检索结果-内蒙古大学图书馆

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

作者： Liu, Lei Zhao, Wei Jiang, Zeyong Wang, Shihai Beijing Electro Mechanical Engineering Institute Beijing100074 China School of Reliability and Systems Engineering Beihang University Beijing100191 China Science and Technology on Reliability and Environment Engineering Laboratory Beihang University Beijing100191 China

Although integrated modular avionics (IMA) provides many advantages such as the reduced weight and higher efficiency for system operations, safety problems in IMA dynamic reconfiguration process come up due to its complexity to analyze. Architecture Analysis and Design Language (AADL) has advantage to model for embedded systems. However, it is quite limited to employ AADL for analyzing system safety. This paper, seeks to translate the AADL models of IMA dynamic reconfiguration process into colored petri net (CPN), which have advantages to simulate and evaluate embedded systems. Then, the colored petri net (CPN) is proposed for the analysis for AADL models, because CPN can describe the properties and behaviors of dynamic reconfiguration process well. Moreover, it is essential to make a transformation from the AADL models to the CPN models. This work will benefit the subsequent analysis of IMA dynamic reconfiguration process. Finally, a case study is provided for effectiveness the transformation rules. © 2020 Journal of Physics: Conference Series.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Head Feature Pyramid Networks for Breast Mass Detection

Multi-Head Feature Pyramid Networks for Breast Mass Detectio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hexiang Zhang Zhenghua Xu Dan Yao Shuo Zhang Junyang Chen Thomas Lukasiewicz State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China College of Computer Science and Software Engineering and Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University Shenzhen China Institute of Logic and Computation TU Wien Vienna Austria Department of Computer Science University of Oxford Oxford United Kingdom

Analysis of X-ray images is one of the main tools to diagnose breast cancer. The ability to quickly and accurately detect the location of masses from the huge amount of image data is the key to reducing the morbidity and mortality of breast cancer. Currently, the main factor limiting the accuracy of breast mass detection is the unequal focus on the mass boxes, leading the network to focus too much on larger masses at the expense of smaller ones. In the paper, we propose the multi-head feature pyramid module (MHFPN) to solve the problem of unbalanced focus of target boxes during feature map fusion and design a multi-head breast mass detection network (MBMDnet). Experimental studies show that, comparing to the SOTA detection baselines, our method improves by 6.58% (in AP@50) and 5.4% (in TPR@50) on the commonly used IN-breast dataset, while about 6-8% improvements (in AP@20) are also observed on the public MIAS and BCS-DBT datasets.

关键词： Limiting Feature extraction Breast cancer Acoustics Speech processing X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation

MPS-AMS: Masked Patches Selection and Adaptive Masking Strat...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiangtao Wang Ruizhi Wang Biao Tian Jiaojiao Zhang Shuo Zhang Junyang Chen Thomas Lukasiewicz Zhenghua Xu State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China College of Computer Science and Software Engineering and Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University Shenzhen China Institute of Logic and Computation TU Wien Vienna Austria Department of Computer Science University of Oxford Oxford United Kingdom

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their applications in medical images are relatively lacking. Besides, their fixed high masking strategy limits the upper bound of conditional mutual information, and the gradient noise is considerable, making less the learned representation information. Motivated by these limitations, in this paper, we propose masked patches selection and adaptive masking strategy based self-supervised medical image segmentation method, named MPS-AMS. We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further. Extensive experiments on three public medical image segmentation datasets (BUSI, Hecktor, and Brats2018) show that our proposed method greatly outperforms the state-of-the-art self-supervised baselines.

关键词： Image segmentation Upper bound Image analysis Self-supervised learning Signal processing Lesions Task analysis

来源：评论

学校读者我要写书评

暂无评论

UBMF: Uncertainty-aware bayesian meta-learning framework for fault diagnosis with imbalanced industrial data

引用

Knowledge-Based Systems 2025年 323卷

作者： Lian, Zhixuan Li, Shangyu Huang, Qixuan Huang, Zijian Liu, Haifei Qiu, Jianan Yang, Puyu Tao, Laifa Hangzhou International Innovation Institute Beihang University China Institute of Reliability Engineering Beihang University Beijing China Science & Technology on Reliability & Environmental Engineering Laboratory Beijing China School of Reliability and Systems Engineering Beihang University Beijing China

Fault diagnosis of mechanical equipment involves data collection, feature extraction, and pattern recognition but is often hindered by the imbalanced nature of industrial data, introducing significant uncertainty and reducing diagnostic reliability. To address these challenges, this study proposes the Uncertainty-Aware Bayesian Meta-Learning Framework (UBMF), which integrates four key modules: data perturbation injection for enhancing feature robustness, cross-task self-supervised feature extraction for improving transferability, uncertainty-based sample filtering for robust out-of-domain generalization, and Bayesian meta-knowledge integration for fine-grained classification. Experimental results on ten open-source datasets under various imbalanced conditions, including cross-task, small-sample, and unseen-sample scenarios, demonstrate the superiority of UBMF, achieving an average improvement of 42.22 % across ten Any-way 1–5-shot diagnostic *** integrated framework effectively enhances diagnostic accuracy, generalization, and adaptability, providing a reliable solution for complex industrial fault diagnosis where imbalanced data and dynamic operating conditions severely challenge traditional methods, such as highstakes industries such as wind turbine monitoring, aerospace systems, and automated manufacturing © 2025 Elsevier B.V.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A modeling method for integrated modular avionics dynamic reconfiguration process based on AADL 6

A modeling method for integrated modular avionics dynamic re...

引用

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

With the great development of integrated modular avionics (IMA), the dynamic reconfiguration of IMA not only provides great advantages in resource utilization and aircraft configuration but also acts as a valid means for resource failure management. It is very vital to ensure the correction of the IMA dynamic reconfiguration process. The analysis of the dynamic reconfiguration process is a significant task. The Architecture Analysis & Design Language (AADL) is widely used in complicated real-time embedded systems. The language can describe the system configuration and the execution behaviors, such as configuration changes. Petri net is a widely used tool to conduct simulation analysis in many aspects. Therefore, we proposed a modeling method of IMA dynamic reconfiguration based on AADL mode, behavioral annex and error model annex in the system level. The model is our first step to analyze and solve the safety problem of IMA system. It can benefit deep analyzing about dynamic reconfiguration of IMA system as the foundation. © 2020 Journal of Physics: Conference Series.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

C2M-DoT: Cross-modal consistent multi-view medical report generation with domain transfer network

arXiv

引用

arXiv 2023年

作者： Wang, Ruizhi Wang, Xiangtao Zhou, Jie Lukasiewicz, Thomas Xu, Zhenghua State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China Shenzhen University Shenzhen China Institute of Logic and Computation Vienna University of Technology Vienna Austria Department of Computer Science University of Oxford Oxford United Kingdom

In clinical scenarios, multiple medical images with different views are usually generated simultaneously, and these images have high semantic consistency. However, most existing medical report generation methods only consider single-view data. The rich multiview mutual information of medical images can help generate more accurate reports, however, the dependence of multi-view models on multi-view data in the inference stage severely limits their application in clinical practice. In addition, word-level optimization based on numbers ignores the semantics of reports and medical images, and the generated reports often cannot achieve good performance. Therefore, we propose a cross-modal consistent multi-view medical report generation with a domain transfer network (C2M-DoT). Specifically, (i) a semantic-based multi-view contrastive learning medical report generation framework is adopted to utilize cross-view information to learn the semantic representation of lesions;(ii) a domain transfer network is further proposed to ensure that the multi-view report generation model can still achieve good inference performance under single-view input;(iii) meanwhile, optimization using a cross-modal consistency loss facilitates the generation of textual reports that are semantically consistent with medical images. Extensive experimental studies on two public benchmark datasets demonstrate that C2M-DoT substantially outperforms state-of-the-art baselines in all metrics. Ablation studies also confirmed the validity and necessity of each component in C2M-DoT. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Study on a 48-Slot Interior Permanent Magnet Synchronous Motor in the Aircraft Drive System

Study on a 48-Slot Interior Permanent Magnet Synchronous Mot...

引用

Power and Electrical technology Conference (APET), Asia

作者： Yuhang Xie Fei Xiong Rui Yan Yu Xiang Kai Yang Weican Yan School of Reliability and Systems Engineering Beijing University of Aeronautics and Astronautics Beijing China State Key Laboratory of Advanced Electromagnetic Technology Huazhong University of Science and Technology Wuhan China Marketing Department SG Micro Corp Beijing China Wolong Electric Group Co. LTD Shangyu China

The torque performance of the interior permanent magnet synchronous motor (IPMSM) has been widely concerned and studied for many years. This article focuses on the structure design and optimization of the IPMSM in the aircraft drive system, and aiming to improve the torque density and reduce the torque ripple. Firstly, the original structure of the IPMSM is given. And then, a fractional slot winding and ∇-type rotor magnetic pole topology are proposed as the optimized IPMSM structure in this article. In addition, the comparison of the original and optimized structure is studied by the simulation. Finally, the performance of an optimized prototype is analyzed by experimental test, and the validity of the design optimization method for proposed IPMSM structure is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PCA: Semi-Supervised Segmentation with Patch Confidence Adversarial Training

引用

IEEE Transactions on Network science and engineering 2025年

作者： Xu, Zhenghua Yang, Runhe Xu, Zihang Zhang, Shuo Yang, Yuchen Liu, Weipeng Xu, Weichao Chen, Junyang Lukasiewicz, Thomas Leung, Victor C. M. Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Tianjin China The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong The Johns Hopkins University Department of Applied Mathematics and Statistic Baltimore United States Hebei University of Technology School of Artificial Intelligence Tianjin China Hebei Provincial Hospital of Traditional Chinese Medicine Digestive Disease Center Shijiazhuang China Shenzhen University College of Computer Science and Software Engineering Shenzhen China University of Oxford Department of Computer Science University of Oxford United Kingdom Department of Computer Science United Kingdom Vienna University of Technology institute of Logic and Computation nstitute of Logic and Computation Vienna Austria

Deep-learning-based semi-supervised learning (SSL) methods have achieved a strong performance in medical image segmentation, which can alleviate doctors' expensive annotation by utilizing a large amount of unlabeled data. Unlike most existing semi-supervised learning methods, adversarial training methods distinguish samples from different sources by learning the data distribution of the segmentation map, leading the segmenter to generate more accurate predictions. We argue that the current performance restrictions for such approaches are the problems of feature extraction and learning preferences. In this paper, we propose a new semi-supervised adversarial method called Patch Confidence Adversarial Training (PCA) for medical image segmentation. The PCA method's discriminator penalizes patch-level structures, guiding the generator to optimize different patch areas, by leveraging pixel context, the generator is driven to focus on high-frequency features, making it harder to deceive the discriminator and easy to converge to an ideal state, which more effectively guides the segmenter to generate high-quality pseudo-labels. Furthermore, at the discriminator's input, we supplement image information constraints, making it simpler to fit the expected data distribution. Extensive experiments on the Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset and the Brain Tumor Segmentation (BraTS) 2019 challenge dataset show that our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation. © 2025 IEEE. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fracture retro estimation of friction plate made of 30CrMnSiA in laboratory condition

Fracture retro estimation of friction plate made of 30CrMnSi...

引用

2020 International Conference on Advanced Materials and Intelligent Manufacturing and Advanced Steel for Automotive Seminar, ICAMIM 2020

作者： Hu, Zheng Gao, Xingyu Zhang, Wanhao Zhang, Weifang Liu, Xuerong China North Vehicle Research Institute Science and Technology on Vehicle Transmission Laboratory Beijing China Beihang University School of Reliability and Systems Engineering Beijing China China North Vehicle Research Institute Science and Technology on Vehicle Transmission Laboratory Beijing China Beihang University School of Reliability and Systems Engineering Beijing China Beihang University School of Reliability and Systems Engineering Beijing China

Fatigue life and fatigue stress range of the friction plate which is made of 30CrMnSiA were studied under laboratory environment. By using Scanning Electron Microscopy (SEM) to observe the fracture striation, the width of the fatigue striation can be obtained. Fatigue life and fatigue stress range can be studied with the combination of Paris law and fatigue striation width. The method is simple and mature, and the relative error of estimation is within expected values. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Fatigue of materials

来源：评论

学校读者我要写书评

暂无评论

Effect of U-Bending Deformation on Pitting Corrosion of 2205 Duplex Stainless Steel Under Wet-Dry Cycling of Chloride Salt Droplets

SSRN

引用

SSRN 2022年

作者： Cheng, Cong-Qian Zhao, Xiao-Yan Zhang, Dong-Jiu Zhao, Yi-Ning Cao, Tie-Shan Zhong, Sheng Zhang, Lei Zhao, Jie School of Materials Science and Engineering Dalian University of Technology Dalian116024 China Key Laboratory of Aerospace Launch Site Reliability Xichang Satellite Launch Center Hainan Haikou571126 China

The pitting corrosion of 2205 duplex stainless steel after U-bending deformation was investigated under wet-dry cycling of droplets. At the tensile side, the average critical relative humidity for pitting (RHpit) was increased from 44.5% to 55.6%, the critical relative humidity (RHrep) for repassivation was correspondingly increased from 60.2% to 76.6%. The compressive strain increased the critical relative humidity to 52.9% (RHpit) and 73.3% (RHrep), respectively. Compared to the hemispherical pits without deformation, selective dissolution of the ferrite phase with irregular pits appeared on the tensile side. The decrease in pitting resistance and the formation of irregular pit morphology were discussed. © 2022, The Authors. All rights reserved.

关键词： Pitting

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：