao, Shunqing Wang, Yubo Qiu, Sanling Fu, Yakun Zhang

“…For multi-part detection network, The YOLOv5s path aggregation network was modified by incorporating a multi-link convolution fusion block (MCFB) to enhance fine-grained feature extraction across objects of different sizes. …”
Get full text

Infrared and visible image fusion network based on multistage progressive injection by Kaixuan Chang, Jianhua Huang, Xiyan Sun, Jian Luo, Shitao Bao, Huansheng Huang

“…Abstract Currently, single-sensor data is frequently utilized in technologies such as object detection. However, in certain scenarios, some sensors may experience failure or information loss, significantly impacting model performance. …”
Get full text

Securing IoT Against Slow-Rate DDoS Attacks: Implementation With Tofino P4 ASIC Hardware by Erick D. Ramirez-Martinez, Jesus A. Perez-Diaz, Noe M. Yungaicela-Naula, Sergio Armando Gutierrez, Christian Garzon

“…A decision tree model is deployed within a programmable switch (P4) to detect the attacks. Furthermore, an SDN controller is responsible for generating mitigation policies and deploying them to the programmable switches, effectively blocking malicious flows. …”
Get full text

Human fall direction recognition in the indoor and outdoor environment using multi self-attention RBnet deep architectures and tree seed optimization by Awais Khan, Jung-Yeon Kim, Chomyong Kim, Muhammad Attique Khan, Hyojin Shin, Jiyoung Woo, Yunyoung Nam

“…Subsequently, we developed four novel residual block and self-attention mechanisms, named residual block-deep convolutional neural network (3-RBNet), 5-RBNet, 7-RBNet, and 9-RBNet self-attention models. …”
Get full text

ST-YOLO: a deep learning based intelligent identification model for salt tolerance of wild rice seedlings by Qiong Yao, Qiong Yao, Pan Pan, Pan Pan, Xiaoming Zheng, Xiaoming Zheng, Guomin Zhou, Guomin Zhou, Guomin Zhou, Jianhua Zhang, Jianhua Zhang

“…BackgroundIn response to the limited models for salt tolerance detection in wild rice, the subtle leaf features, and the difficulty in capturing salt stress characteristics, resulting in low recognition and detection rates and accuracy, a deep learning-based ST-YOLO wild rice seedling salt tolerance phenotype evaluation and identification model is proposed.MethodIn order to improve accuracy and achieve model lightweighting, a multi branch structure DBB (Diverse Branch Block) is used to replace the convolutional layers in the C2f module, and a reparameterization module C2f DBB is proposed to replace some C2f modules. …”
Get full text

Research and Experiment on a Chickweed Identification Model Based on Improved YOLOv5s by Hong Yu, Jie Zhao, Xiaobo Xi, Yongbo Li, Ying Zhao

“…Firstly, the Squeeze-and-Excitation Module (SE) and Convolutional Block Attention Module (CBAM) were added to the model’s feature extraction network to improve the model’s recognition accuracy; secondly, the Ghost convolution lightweight feature fusion network was introduced to effectively identify the volume, parameter amount, and calculation amount of the model, and make the model lightweight; finally, we replaced the loss function in the original target bounding box with the Efficient Intersection over Union (EloU) loss function to further improve the detection performance of the improved YOLOv5s model. …”
Get full text

Flat U-Net: An Efficient Ultralightweight Model for Solar Filament Segmentation in Full-disk Hα Images by GaoFei Zhu, GangHua Lin, Xiao Yang, Cheng Zeng

“…Each block effectively optimizes the channel features from the previous layer, significantly reducing parameters. …”
Get full text

MSFA-BEVNet: Optimization of BEV Scene Recognition Driven by Multiscale Feature Fusion and Alignment by Xiubin Cao, Yifan Li, Hongwei Li

“…This study proposes a novel architecture that integrates multiscale feature extraction and crossmodal structural alignment to enhance the representation and detection capabilities of BEV features. Specifically, we employ a DCN-based block for visual feature extraction, comprising layer normalization (LN), feedforward networks (FFNs), and the Gaussian Error Linear Unit (GELU) activation function, aligned with the Vision Transformer (ViT) paradigm to improve feature modeling. …”
Get full text

Study on real-time warning system of blind path for the visually impaired based on improved deep residual shrinkage network by Zhezhou Yu, Fuwang Wang

“…Additionally, considering the complexity of the road environment and the fact that EEG signals are prone to external interference during acquisition, this study introduces an improved deep residual shrinkage network based on dense blocks (DB-DRSN). DB-DRSN replaces the convolutional hidden layer in the original residual shrinkage module with dense blocks and integrates dense connections to optimize the use of both shallow and deep features. …”
Get full text

CPFT-MOSA: A Comprehensive Parallel Fault-Tolerant Multi-Objective Simulated Annealing Framework for UAV-Assisted Edge Computing in Smart City Traffic Management by Ahmed Shamil Mustafa, Salman Yussof, Nurul Asyikin Mohamed Radzi

“…The proposed method decouples YOLO-based object detection tasks into several parallel modules within each UAV processing block and implements a dynamic resource management mechanism to balance processing efficacy and reliability. …”
Get full text

Spatial and Channel Attention Integration with Separable Squeeze-and-Excitation Networks for Image Classifications by Nazmul Shahadat, Shleshma Regmi, Anup Rijal

“…This paper proposes a novel architecture by integrating spatial and channel attention mechanisms using separable SE (SC-SE) Layers. Our proposed SC-SE layer with 1D CNN block is applied to the SqueezeNext architecture to construct our SC-SE network (SC-SENet). …”
Get full text

Review Study about Portable and Wearable Artificial Kidney Systems by Fanar Aljanabi, Hassanain Ali Hussein Lafta

“…As a result, the discussed studies found that using peristaltic pump pumps with a phase difference by half cycle between blood and dialysate will cause a higher urea clearance rate; multiple studies focused on the modification of the dialyzing filter to find that using Polyethene glycol surface-modified silicon nanopore membranes, dual-layer hollow fiber membranes, the use of BRECS cell therapy, carbon activated blocks, all contributed highly in enhancing the dialyzing process providing the patients with highly efficient blood purification session. …”
Get full text

Multi-View Attention Network With Iterative Feature Refinement and Boundary Awareness for Endoscopic Image Segmentation by Dongzhi He, Rui Zhang, Yu Liang, Jiaping Chen, Yunqi Li

“…To bridge the semantic gap between different feature layers, we propose an Attention-based Cross-layer Feature Fusion (ACFF) block, which incorporates a Triplet Efficient Transformer Attention (TETA) mechanism to capture long-range dependencies across multiple views. …”
Get full text

Research on Optimized Algorithm for Deep Learning Based Recognition of Sediment Particles in Turbulent Flow by WANG Hao, YANG Feiqi, ZHANG Lei, WU Wei, XIE Haonan, ZHAO Lin

“…The YOLOv5 algorithm adopted in this study excels at detecting small targets and provides multi-scale detection, strong versatility, fast training, inference speeds, and adaptable fine-tuning capabilities. …”
Get full text

CXR-Seg: A Novel Deep Learning Network for Lung Segmentation from Chest X-Ray Images by Sadia Din, Muhammad Shoaib, Erchin Serpedin

“…The proposed network mainly consists of four components, including a pre-trained EfficientNet as an encoder to extract feature encodings, a spatial enhancement module embedded in the skip connection to promote the adjacent feature fusion, a transformer attention module at the bottleneck layer, and a multi-scale feature fusion block at the decoder. …”
Get full text

BCSM-YOLO: An Improved Product Package Recognition Algorithm for Automated Retail Stores Based on YOLOv11 by Pingqing Hou, Shaoze Huang

“…Then, the Convolutional Block Attention Module (CBAM) screens the processed data, adaptively focuses on the key regions, and suppresses the background interference. …”
Get full text