检索结果-内蒙古大学图书馆

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Akash Guna R T Raul Benitez Sikha O K Department of Computer Science and Engineering Amrita School of Engineering Coimbatore India Departament of Automatic Control Universitat Politècnica de Catalunya-BarcelonaTech Spain

Existing explainability approaches for convolutional neural networks (CNNs) are mainly applied after training (post-hoc) which is generally unreliable. Ante-hoc explainers trained simultaneously with the CNN are more reliable. However, current ante-hoc explanation methods mainly generate inexplicit concept-based explanations tailored to specific tasks. To address these limitations, we propose a task-agnostic ante-hoc framework that can generate interpretation maps to visually explain any CNN. Our framework simultaneously trains the CNN and a weighting network - an explanation generation module. The generated maps are self-explanatory, eliminating the need for manual identification of concepts. We demonstrate that our method can interpret classification, facial landmark detection, and image captioning tasks. We show that our framework is explicit, faithful, and stable through experiments. To the best of our knowledge, this is the first ante-hoc CNN explanation strategy that produces visual explanations generic to CNNs for different tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CDQKL: Consensus-Based Distributed Quantum Kernel Learning

CDQKL: Consensus-Based Distributed Quantum Kernel Learning

引用

Quantum Communications, Networking, and Computing (QCNC), International Conference on

作者： Wenxuan Ma Mengxiang Liu Ruilong Deng State Key Laboratory of Industrial Control Technology and the College of Control Science and Engineering Zhejiang University Hangzhou China Department of Automatic Control and Systems Engineering University of Sheffield Sheffield UK

ISBN: (数字)9798350366778

ISBN: (纸本)9798350366785

The field of quantum computing has developed rapidly in recent years due to its promising trend of surpassing traditional machine learning in terms of speed and effectiveness. Quantum kernel learning is one of the paradigms of quantum machine learning, but the training of quantum kernel is time consuming. Therefore, this work makes the first attempt to introduce a consensus-based distributed approach to quantum kernel learning - named CDQKL - that only requires to exchange model parameter information between adjacent nodes while avoiding the need of sharing local training data. Through comparative experimental studies, the advantages of CDQKL in classification accuracy and convergence speed are verified. Considering the popularization of quantum computing cloud service and miniaturization of quantum terminals, the CDQKL adapting to this trend is able to play a vital role in data security, which implies the far-reaching significance of this work. Our code is available at https://***/Leisurivan/CDOKL.

关键词： Training Adaptation models Quantum computing Accuracy Training data Machine learning Market research

来源：评论

学校读者我要写书评

暂无评论

Relay-projection microscopic telescopy

引用

Light(science & Applications) 2025年第4期14卷 1143-1155页

作者： Wenjun Yi Shuyue Zhu Meicheng Fu Nan Gu JunliQi Siyu Liu Mengjun Zhu Ping Wang Xin Chen Yi Zhang Hongyu Zhang Yao Xu Junyi Du Peng Xiong Zhaohua Dong Luobing Dong Qiong Liu Xiujian Li College of Science National University of Defense TechnologyChangshaChina Xi’an Satellite Control Center Xi’anChina School of Information and Electronics Engineering Hunan City UniversityYiyangChina College of Electronic Science National University of Defense TechnologyChangshaChina The School of Computer Science and Technology Xidian UniversityXi’anChina Senior Department of Otolaryngology Head and Neck Surgery the 6th Medical Center of Chinese PLA General HospitalChinese PLA Medical SchoolBeijingChina

The fundamental trade-off between spatial resolution and imaging distance poses a significant challenge for current imaging techniques,such as those used in modern biomedical diagnosis and remote ***,we introduce a new conceptual method for imaging dynamic amplitude-phase-mixed objects,termed relay-projection microscopic telescopy(rPMT),which fundamentally challenges conventional light collection techniques by employing non-line-ofsight light collection through square-law relay-projection *** successfully resolved tiny features measuring 2.76μm,22.10μm,and 35.08μm for objects positioned at distances of 1019.0 mm,26.4 m,and 96.0 m,respectively,from single-shot spatial power spectrum images captured on the relay screen;these results demonstrate that the resolution capabilities of rPMT significantly surpass the Abbe diffraction limit of the 25 mm-aperture camera lens at the respective distances,achieving resolution improvement factors of 7.9,25.4,and *** rPMT exhibits long-distance,wide-range,high-resolution imaging capabilities that exceed the diffraction limit of the camera lens and the focusing range limit,even when the objects are obscured by a scattering *** rPMT enables telescopic imaging from centimeters to beyond hundreds of meters with micrometer-scale resolution using simple devices,including a laser diode,a portable camera,and a diffusely reflecting *** contemporary high-resolution imaging techniques,our method does not require labeling reagents,wavefront modulation,synthetic receive aperture,or ptychography scanning,which significantly reduce the complexity of the imaging system and enhance the application *** method holds particular promise for in-vivo label-free dynamic biomedical microscopic imaging diagnosis and remote surveillance of small objects.

关键词： light collection techniques Imaging Distance Non Line Sight Relay Projection Microscopic Telescopy remote sensingherewe imaging techniquessuch biomedical diagnosis Spatial Resolution

来源：评论

学校读者我要写书评

暂无评论

Erasable-Itemset Mining for Sequential Product Databases 22nd

Erasable-Itemset Mining for Sequential Product Databases

引用

22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022

作者： Hong, Tzung-Pei Chen, Yi-Li Huang, Wei-Ming Tsai, Yu-Chuan Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Electrical and Control China Steel Inc. Kaohsiung Taiwan Library and Information Center National University of Kaohsiung Kaohsiung Taiwan

ISBN: (纸本)9783031274084

Erasable-itemset mining has become a popular research topic and is usually used for product production planning in the industry. If some products in a factory may be removed without critically affecting production profits, the set composed of them is called an erasable itemset. Erasable-itemset mining is to find all the removable material sets for saving funds. This paper extends the concept of erasable itemsets to consider customer behavior with a sequence of orders. We consider the scenario that when an item (material) is not purchased, a product using that material cannot be manufactured, and clients will cancel all their orders if at least one such order exists. We propose a modified erasable-itemset mining algorithm for solving the above problem. Finally, experiments with varying thresholds are conducted to evaluate the execution time and mining results of the proposed algorithm considering customer behavior. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Trade-off Between Execution Time and Memory Consumption in Fuzzy Average-Utility Mining 12

Trade-off Between Execution Time and Memory Consumption in F...

引用

12th International Conference on Awareness science and Technology, iCAST 2023

作者： Hong, Tzung-Pei Ku, Meng-Ping Tsai, Yu-Chuan Huang, Wei-Ming Li, Shu-Min Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan Library and Information Center National University of Kaohsiung Kaohsiung Taiwan Department of Electrical and Control China Steel Inc. Kaohsiung Taiwan

ISBN: (纸本)9798350324693

Fuzzy utility mining considers high-utility fuzzy itemsets as valuable knowledge by integrating quantities of items, their profits, and meaningful fuzzy terms derived by quantities according to membership functions. In fuzzy utility mining, the utility value of a fuzzy itemset in a transaction will always be greater than or equal to those of its subsets, so the measurement of fuzzy utility is an unfair evaluation method. Therefore, the fuzzy average-utility mining problem was issued in 2020, and three solutions were proposed to solve fuzzy average-utility itemsets as two-phase fuzzy average-utility algorithm (TPFAU), two-phase method with tree-based structure (HFAUIM) and one-phase approach with tree-based structure (FHFAUIM), respectively. The second and third methods decrease the candidates generated compared to the first. However, the sorting strategy for mining steps for the last two approaches is based on the frequencies of items in a database and then inserting items of a transaction into a tree in descending order of their frequencies, thus spending more computing time on deriving the actual fuzzy utility value of itemsets. To overcome the above-mentioned problem, this paper adopts a different sorting strategy with a tree-based structure and then by using it to design an algorithm named IFHFAUIM to mine high fuzzy average-utility itemsets. It reduces the storage of required fuzzy utility values in tree nodes and recovers them through tree traversal. Computational experiments show that the proposed method could make a good trade-off between execution time and memory usage. © 2023 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Data Poisoning: Issues, Challenges, and Needs 7

Data Poisoning: Issues, Challenges, and Needs

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of engineering & Technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Trusted Execution of Periodic Tasks for Embedded Systems*

引用

IFAC-PapersOnLine 2023年第2期56卷 8845-8850页

作者： Martin Gunnarsson Nils Vreman Martina Maggio RISE Cybersecurity RISE Research Institutes of Sweden Sweden Department of Automatic Control Lund University Sweden Department of Computer Science Saarland University Germany

Systems that interact with the environment around them generally run some periodic tasks. This class of systems include, among others, embedded control systems. Embedded controllers have been proven vulnerable to various security attacks, including attacks that alter sensor and actuator data and attacks that disrupt the calculation of the control signals. In this paper, we propose, and implement, a mechanism to execute a periodic task and its communication interfaces in a trusted execution environment. This allows us to execute an isolated controller, thus offering higher security guarantees. We analyse the overhead of switching between the regular (possibly compromised) execution environment and the trusted execution environment and quantify the effect of this defence mechanism on the control performance.

关键词： Security Embedded computer architectures Embedded computer control systems and applications

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based DMPC Simulation for Autonomous Mobile Robot Platooning

Cloud-Based DMPC Simulation for Autonomous Mobile Robot Plat...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Anca Maxim Ovidiu Pauca Razvan-Gabriel Lazar Cristian-Mihai Amarandei Constantin-Florin Caruntu Department of Automatic Control and Applied Informatics "Gheorghe Asachi" Technical University of Iasi Iasi Romania Department of Computer Science and Engineering "Gheorghe Asachi" Technical University of Iasi Iasi Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

Cloud computing can be an useful tool when dealing with spatially distributed resources, which need to be simultaneously managed. In this work, a simulation environment is developed using OpenStack to apply a Distributed Model Predictive control strategy for a platooning application consisting of multiple autonomous mobile robots. The idea is to develop the entire algorithm by taking advantage of the possibility of creating virtual machines. Thus, each autonomous mobile robot is treated as an individual agent and is modeled and controlled on a virtual machine, whereas the communication between the agents is performed in the cloud, using the TCP/IP protocol standard. The simulation results illustrate that the platooning application deployed in OpenStack outperforms the simulation performed on a single computer.

关键词： Cloud computing Protocols Computational modeling Stability criteria TCPIP Mathematical models Mobile robots MATLAB Autonomous robots Testing

来源：评论

学校读者我要写书评

暂无评论

Carbon-Aware Computing in a Network of Data Centers: A Hierarchical Game-Theoretic Approach

Carbon-Aware Computing in a Network of Data Centers: A Hiera...

引用

European control Conference (ECC)

作者： Enno Breukelman Sophie Hall Giuseppe Belgioioso Florian Dörfler Division of Decision and Control Systems KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden Department of Electrical Engineering and Information Technology Automatic Control Laboratory ETH Zurich Zürich Switzerland

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Over the past decade, the continuous surge in cloud computing demand has intensified data center workloads, leading to significant carbon emissions and driving the need for improving their efficiency and sustainability. This paper focuses on the optimal allocation problem of batch compute loads with temporal and spatial flexibility across a global network of data centers. We propose a bilevel game-theoretic solution approach that captures the inherent hierarchical relationship between supervisory control objectives, such as carbon reduction and peak shaving, and operational objectives, such as priority-aware scheduling. Numerical simulations with real carbon intensity data demonstrate that the proposed approach success-fully reduces carbon emissions while simultaneously ensuring operational reliability and priority-aware scheduling.

关键词： Data centers Processor scheduling Computational modeling Carbon dioxide Games Supervisory control Resource management

来源：评论

学校读者我要写书评

暂无评论

Dubins Vehicle Intercept of a Brownian Target on a Sphere 63

Dubins Vehicle Intercept of a Brownian Target on a Sphere

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Milutinovic, Dejan Casbeer, David W. University of California Department of Electrical and Computer Engineering Santa CruzCA United States Air Force Research Laboratory Control Science Center Wright-Patterson AFBOH United States

ISBN: (纸本)9798350316339

This paper focuses on a navigation of a Dubins vehicle (DV) to intercept a moving target on a sphere. The uncertainty in the target motion is described by a Brownian motion model. An Itô-type stochastic differential equation for the relative motion between DV and the Brownian moving target is derived. This stochastic differential equation is used to formulate an intercept controller as a minimum time optimal controller. The properties of the controller are incorporated into the numerical computations of the controller, which by its construction can intercept a Brownian target. Our numerical simulation results show that the computed controller can intercept both stationary and moving targets on the sphere. © 2024 IEEE.

关键词： Stochastic systems

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：