检索结果-内蒙古大学图书馆

YOLO-Ant: A Lightweight Detector via Depthwise Separable Convolutional and Large Kernel Design for Antenna Interference Source Detection

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Tang, Xiaoyu Chen, Xingming Cheng, Jintao Wu, Jin Fan, Rui Zhang, Chengxi Zhou, Zebo The School of Electronic and Information Engineering Faculty of Engineering South China Normal University Guangdong Foshan528225 China The School of Physics South China Normal University Guangdong Guangzhou510000 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The School of Internet of Things Engineering Jiangnan University Wuxi214122 China The School of Aeronautics Astronautics University of Electronic Science and Technology of China and Aircraft swarm intelligent sensing and cooperative control Key Laboratory of Sichuan Province Chengdu610097 China The National Laboratory on Adaptive Optics Chengdu610209 China

In the era of 5G communication, removing interference sources that affect communication is a resource-intensive task. The rapid development of computer vision has enabled unmanned aerial vehicles to perform various high-altitude detection tasks. Because the field of object detection for antenna interference sources has not been fully explored, this industry lacks dedicated learning samples and detection models for this specific task. In this article, an antenna dataset is created to address important antenna interference source detection issues and serves as the basis for subsequent research. We introduce YOLO-Ant, a lightweight CNN and transformer hybrid detector specifically designed for antenna interference source detection. Specifically, we initially formulated a lightweight design for the network depth and width, ensuring that subsequent investigations were conducted within a lightweight framework. Then, we propose a DSLK-Block module based on depthwise separable convolution and large convolution kernels to enhance the network’s feature extraction ability, effectively improving small object detection. To address challenges such as complex backgrounds and large interclass differences in antenna detection, we construct DSLKVit-Block, a powerful feature extraction module that combines DSLK-Block and transformer structures. Considering both its lightweight design and accuracy, our method not only achieves optimal performance on the antenna dataset but also yields competitive results on public datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Antennas

Study on Mechanical Properties of Dual-Channel Cryogenic 3d Printing Scaffold for Mandibular Defect Repair

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Gao, Lilan Sun, Mengchao Liu, Jie Meng, Lulu Liu, Han Zheng, Xiongfei Liu, Hao Li, Ruixin Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300382 China Tianjin300382 China Beijing Friendship Hospital Capital Medical University 100050 China State Key Laboratory of Robotics Institutes for Robotics and Intelligent Manufacturing Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110017 China Tianjin Key Laboratory of Oral and Maxillofacial Function Reconstruction Tianjin Stomatological Hospital The Affiliated Stomatological Hospital of Nankai University Tianjin300041 China

Mandibular defect repair has always been a clinical challenge, facing technical bottleneck. The new materials directly affect technological breakthroughs in mandibular defect repair field. Our aim is to fabricate a scaffold for mandibular defect repairing with advanced biomaterials. Therefore, a novel dual-channel printed scaffold consisting of silk fibroin/collagen type I /hydroxyapatite (SCH) and polycaprolactone/hydroxyapatite (PCL/HA) was fabricated by 3D printing technology with double nozzles. The mechanical properties and behaviors of dual-channel printed scaffold were investigated by performing uniaxial compression, creep, stress relaxation and ratcheting experiments respectively. The experiments indicated the Young modulus of dual-channel printed scaffold was 60.1 kPa and dual-channel printed scaffold was typical nolinear viscoelastic consistent with bone tissue. Finite Element Analysis (FEA) was employed performing a numerical simulation to evaluate the implantation effect in mandible. The stress distribution of the contact area between scaffold and defect was uniform, the maximum Mises stress of cortical bone and cancellous bone in defect area were 54.52MPa and 3.196MPa, and the maximum displacement of cortical bone and cancellous bone in defect area were 0.1575mm and 0.1555mm, which were distributed in the incisor region. The peak value of the maximum Mises stress for the scaffold implanted was 3.128× MPa and the maximum displacement was 6.453×mm distributed near incisor area. The displacement distribution of the scaffold was consistent with that of cortical and cancellous bone. The scaffold recovered well when the force applied on it disappeared. Above all, dual-channel printed scaffold had excellent bio-mechanical properties in implanting mandible, which provides a new idea for the reconstruction of irregular bone defects in the mandible and has good clinical development prospects. © 2023, The Authors. All rights reserved.

关键词： 3D printing

Non-Singular Fixed-Time Robust Containment control for Autonomous Surface Vehicles

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Ma, Junda Sun, Hefang Tan, Chong Zhao, Tianyuan Liu, Ke College of Automation Harbin University of Science and Technology Harbin150000 China Provincial Key Laboratory of Complex Intelligent System and Integration Harbin150000 China College of Journalism and Communication Jilin University Changchun130000 China College of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin150000 China

For the containment control problem of autonomous surface vehicles with external disturbances, a novel non-singular fixed-time control scheme is developed, where the multi-ship system consists of real leaders and followers. In contrast with traditional containment cases studied in most of the existing literature, the real leaders are required to track the desired trajectories, and the followers need to get into the convex hull spanned by the real leaders in fixed time. The method for solving the fixed-time containment control problem is divided into the following steps: Firstly, a fixed-time disturbance observer is designed to estimate the external disturbance for the leaders and the followers, and the estimation result is used to compensate for the input of the control system;Second, combined with fixed-time stability theory and a switch function, a non-singular fixed-time trajectory tracking controller for leaders is designed, such that the position tracking error could be bounded within a fixed time;Third, to achieve formation efficiently, a non-singular fixed-time containment controller strategy incorporating with graph theory is proposed for coordinating followers, such that the fixed-time stability can be ensured. Finally, simulation examples are given to demonstrate the effectiveness of the proposed method. © 2023, The Authors. All rights reserved.

关键词： Graph theory

An Innovative Theory Method to Calculate 3d Breaking Characteristics of Hard - Thick Layers Supported by Elastic-Plastic Coal and Rock Mass for a Longwall Face

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Tai, Yang Shi, Bowen Yu, Bin Zhang, Chunwang State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing University Chongqing400030 China School of Resources and Safety Engineering Chongqing University Chongqing400030 China Shanxi Engineering Research Center for Coal Mine Intelligent Equipment Taiyuan University of Science and Technology Shanxi Taiyuan030024 China

Hard-thick key strata play a vital role in influencing rock mass behavior, particularly in relation to mining-induced stress and ground subsidence. Theoretical calculations serve as a valuable tool in elucidating their breaking characteristics. Traditional approaches such as Thin Plate Theory fall short by neglecting lateral shear deformations, rendering them inaccurate. Mid-Thick Plate Theory is another avenue some researchers explore, but it too comes with limitations, primarily its tendency to oversimplify boundary conditions and ignore key attributes like material plasticity and strain-softening behavior. In response to these challenges, the paper introduces a refined method aimed at calculating 3D fracturing characteristics in hard-thick layers, especially those supported by an elastic-plastic coal and rock mass. The methodology integrates traditional boundary conditions, like clamping and simple supports, but augments them with elastic-plastic supports. Subsequently, a comprehensive constitutive model is established that describes the full compression behavior of the elastic-plastic coal-rock mass, replete with equations for stiffness calculations. Leveraging the concepts of Mid-Thick Plate Theory, a specialized mechanical fracturing model is developed to suit the unique characteristics of hard-thick layers. Failure criteria are also formulated, alongside guidelines for crack propagation, with the assistance of equations to calculate principal and maximum shear stresses. Finite difference methods are employed to derive equations governing stress components, boundary conditions, and failure criteria. For empirical validation, the methodology is applied to real-world conditions observed in the 8202 Working Face of the Tashan Coal Mine. MATLAB is utilized to calculate the stresses of the K3 key layer, subsequently allowing for an assessment of the cause, pattern, and size of the first and periodic breaks. Additionally, when these findings are contrasted with the

关键词： Boundary conditions

DATA SMOOTHING FILLING METHOD BASED ON SCRNA-SEQ DATA ZERO-VALUE IDENTIFICATION

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Jiang, Linfeng Zhu, Yuan School of Automation China University of Geosciences Hongshan District No. 388 Lumo Road Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Hongshan District No. 388 Lumo Road Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Hongshan District No. 388 Lumo Road Wuhan430074 China

Single-cell RNA sequencing (scRNA-seq) determines RNA expression at single-cell resolution. It provides a powerful tool for studying immunity, regulation, and other life activities of cells. However, due to the limitations of the sequencing technique, the scRNA-seq data are represented with sparsity, which contains missing gene values, i.e., zero values, called dropout. Therefore, it is necessary to impute missing values before analyzing scRNA-seq data. However, existing imputation computation methods often only focus on the identification of technical zeros or imputing all zeros based on cell similarity. This study proposes a new method (SFAG) to reconstruct the gene expression relationship matrix by using graph regularization technology to preserve the high-dimensional manifold information of the data, and to mine the relationship between genes and cells in the data, and then uses a method of averaging the clustering results to fill in the identified technical zeros. Experimental results show that SFAG can help improve downstream analysis and reconstruct cell trajectory. © 2024, CC BY.

关键词： RNA

PyrAug: Gaussian Pyramid-based Multi-scale Data Augmentation for Panoptic Plant Segmentation with Ambiguous Boundary

学校读者我要写书评

暂无评论

PyrAug: Gaussian Pyramid-based Multi-scale Data Augmentation...

IEEE International Conference on Robotics and Biomimetics

作者： Yuhui Zou Zhihan Zhu Zhihao Xu Xuefeng Zhou Shixin Mao Hongmin Wu Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Key Laboratory of Modern Control Technology Guangzhou China College of Geological Engineering and Geomatics Chang'an University Xi'an China Biomimetic and Intelligent Robotics Lab (BIRL) Guangdong University of Technology Guangzhou China Jiutian Innovation (Guangdong) Intelligent Technology Co. Ltd Foshan Guangdong China

ISBN: (纸本)9781665481106

Most of the plants are usually roughly assigned categories in previous panoptic segmentation, which cannot meet the demand for autonomous mobile robotic sprayer sys-tems. Only a reasonable allocation of pesticide doses to different kinds of plants can keep them from being harmed by excessive chemicals. Due to the ambiguous boundaries and similar feature distributions between different plants, implementing precise plant segmentation is still a challenging task. To address this challenge, traditional data augmentation methods enhance the feature extraction capability of the model with geometric and color enhancements. However, these methods only augment the data at the image level such that the implicit scale information in the image is ignored. In this paper, we propose a Gaussian pyramid - based multi -scale data augmentation for panoptic segmentation of plants with ambiguous boundaries, named PyrAug. Our methods attempt to hierarchically enhance images at different levels, in which the network can effectively learn different feature distributions among plants and thus predict the respective masks. In addition to this, we present a new panoptic plant segmentation dataset for improving the seg-mentation performance in complex landscapes. In experimental verification, our method is added to the advanced panoptic segmentation network, and results show that our methods outperform the baselines with higher panoptic quality scores.

关键词： Image segmentation Image color analysis Fuses Feature extraction Data models Robustness Resource management

Networked-based fixed-time discontinuous safety control for DDW systems under stochastic cyber-attacks and intermittent DoS attacks

学校读者我要写书评

暂无评论

IEEE Transactions on Transportation Electrification 2025年

作者： Ding, Kui Zhu, Quanxin Huang, Tingwen Anhui Polytechnic University Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment Ministry of Education Wuhu241000 China Hunan Normal University MOE-LCSM CHP-LCOCS School of Mathematics and Statistics Changsha410081 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This study investigates the network-based fixed-time stabilization problem of the direct drive wheel (DDW) system of electric vehicles under stochastic cyber-attacks and intermittent denial of service (DoS) attacks via reliable discontinuous control strategy, which has important research significance for the application of the communication network security of the direct drive wheel system of electric vehicles. Firstly, aiming at the fact that the widths of control channels induced by stochastic cyber-attacks are inconsistent, a new controller based on quantization discontinuous delay control method is designed. Secondly, the actuator fault is also taken into account to conform to the actual operation of the direct drive wheel system of electric vehicles. Moreover, given the reliability of controllers in practical engineering, this work develops a new sufficient condition for easy implementation based on Lyapunov functional, and construct a new reliable discontinuous safety controller with stochastic cyber-attacks and intermittent DoS attacks to control the stability of the direct drive wheel system of electric vehicles in fixed time. Finally, the correctness and feasibility of the developed theoretical results are verified by experiments. © 2015 IEEE.

关键词： Stochastic control systems

Biomechanical Finite Element Methods Study of a Novel Internal Fixation System for Lumbar Spondylolysis

学校读者我要写书评

暂无评论

SSRN 2025年

作者： Li, Jingyuan Du, Chengfei Wang, Yulei Du, Di Liang, Jinlong Shao, Nengqi Feng, Fanzhe Xu, Wenhao Xu, Yongqing Cui, Yi Center for Joint Surgery Intelligent Manufacturing and Rehabilitation Engineering Center The First Affiliated Hospital of Army Medical University Chongqing400038 China Chongqing Municipal Science and Technology Bureau Key Laboratory of Precision Medicine in Joint Surgery Chongqing400038 China Chongqing Municipal Education Commission Key Laboratory of Joint Biology Chongqing400038 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of mechanical engineering Tianjin University of Technology Tianjin300384 China Department of Orthopaedic Surgery 920th Hospital of Joint Logistics Support Force Kunming650032 China Department of Orthopaedic Surgery 920th Hospital of Joint Logistics Support Force No. 212 of Da-Guan Road Xishan District Kunming650032 China

ObjectiveThis study aimed to verify the biomechanical efficacy of a novel internal fixation system for repairing lumbar spondylolysis (LS). Additionally, the changes in the mechanical performance of the novel internal fixation device during compression were *** healthy 25-year-old male volunteer was recruited for lumbar spine CT data acquisition to construct and validate a nonlinear finite element model of the L4-S1 spinal segment (A). Based on this, models were established for L5 spondylolysis (B), traditional internal fixation (C), and the pressurization process of the novel LS repair device fixation (D→E→F). For these six models, we constrained the lower surface of the S1 vertebral body while applying an axial compression force of 500 N and a moment load of 7.5 N·m on the upper surface of the L4 vertebral body to simulate six motions of the lumbar spine. The performance of each finite element model was evaluated by comparing the range of motion (ROM), maximum displacement, and maximum pressure experienced by the lumbar spine under different motion *** with Model C, Models D, E, and F exhibited a reduced ROM and maximum displacement (1%-38.5%, 12.8%-63.6%, and 32.8%-80.2%) compared with Model C during six different motions. Notably, compared with Model C, the novel internal fixation models consistently demonstrated a decreasing trend in the maximum stress on the intervertebral discs (IVD) and an increasing trend in the maximum stress on the articular cartilage and maximum stress and displacement of the bone graft. Moreover, the novel internal fixation model displayed larger ranges of evenly distributed stresses on the isthmus and reduced maximum stress on the internal fixation device across all six motions, with improved stiffness effects during the pressurization process of the novel internal fixation system (D→E→F).ConclusionsAccording to several mechanical comparisons, the novel internal fixation system had better biomechan

关键词： Axial compression

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image

学校读者我要写书评

暂无评论

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D ...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changlong Jiang Yang Xiao Cunlin Wu Mingyang Zhang Jinghong Zheng Zhiguo Cao Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Alibaba Group Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J- Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer.

关键词：