检索结果-内蒙古大学图书馆

Low-rank matrix recovery with total generalized variation for defending adversarial examples

Frontiers of Information Technology & Electronic Engineering 2024年第3期25卷 432-445页

作者： Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng School of Science Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China Institute of Big Data Modeling and Technology Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image *** advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural ***,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its *** our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery *** the proposed model,TGV is used to better reconstruct texture information without *** reweighted nuclear norm and Li-norm can enhance the global structure ***,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the *** solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of *** results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关键词： Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example

来源：评论

学校读者我要写书评

暂无评论

Real-Time Capability of Dlr's Beamforming Synthetic Aperture Radar Processing architecture

Real-Time Capability of Dlr's Beamforming Synthetic Aperture...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Maron Schlemon Martin Schulz Rolf Scheiber Marc Jäger Joel Amao Oliva German Aerospace Center (DLR) Microwaves and Radar Institute Germany Chair of Computer Architecture and Parallel Systems Technical University of Munich Germany

ISBN: (数字)9798350320107

ISBN: (纸本)9798350331745

Synthetic Aperture Radar (SAR) enables the generation of realistic and high-resolution 2D or 3D representations of landscapes. Typically, radar instruments are deployed in specially equipped, low-flying aircraft that capture a significant amount of raw data, necessitating image reconstruction processing. However, the aircraft's limited onboard processing capabilities (power, size, weight, cooling, and communication bandwidth to ground stations) and the need to generate multiple SAR products, such as slant-range and geo-coded images during a single flight, require efficient onboard processing and transmission to the ground station. This paper outlines the processing architecture of the digital beamforming SAR (DBFSAR) employed by the German Aerospace Center (DLR) and the specific measures implemented to enable onboard processing. We elucidate the essential software optimizations and their integration into the SAR onboard routines, facilitating (near) real-time capability under certain conditions. Furthermore, we share the insights gained from our work and discuss their applicability to other processing scenarios with limited resource availability.

关键词： Three-dimensional displays Array signal processing Instruments computer architecture Radar imaging Real-time systems Software

来源：评论

学校读者我要写书评

暂无评论

Smartphone-based colorimetric detection of formaldehyde in the air

引用

Building Simulation 2024年第11期17卷 2007-2015页

作者： Meng Yang Jin Ye Tao Yu Ying Song Hua Qian Tianyi Liu Yang Chen Junqi Wang Shi-jie Cao Cong Liu School of Energy and Environment Southeast UniversityNanjing210096China School of Energy and Power Jiangsu University of Science and TechnologyZhenjiangJiangsu212100China Wuhan Second Ship Design and Research Institute Wuhan430205China Hubei Provincial Engineering and Technology Research Center for Food Quality and Safety Test Hubei Provincial Institute for Food Supervision and TestWuhan430075China Laboratory of Image Science and Technology the School of Computer Science and EngineeringSoutheast UniversityNanjingChina Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast UniversityNanjingChina School of Cyber Science and Engineering Southeast UniversityNanjingChina Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationNanjingChina School of Architecture Southeast UniversityNanjingChina Jiangsu Province Engineering Research Center of Urban Heat and Pollution Control Southeast UniversityNanjingChina Global Centre for Clean Air Research(GCARE) University of SurreyGuildfordUK

Adverse impacts of exposure to formaldehyde on human health significantly increases attention in monitoring formaldehyde concentrations in the *** formaldehyde detection methods typically rely on large and costly instruments and requires high skills of expertise,preventing it from being widely accessible to *** study introduced a novel approach utilizing smartphone-based colorimetric *** of green channel signals of digital images by a smartphone successfully capture variation of purple color of 4-amino-3-hydrazino-5-mercapto-1,2,4-triazol solution,which is proportional to formaldehyde *** is because that green and purple are complimentary color pairs.A calibration curve was established between green channel signals and formaldehyde concentrations,with a correlation coefficient of *** limit of the smartphone-based method is 0.008 mg/m^(3).Measurement errors decrease as formaldehyde concentrations increase,with median relative errors of 34%,17%,and 6%for concentration ranges of 0–0.06 mg/m^(3),0.06–0.12 mg/m^(3),and 0.12–0.35 mg/m^(3),*** method replaced scientific instrumentation with ordinary items,greatly reducing cost and operation *** would provide an opportunity to realize onsite measurements for formaldehyde by occupants themselves and increase awareness of air quality for better health protection.

关键词： indoor air quality VOC RGB color identification machine vision

来源：评论

学校读者我要写书评

暂无评论

Intelligent Detection of Stratigraphy Boundary Based on Deep Learning 3rd

Intelligent Detection of Stratigraphy Boundary Based on Deep...

引用

3rd China Intelligent Robotics Annual Conference, CCF CIRAC 2022

作者： Zhao, Qin Wang, Tilin Liu, Yanming Yang, Mingsong Ning, Xiaojuan Hei, Xinhong School of Civil Engineering and Architecture Xi’an University of Technology Xi’an China China Railway First Survey and Design Institute Group Ltd. Xi’an China School of Computer Science and Engineering Xi’an University of Technology Xi’an China

ISBN: (纸本)9789819903009

Robotic exploration technology is widely used in various fields such as information acquisition and topographic photography. Due to dimensional transformation and data loss in data transmission, an additional manual pre-processing is required, which is very time consuming and difficult to ensure the data accuracy. In this paper, we propose an intelligent recognition method of stratigraphy boundaries of engineering geological images based on the Hough prior deep learning network (HT-LCNN). We annotate geological drawing datasets manually at first. And then improve the binary matrix size of the original network, retrain the network on a self-constructed dataset. Finally we design experiments to compare and analyze model learning capabilities so that the optimal model can be adopted to detect negligible gaps on graphical junctions. Experimental results demonstrate that our method outform HT-LCNN in recognizing strata features. It gives the robot the capability to intelligently recognize geological images and can accurately identify over 96% of stratigraphy boundaries and junctions location, thus improving the fluidity of data in the design process and reducing time costs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stratigraphy

来源：评论

学校读者我要写书评

暂无评论

Real-Time Inference of Temporal Emotional and Behavioral Conditions of Learners in Problem Solving Within Mixed Reality Environments 1

引用

19th International Conference on Computing in Civil and Building Engineering, ICCCBE 2022

作者： Castets, Édouard Mutis, Ivan Agam, Gady Department of Mechanical Materials and Aerospace Engineering Illinois Institute of Technology ChicagoIL60616 United States Department of Civil Architecture and Environmental Engineering Illinois Institute of Technology ChicagoIL60616 United States Department of Computer Science Illinois Institute of Technology Chicago60616 United States

ISBN: (数字)9783031325151

ISBN: (纸本)9783031325144

Using new affordances of Machine Learning (ML) and Mixed Reality (MX) technology, the presented research looks at how learners’ decision-making in problem-solving can increase with the technology interaction. The approach empowers users for enhanced problem-solving outcomes by enabling them to perform adapted actions in an MX environment. For example, present an adapted user’s view of 3D design components in the immersive space for any action (locking and moving) in problem-solving (e.g., design interpretations). The aim is to incorporate ML to tailor the user’s ability to problem-solve complex 3D design components by capitalizing on the flexibility of MX immersive environments. The system uses a collection of physiological and pupillometry data to create real-time inferences of the user’s state (emotional and physiological conditions). This paper focuses on the first phase of developing the MX and ML system for the augmented technology-user interaction to allow inference of the data in real time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Dissipativity-Based Scalable $\mathcal{L}_{2}$-Gain Analysis for Nonlinear Networked Systems

Dissipativity-Based Scalable $\mathcal{L}_{2}$-Gain Analysis...

引用

European Control Conference (ECC)

作者： Magnus Axelson-Fisk Bart Besselink Steffi Knorn Chair of Control Technical University of Berlin Berlin Germany Bernoulli Institute for Mathematics Computer Science and Artifical Intelligence University of Groningen Groningen Netherlands

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

By making use of dissipativity theory we can provide an easily verifiable condition which ensures a scalable $\mathcal{L}_{2^{-}}$ gain in a network of nonlinear systems, i.e. a gain independent on the number of systems. However, ensuring bounded $\mathcal{L}_{2}$ -gains may become insufficient, since the energy of the input may grow unbounded. Therefore, we can also give a proof that the same condition may be used to bound the energy of the local systems. Such a bound ensures that the effects of increasing network size do not accumulate in any of the systems. We end the paper with an example in which we demonstrate that scaling the network size does not lead to an accumulation in any part of the network.

关键词： Upper bound Limiting Europe Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Comparison of Atom Detection Algorithms for Neutral Atom Quantum Computing

Comparison of Atom Detection Algorithms for Neutral Atom Qua...

引用

Quantum Computing and Engineering (QCE), IEEE International Conference on

作者： Jonas Winklmann Andrea Alberti Martin Schulz Chair of Computer Architecture and Parallel Systems Technical University of Munich Munich Germany Quantum Many-Body Systems Division Max Planck Institute of Quantum Optics Garching Germany

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

In neutral atom quantum computers, readout and preparation of the atomic qubits are usually based on fluorescence imaging and subsequent analysis of the acquired image. For each atom site, the brightness or some comparable metric is estimated and used to predict the presence or absence of an atom. Across different setups, we can see a vast number of different approaches used to analyze these images. Often, the choice of detection algorithm is either not mentioned at all or it is not justified. We investigate several different algorithms and compare their performance in terms of both precision and execution run time. To do so, we rely on a set of synthetic images across different simulated exposure times with known occupancy states, which we generated using a previously validated imaging simulation. Since the use of simulation provides us with the ground truth of atom site occupancy, we can easily state precise error rates and variances of the reconstructed property. However, knowing the relative performance of these algorithms is not sufficient to justify their use, since better ones can exist that were not compared. To investigate this possibility, we calculated the Cramer-Rao bound in order to establish an upper limit that even a perfect estimator cannot outperform. As the metric of choice, we used the number of photonelectrons that can be contributed to a specific atom site. Every estimator that reconstructs a different property can simply be scaled accordingly. Since the bound depends on the occupancy of neighboring sites, we provide the best and worst cases, as well as a half filled one, which should represent an averaged bound best. Our comparison shows that of our tested algorithms, a global nonlinear least-squares solver that uses the optical system's point spread function (PSF) to return a global bias and each sites' number of photoelectrons performed the best, on average crossing the worst-case bound for longer exposure times. Its main drawback is its huge

关键词： Measurement computers Runtime Deconvolution Error analysis Qubit Quantum mechanics Prediction algorithms Detection algorithms Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Comparison of Atom Detection Algorithms for Neutral Atom Quantum Computing

arXiv

引用

arXiv 2024年

作者： Winklmann, Jonas Alberti, Andrea Schulz, Martin Chair of Computer Architecture and Parallel Systems Technical University of Munich Munich Germany Quantum Many-Body Systems Division Max Planck Institute of Quantum Optics Garching Germany

In neutral atom quantum computers, readout and preparation of the atomic qubits are usually based on fluorescence imaging and subsequent analysis of the acquired image. For each atom site, the brightness or some comparable metric is estimated and used to predict the presence or absence of an atom. Across different setups, we can see a vast number of different approaches used to analyze these images. Often, the choice of detection algorithm is either not mentioned at all or it is not justified. We investigate several different algorithms and compare their performance in terms of both precision and execution run time. To do so, we rely on a set of synthetic images across different simulated exposure times with known occupancy states, which we generated using a previously validated imaging simulation. Since the use of simulation provides us with the ground truth of atom site occupancy, we can easily state precise error rates and variances of the reconstructed property. However, knowing the relative performance of these algorithms is not sufficient to justify their use, since better ones can exist that were not compared. To investigate this possibility, we calculated the Cramér-Rao bound in order to establish an upper limit that even a perfect estimator cannot outperform. As the metric of choice, we used the number of photonelectrons that can be contributed to a specific atom site. Every estimator that reconstructs a different property can simply be scaled accordingly. Since the bound depends on the occupancy of neighboring sites, we provide the best and worst cases, as well as a half filled one, which should represent an averaged bound best. Our comparison shows that of our tested algorithms, a global non-linear least-squares solver that uses the optical system’s point spread function (PSF) to return a global bias and each sites’ number of photoelectrons performed the best, on average crossing the worst-case bound for longer exposure times. Its main drawback is its hug

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Condition monitoring of industrial exhaust motor-fan assembly using statistical feature optimization with nature-inspired optimizers 3

Condition monitoring of industrial exhaust motor-fan assembl...

引用

3rd IEEE International Conference on Control, Instrumentation, Energy and Communication, CIEC 2024

作者： Das, Abhrodeep Agrawal, Ayushman Kundoliya, Nishkarsh Dutta, Ananta Pal, Surjya K. Kumar, Rishi Jalpaiguri Government Engineering College Dept. of Computer Science and Engineering WB India Indian Institute of Technology Dept. of Mechanical Engineering WB Kharagpur India Indian Institute of Technology Dept of Ocean Engg & Naval Architecture WB Kharagpur India Research & Development Centre for Iron & Steel Jharkhand Ranchi India

ISBN: (纸本)9798350313703

Exhausters are very crucial components in sinter plant of steel manufacturing industries. Problems in fan or motor side of the exhausters lead to machine stoppages or reduced speed, resulting in stoppage of the system and decreased sinter production. Common issues include imbalance, misalignments, looseness, eccentricity, and motor bearing failure. The proposed IoT-based system aims to continuously analyze vibration signals, predict issues, and prevent sudden stoppages and exhauster tripping, thereby enhancing overall plant efficiency. This study focuses on online monitoring and health prediction of industrial exhausters by selection of statistical features extracted from triaxial time-series vibration data by using multiple optimizers, followed by implementation of machine learning classifiers. By incorporating a novel feature selection process based on nature-inspired optimizers, this methodology aims to enhance the overall generalization performance of classification. The retrained models with cross-validation were evaluated with real-time industrial data, which shows 99.5% cross-validation accuracy and 95.83% real-time prediction accuracy. The proposed methodology holds great potential for detecting machine faults in industrial applications. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging Hybrid Classical-Quantum Methods for Efficient Load Rebalancing in HPC

Leveraging Hybrid Classical-Quantum Methods for Efficient Lo...

引用

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Justyna Zawalska Minh Chung Katarzyna Rycerz Laura Schulz Martin Schulz Dieter Kranzlmüller Institute of Computer Science AGH University of Krakow Krakow Poland Academic Computer Center CYFRONET AGH Krakow Poland Leibniz Supercomputing Centre (LRZ) Garching bei München Germany MNM-Team Ludwig-Maximilians-Universität München (LMU) Germany Chair for Computer Architecture and Parallel Systems Technical University of Munich (TUM) Germany

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

Load imbalance is a challenge for parallel applications in High Performance Computing (HPC). It is caused by processes having different execution times or load values, leading to idle or wait times at synchronization points, where faster processes must wait for the slowest process to catch up. To mitigate this issue, applications can employ load balancing (LB) strategies, which migrate load between processes to even out load. This is often referred to as the Load Rebalancing Problem (LRP). While many approaches solving the LRP exist, they can only be heuristics and hence further optimization potential exists. In our work, we turn to a novel approach by using hybrid classical-quantum approaches and present two versions of the constrained quadratic model for solving the LRP; the two differ in how they balance the number of qubits required with the types of applied constraints. We compare the quantum-based methods with classical methods using heuristic algorithms Greedy, Karmarkar–Karp, and ProactLB. We evaluate our approaches using imbalance ratio and speedup as metrics, as well as the number of migrated tasks to indicate overhead caused by migrations. Our results show that the quantum-based methods outperform the classic methods. For example, we need only 1/4 of the number of migrated tasks in a realistic use case compared with classical methods, particularly Greedy and KK, to balance the load.

关键词： Measurement Upper bound NP-hard problem High performance computing Heuristic algorithms Qubit Load management Synchronization Optimization Load modeling

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：