Clinical and demographic characteristics of patients undergoing endovenous laser ablation for saphenous vein insufficiency by Abdullah M. Alwahbi

Get full text

Intelligent implementation of muscle strain identification algorithm in Mi health exercise induced waist muscle strain by Hu Wei, Zhong Hao, Wang Changyong

“…In order to improve the accuracy and efficiency of identifying lumbar muscle strain, based on the You Only Look Once version 3 algorithm, an intelligent recognition filtering algorithm combining sliding window and histogram of oriented gradient features is proposed to avoid misdiagnosis caused by artifact interference. …”
Get full text

CM-YOLO: Typical Object Detection Method in Remote Sensing Cloud and Mist Scene Images by Jianming Hu, Yangyu Wei, Wenbin Chen, Xiyang Zhi, Wei Zhang

Get full text

TECHNIQUES FOR FORMATION OF FERROELECTRIC PHOTONIC AND PHONONIC CRYSTALS by V. V. Krutov, A. S. Sigov, A. A. Shchuka

“…Researches in the field of technology of creation of ferroelectric photonic and phononic crystals are analyzed. Features of formation of antiparallel ferroelectric domains are examined by various methods. …”
Get full text

The library of reference models of the physical layer signals by Sergey Gennadiyevich Rassomakhin, Sergey Gennadiyevich Veklich, Oleg Pavlovich Malofey

Get full text

Small Object Detection in UAV Remote Sensing Images Based on Intra-Group Multi-Scale Fusion Attention and Adaptive Weighted Feature Fusion Mechanism by Zhe Yuan, Jianglei Gong, Baolong Guo, Chao Wang, Nannan Liao, Jiawei Song, Qiming Wu

“…Such modifications enhance the model’s ability to capture the minute features of small objects. In addition, an adaptive feature fusion module is introduced, which is capable of automatically adjusting the weights based on the significance and contribution of features at different scales to improve the detection sensitivity for small objects. …”
Get full text

Topic adversarial neural network for cross-topic cyberbullying detection by Shufeng Xiong, Wenzhuo Liu, Bingkun Wang, Yinchao Che, Lei Shi

“…TANN integrates a multi-level feature extractor with a topic discriminator and a cyberbullying detector. …”
Get full text

Design of a Low-Latency <roman>d<italic>v</italic></roman>/<roman>d<italic>t</italic></roman> and <roman>d<italic>i</italic></roman>/<roman>d<italic>t</italic></roman> Closed-Loop... by Xuhao Zhu, Wu Chen, Yubo Yuan

Get full text

R-SABMNet: A YOLOv8-Based Model for Oriented SAR Ship Detection with Spatial Adaptive Aggregation by Xiaoting Li, Wei Duan, Xikai Fu, Xiaolei Lv

“…First, we introduce the Spatial-Guided Adaptive Feature Aggregation (SG-AFA) module, which enhances sensitivity to ship features while suppressing land scattering interference. …”
Get full text

Exposed conductor detection of 10 kV distribution line based on improved YOLOv8 by Qiwen JING, Sipeng HAO, Siyuan LI

“…The algorithm replaces the original convolution with omni-dimensional dynamic convolution in the backbone network, enhancing the features of exposed conductors through multi-dimensional feature extraction. …”
Get full text

YOLO-Air: An Efficient Deep Learning Network for Small Object Detection in Drone-Based Imagery by Jigang Qiu, Fangkai Cai, Ning Fu, Yuanfei Yao

“…Furthermore, we develop ASFM (Adaptive Scale Fusion Module), which suppresses background noise interference through effective multi-scale feature fusion and adaptive channel attention mechanisms, thereby improving the network&#x2019;s ability to detect small objects. …”
Get full text

Mobile platform continuous authentication scheme based on gait characteristics by Li YANG, Zhuoru MA, Chenghui ZHANG, Qingqi PEI

“…The popularity of smart phones renders people extremely high requirements for safety.But the traditional one-time authentication method can’t continuously guarantee the security of equipment.To solve the problem,a continuous authentication scheme based on gait characteristics was proposed to realize the identification of current visitors.Moving average filtering,threshold-based useful information interception method and other operations were adopted to reduce noise interference.Template interception was used to maximize the utilization of information,and an optimal combination of time domain features and frequency domain features were proposed to reduce the storage space requirement of users’ information.Finally,the support vector machine realized the identity authentication function.Experiments show that the proposed scheme can effectively authenticate the identities of visitors.…”
Get full text

Unsupervised Anomaly Detection on Metal Surfaces Based on Frequency Domain Information Fusion by Wenfei Wu, Tao Tao, Jinsheng Xiao, Yichu Yao, Jianfeng Yang

“…A scale-adaptive feature reconstruction module is used to effectively fuse the spatial and frequency domain features to fully utilize the information from different domains. …”
Get full text

Grape cluster detection based on spatial-to-depth convolution and attention mechanism by Shuai Rong, Xinghai Kong, Ruibo Gao, Zhiwei Hu, Hua Yang

“…Thirdly, a simple, parameter-free attention mechanism (SimAM) is applied to the backbone to improve the weight of grape targets and suppress background interference weight in feature extraction. Experiments show that combining STD-Conv and SimAM can improve the accuracy of YOLOv4, YOLOv5, and YOLOX. …”
Get full text

SDA-YOLO: An Object Detection Method for Peach Fruits in Complex Orchard Environments by Xudong Lin, Dehao Liao, Zhiguo Du, Bin Wen, Zhihui Wu, Xianzhi Tu

“…To address insufficient feature fusion flexibility caused by scale variations from occlusion and illumination differences in multi-scale peach detection, a novel Adaptive Multi-Scale Fusion Pyramid (AMFP) module is proposed to enhance the neck network, improving flexibility in processing complex features. …”
Get full text

A Joint LiDAR and Camera Calibration Algorithm Based on an Original 3D Calibration Plate by Ziyang Cui, Yi Wang, Xiaodong Chen, Huaiyu Cai

“…At the image level, corner features and localization markers facilitate the rapid and precise acquisition of 2D pixel coordinates, with minimal interference from environmental noise. …”
Get full text

SEMA-YOLO: Lightweight Small Object Detection in Remote Sensing Image via Shallow-Layer Enhancement and Multi-Scale Adaptation by Zhenchuan Wu, Hang Zhen, Xiaoxinxi Zhang, Xuechen Bai, Xinghua Li

“…Small object detection remains a challenge in the remote sensing field due to feature loss during downsampling and interference from complex backgrounds. …”
Get full text

A review of deep learning in blink detection by Jianbin Xiong, Weikun Dai, Qi Wang, Xiangjun Dong, Baoyu Ye, Jianxiang Yang

“…Compared with traditional methods, the blink detection method based on deep learning offers superior feature learning ability and higher detection accuracy. …”
Get full text

MambaPose: A Human Pose Estimation Based on Gated Feedforward Network and Mamba by Jianqiang Zhang, Jing Hou, Qiusheng He, Zhengwei Yuan, Hao Xue

“…We used slice downsampling (SD) to reduce the resolution of the feature map to half the original size, and then fused local features from four different locations. …”
Get full text

SE-ResUNet Using Feature Combinations: A Deep Learning Framework for Accurate Mountainous Cropland Extraction Using Multi-Source Remote Sensing Data by Ling Xiao, Jiasheng Wang, Kun Yang, Hui Zhou, Qianwen Meng, Yue He, Siyi Shen

“…The results showed the following: (1) feature fusion (NDVI + TerrainIndex + SAR) had the best performance (OA: 97.11%; F1-score: 96.41%; IoU: 93.06%), significantly reducing shadow/cloud interference. (2) SE-ResUNet outperformed ResUNet by 3.53% for OA and 8.09% for IoU, emphasizing its ability to recalibrate channel-wise features and refine edge details. (3) The model exhibited robustness across diverse slopes/aspects (OA > 93.5%), mitigating terrain-induced misclassifications. …”
Get full text