检索结果-内蒙古大学图书馆

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Ji, Haojie Wang, Jingyan Wang, Liyong Chen, Yupeng He, Peng Jin, Long Fang, Junzhe State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology Univ. Beijing China China Automotive Engineering Research Institute Co. Ltd. Chongqing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

With the increasing information interaction in intelligent and connected vehicles (ICVs), there are more and more security vulnerabilities in the exploitable data. These vulnerabilities may cause personal privacy leaks, property damage, etc. This paper analyzes the data security risks in the four basic functional areas of ICVs and introduces a novel desensitized data testing framework. This work will provide support for security testing methods for desensitized data in ICVs and provide effective security protection for sensitive personal information in ICVs. © ASCE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

AN ADAPTIVE PAGE LEVEL ECC STRATEGY FOR MLC NAND FLASH BASED ON ERROR PREDICTION MODEL 9

AN ADAPTIVE PAGE LEVEL ECC STRATEGY FOR MLC NAND FLASH BASED...

引用

9th International Symposium on Test Automation and Instrumentation, ISTAI 2022

作者： Wei, Debao Song, Yu Li, Lin Han, Bingtong School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Navigation and Control Technology Research Institute of Norinco Group Beijing China Beijing Institute of Radio Measurement Beijing China

ISBN: (纸本)9781839538391

The traditional method of high ability of ECC used when NAND flash in low P/E cycles state would cause the waste of computing process and storage space. To deal with this problem, the research in this paper aims at ECC integrated operation cost. This point based on the following two main theories: (1) the increasing trend of average BER with the retention time and the P/E cycles can be easily modelled;(2) the reliability of different pages in the block varies, and only a small part of the whole pages is poor. The main idea is: traditional FTL management algorithm completed wear equilibrium, but it ignored the reliability difference between different pages. For different pages with different erasure conditions, we choose adaptation strategies of ECC for each page, in that way, we can avoid waste of computing and redundant area consumption of OOB (out of band) caused by high error correcting ability of ECC. The experimental results show that the adaptive page level ECC strategy not only meet the requirements of the reliability, but also raise the efficiency of ECC encoding/decoding. The access time of ECC data of was reduced by 38.1%, and the area consumption of OOB decreased by 56.7%. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

A study of pulsed high voltage driven hollow-cathode electron beam sources through synchronous optical trigger

引用

Plasma Science and technology 2024年第5期26卷 82-90页

作者：霍卫杰贺伟国韩罗峰朱康武王锋 Shanghai Aerospace Electronic Technology Institute Shanghai 201109People’s Republic of China School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444People’s Republic of China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024People’s Republic of China Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province Taiji Laboratory for Gravitational Wave UniverseHangzhou 310024People’s Republic of China Shanghai Aerospace Control Technology Institute Shanghai 201109People’s Republic of China

In this study,a pulsed,high voltage driven hollow-cathode electron beam sources through an optical trigger is designed with characteristics of simple structure,low cost,and easy *** validate the new design,the characteristics of hollow-cathode discharge and electron beam characterization under pulsed high voltage drive are studied experimentally and discussed by discharge characteristics and analyses of waveform details,*** validation experiments indicate that the pulsed high voltage supply significantly improves the frequency and stability of the discharge,which provides a new solution for the realization of a high-frequency,high-energy electron beam *** peak current amplitude in the high-energy electron beam increases from 6.2 A to 79.6 A,which indicates the pulsed power mode significantly improves the electron beam ***,increasing the capacitance significantly affects the highcurrent,lower-energy electron beam more than the high-energy electron beam.

关键词： hollow-cathode nanosecond pulsed electron beam sources optical trigger pulsed high voltage supply beam current distribution

来源：评论

学校读者我要写书评

暂无评论

Area Expansion Effect of Glare Suppression with Low-transmittance Eigenchannels of Transmission Matrices 14

Area Expansion Effect of Glare Suppression with Low-transmit...

引用

14th International Conference on Information Optics and Photonics, CIOP 2023

作者： Zhang, Hengkang Liu, Kaige Wang, Li Chen, Mingce Guo, Shaogang Liu, Qiang Space Optoelectronic Measurement and Perception Lab. Beijing Institute of Control Engineering Beijing100190 China Ministry of Education Beijing100084 China Tsinghua University State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Beijing100084 China

ISBN: (纸本)9781510671744

Wavefront shaping technique has been applied to actively control the intensity profile of optical speckles, and a recent progress is to realize glare suppression with the low-transmittance eigenchannels of the transmission matrices (TMs). This makes it possible to custom-tailor the speckle fields. For the purpose of suppressing glare at will, research about the properties of low-transmittance eigenchannels in glare suppression is demanded. In this paper, we report the area expansion effect of glare suppression with low-transmittance eigenchannels. With numerical simulations, we found the actual darkened area was larger than the set target area due to the transverse correlation of the speckle field. Their difference is related to the measuring noise of the TM and gets smaller with the increase of the noise intensity. We believe our research could help to design structured speckle fields, and it will be of significant for advanced applications of optical speckles. © 2023 SPIE.

关键词： Glare

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter-based Cycle-Consistent Adversarial Learning for Time Series Anomaly Detection

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 790-803页

作者： Liu, Shu-Tang Fan, Ji-Jie Wang, Rui-Dong Han, Han Zhang, De-Yang Faculty of Humanities and Arts Macau University of Science and Technology 999078 China Academic Affairs Office Minjiang University Fuzhou350108 China Kyrgyz National University Named after Jusup Balasagyn Bishkek720033 Kyrgyzstan School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China School of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin150080 China Henan Provincial Institute of Scientific and Technical Information Zhengzhou450003 China

Anomaly detection in time series is challenging for machine learning due to the uncertainty and complex pattern in time series. In this paper, we propose a Kalman filter-based cycle-consistent adversarial learning framework (KFCGAN) for time series anomaly detection, assuming that the abnormal pattern prevents the model from reconstructing the original and filtered signals. Specifically, KFCGAN comprises a Kalman filter module and a cycle-consistent adversarial learning module that utilizes an autoencoder as its generator. Firstly, the Kalman filter module generates the filtered signals from the original signals as the target domain. Then, the forward direction of the cycleconsistent adversarial learning module learns the transformation of the original time series domain to the filtered time series domain. At the same time, the backward direction optimizes it by transforming the target domain to the original domain. Finally, anomaly detection can be modeled as the signal reconstruction problem between the original and target domains. The experimental results on five real-world datasets show that the proposed method outperforms the start-of-the-art, demonstrating that KFCGAN can effectively capture abnormal time series patterns. © 2024, J. Network Intell. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation Integrated with Feature-Enhanced Convolutional Neural Network for Imbalanced Fault Diagnosis in Rolling Bearings 13

Data Augmentation Integrated with Feature-Enhanced Convoluti...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Wang, Li Qu, Qilin Wang, Yanwei Wong, David Shan-Hill Zheng, Ying School of Artificial Intelligence and Automation Huazhong University of Science and Technology China -Belt and Road Joint Laboratory on Measurement and Control Technology Wuhan430074 China School of Mechanical & Electrical Engineering Wuhan Institute of Technology 693 Chuxiong Road Wuhan430073 China National Tsing-Hua University Department of Chemical Engineering Hsinchu30071 Taiwan

ISBN: (纸本)9798350361674

Imbalance in fault samples is a key problem with most rolling bearing datasets in real industrial processes, limiting the performance of fault detection. In addition, existing fault diagnosis methods for rolling bearings do not adopt a modular division between the initial layer and the classification layer. This lack of modularization inhibits the full activation of the network's feature extraction capabilities and impedes subsequent model improvements. In this paper, a novel fault diagnosis method based on data augmentation integrated with a feature-enhanced convolutional neural network (DA-FECNN) is proposed. First, Variational Autoencoder-Generative Adversarial Network (VAE-GAN) is utilized to expand the number of fault samples and improve the diversity of few-shot. Second, a uniform feature-enhanced structure is designed with a feature extraction module, a multi-scale classification module, and a reconstruction module. The network's ability on feature extraction is improved by focusing on high quality features. Thereby, accurate fault classification is realized simultaneously. Experiments on real world data show the effectiveness of the proposed method on fault diagnosis task. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Combined Classification of Hyperspectral and LiDAR Data based on Dual-Channel Cross-Transformer 23

Combined Classification of Hyperspectral and LiDAR Data base...

引用

Proceedings of the 2023 5th International Conference on Video, Signal and Image Processing

作者： Binbin Zhou Qingyan Wang Junping Zhang Yujing Wang School of Measurement-Control and Communication Engineering Harbin University of Science and Technology China School of Electronics and Information Engineering Harbin Institute of Technology China

ISBN: (纸本)9798400709272

In the face of complex scenes, single-modal dominant classification tasks encounter limitations in performance due to insufficient information. On the other hand, joint classification of multimodal remote sensing data faces challenges such as data sample differences and lack of correlation in physical features between modalities, which can impact classification performance. To fully integrate the heterogeneous information of multimodal data and improve classification performance, we propose a dual-channel cross-transformer feature fusion extraction network. The framework leverages self-attention mechanisms to aggregate features within each modality, and the feature fusion module based on cross-modal attention fully considers the complementary information between modalities. Classification tasks are performed using the fused spatial-spectral features obtained from the joint representation of modalities. Extensive experiments conducted on the Houston and MUUFL datasets demonstrate the effectiveness of the proposed model compared to existing methods.

关键词： Hyperspectral image LiDAR data cross modality feature fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Multi-Object Detection and Classification in Construction Sites Based on YOLOv5 23

Multi-Object Detection and Classification in Construction Si...

引用

Proceedings of the 2023 5th International Conference on Video, Signal and Image Processing

作者： Xintao Liang Tianqi Jiang Qiang Fu Qingyan Wang School of Measurement-Control and Communication Engineering Harbin University of Science and Technology China School of Electronics and Information Engineering Harbin Institute of Technology China

ISBN: (纸本)9798400709272

A thorough analysis of the framework structure of the YOLO algorithm is conducted, and based on the YOLOv5 algorithm, rapid detection and classification of extracted features are implemented. Addressing the issue of multi-object detection and classification in engineering sites, this study utilizes the YOLOv5 algorithm for object detection in engineering scenarios, constructs the ResNet50 network, and achieves training and recognition of categories for engineering vehicles, whether washed or unwashed. Additionally, the YOLOv5 algorithm is employed to detect whether construction personnel are wearing safety helmets and reflective clothing, enabling fast and accurate entity detection and classification at construction sites.

关键词： Deep Learning Object Detection ResNet50 YOLOv5

来源：评论

学校读者我要写书评

暂无评论

Wrapper-based feature selection for general data set: the quantum sand cat swarm optimization

Wrapper-based feature selection for general data set: the qu...

引用

Computer, Vision and Intelligent technology (ICCVIT), International Conference on

作者： Jin Yue Ying Guo Hongyuan Gao Dalian Institute of Measurement and Control Technology Dalian China College of Information and Communication Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798331540043

ISBN: (纸本)9798331540050

The existing wrapper feature selection methods have problems such as the difficulty of balancing a relatively high classification accuracy rate with a low feature selection rate, and there are problems such as long time consumption. In response to these issues, this paper combines quantum computing theory and sand cat swarm optimization to design quantum sand cat swarm optimization and combined with K-nearest neighbor method for feature selection. The optimal solution of quantum sand cat swarm optimization is set as the selected optimal feature subset. Simulation experiments are executed on 6 UCI data sets to compare with 4 classical swarm intelligence algorithms. The simulation outcomes show that the wrapper feature selection on the ground of quantum sand cat swarm optimization achieves lower feature selection rate , faster time and higher classification accuracy than the comparison method. It is a high precision and practical wrapper feature selection method.

关键词： Quantum computing Accuracy High dimensional data Quantum mechanics Nearest neighbor methods Feature extraction Robustness Classification algorithms Particle swarm optimization Optimization

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effect of the Intra-Pixel Position of Small PSFs for Optimizing the PL of Optical Subpixel Localization

引用

engineering 2023年第8期27卷 140-149页

作者： Haiyang Zhan Fei Xing Jingyu Bao Ting Sun Zhenzhen Chen Zheng You Li Yuan Department of Precision Instrument Tsinghua UniversityBeijing 100084China State Key Laboratory of Precision Measurement Technology and Instruments Tsinghua UniversityBeijing 100084China Beijing Advanced Innovation Center for Integrated Circuits Tsinghua UniversityBeijing 100084China Joint International Research Laboratory of Advanced Photonics and Electronics Beijing Information Science and Technology UniversityBeijing 100192China Beijing Institute of Control Engineering Beijing 100190Chin

Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement *** unavoidable imaging noise,there is a precision limit(PL)when estimating the target positions on image sensors,which depends on the detected photon count,noise,point spread function(PSF)radius,and PSF’s intra-pixel *** studies have clearly reported the effects of the first three parameters on the PL but have neglected the intra-pixel position ***,we develop a localization PL analysis framework for revealing the effect of the intra-pixel position of small *** accurately estimate the PL in practical applications,we provide effective PSF(e PSF)modeling approaches and apply the Cramér–Rao lower *** on the characteristics of small PSFs,we first derive simplified equations for finding the best PL and the best intra-pixel region for an arbitrary small PSF;we then verify these equations on real ***,we use the typical Gaussian PSF to perform a further analysis and find that the final optimum of the PL is achieved at the pixel boundaries when the Gaussian radius is as small as possible,indicating that the optimum is ultimately limited by light ***,we apply the maximum likelihood *** combination with e PSF modeling allows us to successfully reach the PL in experiments,making the above theoretical analysis *** work provides a new perspective on combining image sensor position control with PSF engineering to make full use of information theory,thereby paving the way for thoroughly understanding and achieving the final optimum of the PL in optical localization.

关键词： Optical measurement Subpixel localization Precision limit optimization Small point spread functions Centroiding Star sensors

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：