检索结果-内蒙古大学图书馆

6th International Conference on System Reliability and Safety engineering, SRSE 2024

作者： Wang, Hao Zhang, Han Qi, Jia China Institute of Marine Technology and Economy Quality and Reliability Center Beijing China Harbin University of Science and Technology School of Measurement-Control Technology and Communications Engineering Harbin China

ISBN: (纸本)9798350356083

This paper presents a vibration testing program designed to evaluate the reliability of PCB boards in complex underwater environments. The study thoroughly examines the structural components of the PCB and the vibrations it encounters throughout its lifecycle. Based on the characteristics of vibrations at different stages, corresponding testing standards and methods were developed, providing a scientific basis for the reliability assessment of PCB boards. © 2024 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

A Reliability Evaluation Method for Zero-Failure Products Based on Moment-Entropy Normalization 6

A Reliability Evaluation Method for Zero-Failure Products Ba...

引用

6th International Conference on System Reliability and Safety engineering, SRSE 2024

作者： Kong, Xiangrui Sun, Yongquan Tang, Qing An, Zijian Qi, Jia Guo, Kangkang Harbin University of Science and Technology School of Measurement-Control Technology and Communications Engineering Harbin China China Lnstitute of Marine Technology and Economy Quality and Reliability Center Beijing China

ISBN: (纸本)9798350356083

This paper addresses the challenge of reliability evaluation for small-sample and zero-failure data by introducing a method that integrates Bayesian theory with curve fitting. Initially, we employ the moment-entropy normalization method to determine the hyperparameters of the Beta distribution. This approach incorporates data from similar products, effectively overcoming the limitations posed by small sample sizes. Next, we use a Bayesian method to merge data from similar products with the current product data. By treating the likelihood function as binomial with zero failures, we accurately estimate parameters and improve the precision of reliability assessments. This enables us to obtain point estimates of failure probabilities at different time points and determine the upper confidence limits of failure probabilities at a given confidence level. Furthermore, we introduce the Weibull distribution as a life distribution model and apply curve fitting to estimate the Weibull parameters and their lower confidence limits, further enhancing the robustness of our reliability estimates. Finally, the proposed Bayesian method demonstrates strong practical applicability in case studies, providing valuable insights for the design and testing of reliable products. © 2024 IEEE.

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

A semantic and emotion-based dual latent variable generation model for a dialogue system

引用

CAAI Transactions on Intelligence technology 2023年第2期8卷 319-330页

作者： Ming Yan Xingrui Lou Chien Aun Chan Yan Wang Wei Jiang State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijingChina School of Information and Communications Engineering Communication University of ChinaBeijingChina Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of ChinaBeijingChina Department of Electrical and Electronic Engineering The University of MelbourneMelbourneVictoriaAustralia School of Data Science and Intelligent Media Communication University of ChinaBeijingChina

With the development of intelligent agents pursuing humanisation,artificial intelligence must consider emotion,the most basic spiritual need in human *** emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate ***,selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the *** propose a semantic and emotion-based dual latent variable generation model(Dual-LVG)for dialogue systems,which is able to generate appropriate emotional responses without an emotional *** from previous work,the conditional variational autoencoder(CVAE)adopts the standard transformer ***,Dual-LVG regularises the CVAE latent space by introducing a dual latent space of semantics and *** content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features ***,the average attention mechanism is adopted to better extract semantic features at the sequence level,and the semi-supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the *** results show that Dual-LVG can successfully achieve the effect of generating different content by controlling emotional factors.

关键词： conditional variational autoencoder dual latent space emotional responses latent variable generation

来源：评论

学校读者我要写书评

暂无评论

The Client-Level GAN-Based Data Reconstruction Attack and Defense in Clustered Federated Learning 18th

The Client-Level GAN-Based Data Reconstruction Attack and D...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Wu, Han Shi, Lei Ye, Junyu Fan, Yuqi Lv, Zengwei School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714634

Clustered Federated Learning (CFL) is an innovative architecture that effectively tackles the challenge of data heterogeneity in Federated Learning (FL). However, such a setup also introduces vulnerabilities that can be exploited by attackers to execute more severe attacks. This paper compares the efficacy of data reconstruction attacks utilizing Generative Adversarial Nets (GANs) in FL and CFL, respectively. It also proposes a general client-level data reconstruction attack scheme whose key is in that the attackers can eavesdrop the victim’s partial uploaded parameters. Experimental results demonstrate that the sample data generated in this kind of attack within the scenario of CFL exhibit a higher degree of similarity with the targeted data compared to FL. And it is observed that the attacks involving eavesdropping in CFL perform more effectively with a client-level attack accuracy. In addition, we design a lightweight and adaptive local differential privacy (LDP) mechanism to defend against this kind of attack. In this method, under the premise that the differential privacy budget decreases as the number of training round adds, each client dynamically adjusts the probability of adding differential privacy noise and the size of DP’s parameters according to the training accuracy and the resemblance to the reconstructed data generated by attackers. Our defense method can effectively alleviate the loss of training accuracy for each client caused by the accumulation of the differential privacy budget while ensuring the defense effect, and it also reduces clients’ computational burden. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Abnormal Detection and Poisoned Data Recovery in Clustered Federated Learning 18th

A Method for Abnormal Detection and Poisoned Data Recovery...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Chen, Yingying Shi, Lei Xu, Hao Ye, Junyu Xu, Juan School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714665

Clustered Federated Learning (CFL), as a type of Federated Learning (FL) paradigm, divides the clients into multiple clusters through the clustering process and trains them within the clusters, thus improving the overall model training accuracy. But the clustering process is also the weak link, which can lead to the failure of the whole model training if it is interfered or destroyed by the attacker. In this paper, we study the attack methods and defense strategies for attackers to implement data poisoning by tampering with client data, resulting in overall clustering failure. Our defense approach is designed to identify anomalous clients and recover their poisoned data. In order to resist the malicious behavior of attackers, we propose a dual-threshold pixel difference and watermark authentication defense method for detecting the presence of anomalous clients. The method can accurately identify the abnormal fluctuations in the data and effectively screen out the abnormal clients. Meanwhile, we propose a self-embedding watermarking defense algorithm based on shuffling idea for recovering poisoned data. Among them, our self-embedding watermarking algorithm not only accurately locates and recovers the tampered region of the image, but also improves the watermark security to prevent attackers from cracking it easily. Simulation results show that our proposed algorithm can accurately identify the abnormal client and recover the data. Even if the client’s data is massively tampered with, we can recover the tampered data images with high quality and ensure that the CFL clustering is not corrupted. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Design of Airborne VLF Dual Trailing Wire Antenna 6

Design of Airborne VLF Dual Trailing Wire Antenna

引用

6th International Conference on Electronics technology, ICET 2023

作者： Dong, Jianming Wu, Dan Communication Measurement and Control of Technology of Institute of Cetc China Beijing Key Laboratory of Millimeter-wave and Terahertz Wave Technology School of Integrated Circuits and Electronics China

ISBN: (纸本)9798350337693

The airborne Dual Trailing Wire Antenna (DTWA) has a complex shape that makes it challenging to calculate using the conventional analytical method and challenging to obtain results with high precision. The purpose of this thesis is to study the performance of the Dual Trailing Wire Antenna on the aircraft. The operation theory of the airborne DTWA is presented in this paper along with a method of establishing such large models of airborne Very Low Frequency (VLF) dual trailing wire antenna systems. The performance of the DTWA model is calculated, which is 6000 meters long. Then discuss dual trailing wire antenna's EM radiation characteristics and impedances by the analysis of simulation results. The electromagnetic field distribution and induced current of the Airborne Dual Trailing Wire Antenna are analyzed by calculating the radiation field of the DTWA. The conclusions are beneficial for further study on the application of airborne VLF communication systems. © 2023 IEEE.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

ICEEMDAN and LSTM Spindle System Fault Diagnosis Method

ICEEMDAN and LSTM Spindle System Fault Diagnosis Method

引用

UNIfied Conference of International Workshop on Defence Applications of Multi-Agent Systems, DAMAS 2023, International Conference on Maintenance engineering, IncoME-V 2023, International conference on the Efficiency and Performance engineering Network, TEPEN 2023

作者： Wang, Nan Wang, Hongjun Zhang, Zhuangzhuang Chen, Baisheng School of Mechanic and Electric Engineering BISTU Beijing100192 China Key Laboratory of Modern Measurement and Control Technology BISTU Beijing100192 China

ISBN: (纸本)9783031494123

Research on fault diagnosis of rotating machinery is crucial as it serves as a core component. In order to diagnose spindle system fault types quickly and accurately, Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Long Short-Term Memory (LSTM) fault diagnosis method is presented. Firstly, collect the fault vibration, then ICEEMDAN is used for vibration signals to extract seven times domain features and four frequency domain features. Finally, the time domain and frequency domain features’ parameters are input into the LSTM network for fault classification. The method is verified for the practical industrial CNC machine center spindle system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Data Collection over Underwater MI-Assisted Acoustic Cooperative MIMO WSNs

引用

China communications 2023年第11期20卷 96-110页

作者： Qingyan Ren Yanjing Sun Song Li Bin Wang Zhengda Yu School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China Department of Information Technology and Electrical Engineering ETH ZurichZurich 8092Switzerland School of Communication and Information Engineering Xi’an University of Science and TechnologyXi’an 710054China Xuzhou Engineering Research Center of Intelligent Industry Safety and Emergency Collaboration Xuzhou 221000China

Underwater magnetic induction(MI)-assisted acoustic cooperative multiple-input-multipleoutput(MIMO) has been recently proposed as a promising technique for underwater wireless sensor networks(UWSNs).For the more,the energy utilization of energy-constrained sensor nodes is one of the key issues in UWSNs,and it relates to the network *** this paper,we present an energy-efficient data collection for underwater MI-assisted acoustic cooperative MIMO wireless sensor networks(WSNs),including the formation of cooperative MIMO and relay link ***,the cooperative MIMO is formed by considering its expected transmission range and the energy balance of nodes with ***,from the perspective of the node’s energy consumption,the expected cooperative MIMO size and the selection of master node(MN) are ***,to improve the coverage of the networks and prolong the network lifetime,relay links are established by relay selection algorithm that using matching ***,the simulation results show that the proposed data collection improves its efficiency,reduces the energy consumption of the master node,improves the networks’ coverage,and extends the network lifetime.

关键词： cooperative MIMO cooperative MIMO size data collection heterogeneous UWSNs relay link establishment

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Rolling Bearings under Different Working Conditions Based on Federated Feature Transfer Learning 3

Fault Diagnosis Method of Rolling Bearings under Different W...

引用

3rd International Conference on Sensing, measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022

作者： Kang, Shouqiang Yang, Jiawei Sun, Yulin Wang, Yujing Wang, Qingyan Mikulovich, V.I. School of Measurement-Control and Communication Engineering Harbin University of Science and Technology Harbin China Belarusian State University Minsk Belarus

ISBN: (纸本)9781665492812

A rolling bearing fault diagnosis method based on the federated feature transfer learning is proposed for the low accuracy of the diagnosis model in the presence of large differences in data distribution under different working conditions, difficulty in obtaining labeled data and non-sharing of data among different users. This method performs wavelet transformation on the time domain vibration data of rolling bearings to obtain a time-frequency diagram. The priori labeled public data and the multi-user island private data are regarded as the source domain and the target domain. The multi-representation feature extraction structure is introduced to improve the original residual network. Based on an improved residual network and multi-representation features in the source domain and the target domain, every local model and a federated global model are constructed. Through verification of bearing data, the proposed method can establish an effective fault diagnosis model with high fault diagnosis accuracy. It can integrate the knowledge of isolated island data without sharing data among multiple users. © 2022 IEEE.

关键词： Different working conditions domain adaptation fault diagnosis feature transfer learning federated learning

来源：评论

学校读者我要写书评

暂无评论

Observation and research of deep underground multi-physical fields—Huainan–848 m deep experiment

引用

Science China Earth Sciences 2023年第1期66卷 54-70页

作者： Yun WANG Yaxin YANG Heping SUN Chengliang XIE Qisheng ZHANG Xiaoming CUI Chang CHEN Yongsheng HE Qiangqiang MIAO Chaomin MU Lianghui GUO Jiwen TENG School of Geophysics and Information Technology China University of GeosciencesBeijing 100083China School of Geophysics and Measurement-control Technology East China University of TechnologyNanchang 330013China Innovation Academy for Precision Measurement Science and Technology Chinese Academy of SciencesWuhan 430077China Institution of Engineering Protection IDEAMSPLALuoyang 471023China State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines Anhui University of Science and TechnologyHuainan 232001China Institute of Geochemistry Chinese Academy of SciencesGuiyang 550081China

Compared with the surface,the deep environment has the advantages of allowing“super-quiet and ultra-clean”-geophysical field observation with low vibration noise and little electromagnetic interference,which are conducive to the realization of long-term and high-precision observation of multi-physical fields,thus enabling the solution of a series of geoscience *** the Panyidong Coal Mine,where there are extensive underground tunnels at the depth of 848 m below sea level,we carried out the first deep-underground geophysical observations,including radioactivity,gravity,magnetic,magnetotelluric,background vibration and six-component seismic *** concluded from these measurements that(1)the background of deep subsurface gravity noise in the long-period frequency band less than 2 Hz is nearly two orders of magnitude weaker than that in the surface observation environment;(2)the underground electric field is obviously weaker than the surface electric field,and the relatively high frequency of the underground field,greater than 1 Hz,is more than two orders of magnitude weaker than that of the surface electric field;the east-west magnetic field underground is approximately the same as that at the surface;the relatively high-frequency north-south magnetic field underground,below 10 Hz,is at least one order of magnitude lower than that at the surface,showing that the underground has a clean electromagnetic environment;(3)in addition to the highfrequency and single-frequency noises introduced by underground human activities,the deep underground space has a significantly lower background vibration noise than the surface,which is very beneficial to the detection of weak earthquake and gravity signals;and(4)the underground roadway support system built with ferromagnetic material interferes the geomagnetic *** also found that for deep observation in the“ultra-quiet and ultra-clean”environment,the existing geophysical equipment and observation technology hav

关键词： Multi-physical fields Radioactivity Gravity Geomagnetic Electromagnetic Earthquake Observations deep underground

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：