检索结果-内蒙古大学图书馆

intelligent Communication, Sensing and Electromagnetics (ICSE), International Conference on

作者： Heng Du Huaiming Cang Yiwen Bai Xinyi Wang Beijing Elephant Technology Co. Ltd Beijing China School of Transportation Science and Engineering Beihang University Beijing China The State Key Lab of Intelligent Transportation System Beijing China Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin China

ISBN: (数字)9798350354935

ISBN: (纸本)9798350354942

In the field of railway transportation, with the continuous improvement of train running speed and the continuous increase of operating mileage, it becomes particularly important to ensure the safety and integrity of small-target infrastructure along the railway train. Although many small-target detection methods have been proposed, the research on small-target infrastructure detection along rail trains is very rare. To solve this problem, this paper proposes a small-target infrastructure detection network with spatial tracking and multi-level feature extraction based on Yolov8n. The experimental results show that ST-YOLO has a 3.6% mAP improvement on the OSDaR23 dataset compared to the baseline Yolov8n, and shows significant advantages over other state-of-the-art methods.

关键词： Rails Transportation Railway safety Switches Feature extraction Rail transportation Real-time systems Sensors Safety Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Automatic Method for Brain Tumors Segmentation Based on Deep Convolutional Neural Network

An Automatic Method for Brain Tumors Segmentation Based on D...

引用

2021 IEEE International Conference on Medical Imaging Physics and Engineering, ICMIPE 2021

作者： Lin, Hui Zhang, Benjian Guo, Xin Guo, Dong Jing, Jia Huiyuan, Luo Yumeng, Zhao Hu, Min Ren, Fuji School of Physics Hefei University of Technology Hefei China School of Computer and Information Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei China School of Computer and Information Hefei University of Technology Hefei China Graduate School of Advanced Technology and Science University of Tokushima Tokushima Japan

ISBN: (纸本)9781665426084

[Purpose] Accurate outline of tumor targets is critical to a high quality radiotherapy plan. Manual segmentation is of great workload and has a strong artificial subjectivity. Using deep learning method to assist automatically segmenting of tumor target is the penetration and application of artificial intelligence in medicine. [Methods] A 6-layer model of deep Convolution Neural Network (CNN) has been constructed by taking advantage of different types of layers for brain tumor segmentation. This model is a 6 layer CNN model (6-CNN) composed of three convolution layers, two pool layers and one full connection layer. To obtain enough samples for 6-CNN model training, a patch-based technology has been adopted. That is to successively extract a local area from the whole image as a patch. And the center pixel value is taken as the pixel value of the whole patch. Similarly, the label of the center pixel is also taken as the label of the whole patch. Thus the 6-CNN model transforms the brain tumor image segmentation into patch classification based on the excellent classification characteristics of deep convolution neural network. The model combines the local features of patch, the information extracted from shallow network and the global features to predict the category label of the central pixel of patch. [Results] The model is validated on BRATS 2015 dataset and results show that the segmentation accuracy can be up to Dice Similarity Coefficient (DSC) 90\%\pm 4\%. [Conclusions] An automatic deep CNN segmentation model for brain tumors has been constructed based on MRI image patches, which is expected to assist or even substitute the manual segmentation of brain tumors. © 2021 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

New β-type Ti-Zr-V-Nb alloys used for laser-based direct energy deposition: design, microstructure, and properties

引用

Materials Characterization 2022年 189卷

作者： Zhao, Zisong Wang, Cunshan Yu, Qun Song, Lijun Yang, Guang Zhang, Jingtao Key Laboratory of Materials Modification by Laser Ion and Electron Beams Dalian University of Technology Liaoning Dalian116024 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan Provincial Key Laboratory of Intelligent Laser Manufacturing Hunan University Changsha410082 China School of Mechatronics Engineering Shenyang Aerospace University Liaoning Shenyang110136 China

To develop new titanium alloys for laser-based direct energy deposition, Ti-Zr-V-Nb alloys were designed from a basic Ti60.94Zr39.06 congruent composition alloyed with constant V content and varying Nb contents. The microstructure and properties of the alloys, fabricated by laser-based direct energy deposition, were systematically studied. The results show that all as-deposited alloys consist of near-equiaxed β grains with multiple orientations. The difference is that the lattice parameter of the phase enlarges and its grain size reduces with increasing Nb content, which leads to a continuous increase in hardness, strength, wear and corrosion resistance. But the ductility shows a reverse variation due to the combination of enhanced solid solution strengthening and dislocation strengthening. Owing to the combined effect of fluidity and spreadability of melt, the surface roughness firstly decreases and then increases with the increase of Nb content. The optimized alloy with 3.91 at.% Nb exhibits a good match of mechanical, tribological, and chemical properties compared with Ti60.94Zr39.06 congruent alloy, being a promising candidate used for laser-based direct energy deposition. © 2022 Elsevier Inc.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

YTCNet: A Real-time Algorithm for Parcel Damage Detection with Rich Features and Attention

YTCNet: A Real-time Algorithm for Parcel Damage Detection wi...

引用

International Conference on Computer Supported Cooperative Work in design

作者： Zhi Chen Cuifeng Du Yuyu Zhou Haoxuan Guan Xiujie Huang Zhefu Li Changjiang Liu Xiaotian Zhuang Xingyu Zhu Quanlong Guan Jinan University Guangzhou China Guangdong-Macao Advanced Intelligent Computing Joint Laboratory China Cetc Potevio Science & Technology Co. Ltd Guangzhou China Guangdong Key Laboratory of Data Security and Privacy Preserving China Guangdong Testing Institute of Product Quality Supervision China Beijing JD Zhenshi Information Technology Co. Ltd Beijing China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In this study, we tackle the challenge of parcel damage detection and present YTCNet to improve both accuracy and real-time performance. We enhance the Yolov5 algorithm by integrating C3TR modules into the architecture to capture more comprehensive feature information. Furthermore, we introduce the CBAM attention module to focus on critical areas in parcel images, enhancing the model’s feature extraction capabilities. By effectively combining C3TR and CBAM modules, we successfully developed an efficient parcel damage detection algorithm. Our experimental results demonstrate the superior performance of YTCNet in accuracy and real-time processing compared to various object detection models across multiple parcel damage scenarios. Our research significantly contributes to the logistics supply chain industry by aligning with IoT development. It enables practical applications to more effectively identify parcel damage, thereby enhancing customer satisfaction.

关键词： YOLO Industries Accuracy Supply chains Transportation Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

ASM: Adaptive Sample Mining for In-The-Wild Facial Expression Recognition

arXiv

引用

arXiv 2023年

作者： Zhang, Ziyang Sun, Xiao An, Liuwei Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Heifei China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machines Hefei University of Technology Heifei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Heifei China

Given the similarity between facial expression categories, the presence of compound facial expressions, and the subjectivity of annotators, facial expression recognition (FER) datasets often suffer from ambiguity and noisy labels. Ambiguous expressions are challenging to differentiate from expressions with noisy labels, which hurt the robustness of FER models. Furthermore, the difficulty of recognition varies across different expression categories, rendering a uniform approach unfair for all expressions. In this paper, we introduce a novel approach called Adaptive Sample Mining (ASM) to dynamically address ambiguity and noise within each expression category. First, the Adaptive Threshold Learning module generates two thresholds, namely the clean and noisy thresholds, for each category. These thresholds are based on the mean class probabilities at each training epoch. Next, the Sample Mining module partitions the dataset into three subsets: clean, ambiguity, and noise, by comparing the sample confidence with the clean and noisy thresholds. Finally, the Tri-Regularization module employs a mutual learning strategy for the ambiguity subset to enhance discrimination ability, and an unsupervised learning strategy for the noise subset to mitigate the impact of noisy labels. Extensive experiments prove that our method can effectively mine both ambiguity and noise, and outperform SOTA methods on both synthetic noisy and original datasets. The supplement material is available at https://***/zzzzzzyang/ASM. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Numerical Trajectory Planning of Panel Installation with Optimal Energy Consumption for Redundant Articulating Crane

SSRN

引用

SSRN 2024年

作者： Li, Penghao Zhang, Bangji Zhang, Zheshuo Hu, Wen Zhang, Jie Dai, Di State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Intelligent Transportation System Research Center Hangzhou City University Hangzhou China School of Vehicle and Mobility Tsinghua University Beijing China College of Automotive and Mechanical Engineering Changsha University of Science and Technology Changsha China

The automatic installation of panels has become crucial in numerous industries scenarios. This paper proposed a trajectory planning method to addresses the position and posture adjustment of panel installation using redundant articulating cranes. Configuration space of the crane and rotation matrix are combined to investigate the strong coupling of the panel's position and posture. Moreover, the study combines the motion modes of the crane with the sequential analysis of redundant motion to assess energy consumption, incorporating energy efficiency as one of the planning objectives. Simultaneously, an intrinsic connection between the motion sequences within the C-space and safety considerations is analyzed. The installation experiment is performed with a real crane. The experimental results indicate that the proposed method achieves the function of installation of panels, which can make both the panel’s position and posture safely reach the predetermined state with less energy consume. © 2024, The Authors. All rights reserved.

关键词： Cranes

来源：评论

学校读者我要写书评

暂无评论

Autonomous On-ramp Merge Strategy Using Deep Reinforcement Learning in Uncertain Highway Environment

Autonomous On-ramp Merge Strategy Using Deep Reinforcement L...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Wu, Sifan Tian, Daxin Zhou, Jianshan Duan, Xuting Sheng, Zhengguo Zhao, Dezong Beijing Key Laboratory For Cooperative Vehicle Infrastructure Systems&Safety Cooperative Control Beijing China Beijing Advanced Innovation Center For Big Data and Brain Computing Beijing China Department of Engineering and Design Richmond United Kingdom University of Sussex Richmond United Kingdom James Watt School of Engineering Glasgow United Kingdom University of Glasgow Glasgow United Kingdom

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

On-ramp merge is a complex traffic scenario in autonomous driving. Because of the uncertainty of the driving environment, most rule-based models cannot solve such a problem. In this study, we design a Deep Reinforcement Learning (DRL) method to solve the issue of ramp merges in uncertain scenarios and modify the structure of the Twin Delayed Deep Deterministic policy gradient algorithm (TD3), using Long Short-Term Memory (LSTM) to select an action based on temporal information. The proposed method is applied in the on-ramp merge and verified in the Simulation of Urban Mobility (SUMO). Results show that the proposed method performs significantly better generalization in uncertain traffic scenarios. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

design of an Embedded Leg Capsule Robot

Design of an Embedded Leg Capsule Robot

引用

IEEE International Conference on Mechatronics and Automation

作者： Yihui Wang Tao Xue Jing Wang Yimuranjiang Yueliwasi Tianjin Key Laboratory for Advanced Electromechanical System Design and Intelligent Control Tianjin University of Technology 391 Binshui Xidao Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology 391 Binshui Xidao Tianjin China

The capsule robot enters the patient’s intestinal system directly by swallowing and takes continuous images using the miniature camera unit it carries, but during its travel, its own gravity and the peristaltic movement of the intestine make the physician limited in obtaining images of the intestine and making a diagnosis. In order to solve this problem, a capsule endoscope with an embedded leg mechanism is proposed. Compared to commercially available capsule robot. This capsule robot can easily move through the intestine autonomously by means of the relationship between the leg, the screw nut and the linkage, enabling forward, backward and stationary functions. The capsule robot has a diameter of 14 mm, a length of 30 mm and a maximum diameter of 26.66 mm with the legs spread out. The hollow space is allocated to include basic endoscopic components such as a miniature camera and a rotating motor. A series of tests, including in vitro tests, were carried out to test the feasibility of the leg mechanism of this capsule robot. Based on the results of the experiments, the proposed leg mechanism can effectively act on the Micro-capsule endoscope, and is able to move effectively through the intestine.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Computer Network Technology System Based on Artificial Intelligence Technology 7

Research on Computer Network Technology System Based on Arti...

引用

2020 7th International Conference on Computer-Aided design, Manufacturing, Modeling and Simulation, CDMMS 2020

作者： Yao, Jinling Liu, Jie College of Electronic Information and Engineering Tianjin Vocational Institute Tianjin300000 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin300384 China

This article introduces computer network intrusion detection systems and their classification based on artificial intelligence technology, and points out the challenges that intrusion detection systems (IDS) are facing in wireless sensor computer networks. On this basis, a hierarchical multi-layer wireless sensor network intrusion detection system and technology based on artificial intelligence technology Agent is proposed, and its network structure, working principle and performance are analysed. © Published under licence by IOP Publishing Ltd.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Elucidating the Rate Limitation of Lithium-Ion Batteries Under Different Charging Conditions Through Polarization Analysis

SSRN

引用

SSRN 2023年

作者： Xie, Wenlong Guo, Peng Gao, Xinlei Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China Dyson School of Design Engineering Imperial College London London United Kingdom

The charging performance of lithium-ion batteries is significantly affected by the polarization effect, which leads to increased resistance and prolonged charging time. this paper combines experimental testing with numerical simulation to qualitatively and quantitatively investigate the polarization effects under different charging conditions. The results indicate that the proportions of positive and negative polarization to cell polarization are comparable and basically constant with variations in the charging rate. The polarization voltages of different categories within the electrode are positively correlated with the charging rate. At high charging rates, electrochemical polarization accounts for the majority, followed by solid-phase and liquid-phase concentration polarization, while solid-phase and liquid-phase ohmic polarization is relatively negligible. On the other hand, the cell polarization exhibits a non-linear trend with temperature. The lower the temperature, the greater the proportion of negative polarization, while positive polarization is insensitive to temperature. At low temperature charging, the solid-phase concentration polarization of the negative electrode accounts for the majority of electrode polarization, which can be attributed to the larger lithium ion concentration gradient induced by the sluggish diffusion of ions in the active material. In-depth investigation of the polarization effect will provide guidance for achieving more efficient charging under different operating conditions. © 2023, The Authors. All rights reserved.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：