检索结果-内蒙古大学图书馆

Explainable multi-layer COSFIRE filters robust to corruptions and boundary attack with application to retina and palmprint biometrics

引用

Neural Computing and Applications 2024年第30期36卷 19231-19245页

作者： Apap, Adrian Bhole, Amey Fernández-Robles, Laura Castejón-Limas, Manuel Azzopardi, George Department of Artificial Intelligence University of Malta Msida Malta Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747AG Netherlands Department of Mechanical Informatics and Aerospace Engineering Universidad de León Spain Campus de Vegazana s/n León24071 Spain

We propose a novel and versatile computational approach, based on hierarchical COSFIRE filters, that addresses the challenge of explainable retina and palmprint recognition for automatic person identification. Unlike traditional systems that treat these biometrics separately, our method offers a unified solution, leveraging COSFIRE filters’ trainable nature for enhanced selectivity and robustness, while exhibiting explainability and resilience to decision-based black-box adversarial attack and partial matching. COSFIRE filters are trainable, in that their selectivity can be determined with a one-shot learning step. In practice, we configure a COSFIRE filter that is selective for the mutual spatial arrangement of a set of automatically selected keypoints of each retina or palmprint reference image. A query image is then processed by all COSFIRE filters and it is classified with the reference image that was used to configure the COSFIRE filter that gives the strongest similarity score. Our approach, tested on the VARIA and RIDB retina datasets and the IITD palmprint dataset, achieved state-of-the-art results, including perfect classification for retina datasets and a 97.54% accuracy for the palmprint dataset. It proved robust in partial matching tests, achieving over 94% accuracy with 80% image visibility and over 97% with 90% visibility, demonstrating effectiveness with incomplete biometric data. Furthermore, while effectively resisting a decision-based black-box adversarial attack and impervious to imperceptible adversarial images, it is only susceptible to highly perceptible adversarial images with severe noise, which pose minimal concern as they can be easily detected through histogram analysis in preprocessing. In principle, the proposed learning-free hierarchical COSFIRE filters are applicable to any application that requires the identification of certain spatial arrangements of moderately complex features, such as bifurcations and crossovers. Moreover, the sele

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

CyberTEA: a Technical and Economic Approach for Cybersecurity Planning and Investment 36

CyberTEA: a Technical and Economic Approach for Cybersecurit...

引用

36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023

作者： Franco, Muriel Figueredo Granville, Lisandro Zambenedetti Stiller, Burkhard University of Züurich Uzh Communication Systems Group Csg Department of Informatics IfI Binzmüuhlestrasse 14 Zürich8050 Switzerland Computer Networks Group Institute of Informatics Federal University of Rio Grande Do sul Ufrgs Av. Bento Gonçalves Porto Alegre9500 Brazil

ISBN: (纸本)9781665477161

It is essential to look at cybersecurity not only as a technical problem but also from economic, societal, and legal perspectives. Companies need to pay more attention to planning and investments in cybersecurity due to different factors, such as budget constraints and complexities involved in the planning and decision-making processes. Also, companies wrongly do not see themselves as the target of a potential cyberattack. Therefore, there is still a need for approaches that support companies, especially Small and Medium-sized Enterprises (SME), during the cybersecurity planning and investment decisions. This PhD thesis addressed cybersecurity planning and investment gaps by proposing the CyberTEA approach. This approach is composed of a five-phase methodology, a framework, and a set of solutions for cybersecurity planning and investment, considering the technical requirements of cybersecurity and its economic dimensions, such as the potential economic impacts of cyberattacks and the cost-benefit of protections available on the market to protect against specific threats. The evaluations and scientific advances of CyberTEA approach was proven valid to support SMEs while also showing the benefits and opportunities for cybersecurity economic approaches. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Designing low-diameter interconnection networks with multi-ported host-switch graphs

Designing low-diameter interconnection networks with multi-p...

引用

作者： Yasudo, Ryota Nakano, Koji Koibuchi, Michihiro Matsutani, Hiroki Amano, Hideharu Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan Department of Information and Computer Science Keio University Yokohama Japan

A host-switch graph was originally proposed as a graph that represents a network topology of a computer systems with 1-port host computers and (Formula presented.) -port switches. It has been studied from both theoretical and practical aspects in terms of the diameter, the average shortest path length, and the performance of real applications. In recent high-performance computing systems, however, a host computer is connected to multiple switches by using InfiniBand, NVSwitch, or Omni-Path, and consequently they provide high bandwidths. Since a host-switch graph cannot represent such systems, this article extends a host-switch graph so that it can represent such systems. As a result, a host-switch graph can include multi-ported hosts. Furthermore, we propose to use multi-port hosts for reducing the diameter. We show that the diameter minimization is equivalent to solving the degree diameter problem for bipartite graphs of diameter three. Our experimental results show that we can drastically reduce the diameter as well as increasing the bandwidth and improves performance of MPI applications by up to 162% as compared with networks with single-ported hosts. © 2020 John Wiley & Sons, Ltd.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Exploring Children’s Strategies in Response to Robot’s Advice During a group Task with iCub and Nao 16th

Exploring Children’s Strategies in Response to Robot’s A...

引用

16th International Conference on Social Robotics, ICSR + AI 2024

作者： Pusceddu, Giulia Sangineto, Mariapia Cocchella, Francesca Bogliolo, Michela Belgiovine, Giulia Lastrico, Linda Casadio, Maura Rea, Francesco Gena, Cristina Sciutti, Alessandra Robotics Brain and Cognitive Science Department Italian Institute of Technology Genoa Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Computer Science University of Turin Turin Italy Cognitive Architecture for Collaborative Technologies Unit Italian Institute of Technology Genoa Italy Scuola di Robotica Genoa Italy

ISBN: (纸本)9789819635184

This study investigates children’s trust in two humanoid robots, Nao and iCub, through a cooperative game designed to elicit spontaneous behaviors and group dynamics. We investigate whether participants change their choices after hearing advice from a robot, considering rounds where the advice is correct or incorrect, with the robot apologizing for its mistakes. Results reveal that, in most cases, participants prefer not to change their moves after the robot’s advice. Additionally, after the robots made mistakes, participants are less likely to actively follow their advice and more likely to reject it. No significant differences in strategies among the iCub and Nao samples are evidenced. Furthermore, we examine the influence of group dynamics, identifying "Proactive Players" who consistently initiated moves. A significant association between the strategies of this player and their teammates is found, suggesting potential influence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Beyond Entertainment: An Investigation of Externalization Design in Video Games

引用

computer Graphics Forum 2025年

作者： Becker, F. Warnking, R.P. Brückler, H. Blascheck, T. University of Stuttgart Institute for Visualization and Interactive Systems Germany Heidelberg University Medical Faculty Mannheim Department of Biomedical Informatics Germany University of Osnabrück Institute for Computer Science Visual Computing Group Germany

This article investigates when and how video games enable players to create externalizations in a diverse sample of 388 video games. We follow a grounded-theory approach, extracting externalizations from video games to explore design ideas and relate them to practices in visualization. Video games often engage players in problem-solving activities, like solving a murder mystery or optimizing a strategy, requiring players to interpret heterogeneous data—much like tasks in the visualization domain. In many cases, externalizations can help reduce a user's mental load by making tangible what otherwise only lives in their head, acting as external storage or a visual playground. Over five coding phases, we created a hierarchy of 277 tags to describe the video games in our collection, from which we extracted 169 externalizations. We characterize these externalizations along nine dimensions like mental load, visual encodings, and motivations, resulting in 13 categories divided into four clusters: quick access, storage, sensemaking, and communication. We formulate considerations to guide future work, looking at tasks and challenges, naming potentials for inspiration, and discussing which topics could advance the state of externalization. © 2025 The Author(s). computer Graphics Forum published by Eurographics - The European Association for computer Graphics and John Wiley & Sons Ltd.

关键词： Flow visualization

来源：评论

学校读者我要写书评

暂无评论

Model Parallelism on Distributed Infrastructure: A Literature Review from Theory to LLM Case-Studies

arXiv

引用

arXiv 2024年

作者： Brakel, Felix Odyurt, Uraz Varbanescu, Ana-Lucia Informatics Institute University of Amsterdam Amsterdam The Netherlands Vrije Universiteit Amsterdam Amsterdam Netherlands Amsterdam Netherlands Computer Architecture for Embedded Systems University of Twente Enschede The Netherlands Informatics Institute University of Amsterdam Amsterdam Netherlands

Neural networks have become a cornerstone of machine learning. As the trend for these to get more and more complex continues, so does the underlying hardware and software infrastructure for training and deployment. In this survey we answer three research questions: "What types of model parallelism exist?", "What are the challenges of model parallelism?", and "What is a modern use-case of model parallelism?" We answer the first question by looking at how neural networks can be parallelised and expressing these as operator graphs while exploring the available dimensions. The dimensions along which neural networks can be parallelised are intra-operator and inter-operator. We answer the second question by collecting and listing both implementation challenges for the types of parallelism, as well as the problem of optimally partitioning the operator graph. We answer the last question by collecting and listing how parallelism is applied in modern multi-billion parameter transformer networks, to the extend that this is possible with the limited information shared about these networks. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Evolution of Variable Ordering for Binary Decision Diagram Optimization

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Krauss, Rune Drechsler, Rolf German Research Center for Artificial Intelligence Cyber-Physical Systems Department Bremen28359 Germany University of Bremen Group of Computer Architecture Institute of Computer Science Bremen28359 Germany

The hardware complexity related to the number of transistors in electronic devices used by today's society has grown considerably in the last decades because of technological progress. In order to guarantee the correct behavior of such devices and meet time-to-market constraints, there is a need to continuously develop more efficient data structures and algorithms in formal verification. The performance of verification algorithms depends in particular on the compactness of data structures. A reduced ordered binary decision diagram (BDD) is basically a suitable data structure to verify digital circuits, as it represents Boolean functions canonically respecting a variable ordering and allows direct manipulation of them. However, one of the main challenges with BDDs is to find a variable ordering so that the BDD size of a function is compact and does not become impractical due to a dramatically increasing number of BDD nodes. To address the aforementioned issue, this article presents a novel evolution strategy having an efficient evaluation of variable ordering in a divide-and-conquer manner for BDD optimization. Experiments on benchmarks of multilevel circuits show that using this strategy results in considerably smaller BDDs being found significantly faster compared to state-of-the-art optimization techniques. © 1997-2012 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Real-Time Anomaly Detection Using Hardware-based Unsupervised Spiking Neural Network (TinySNN)

Real-Time Anomaly Detection Using Hardware-based Unsupervise...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Ali Mehrabi Nik Dennler Yeshwanth Bethi André van Schaik Saeed Afshar The MARCS Institute International Centre for Neuromorphic Systems Western Sydney University AU Biocomputation Group Centre for Computer Science and Informatics Research University of Hertfordshire UK

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

We present TinySNN, a novel unsupervised spiking neural network hardware designed for real-time anomaly detection. TinySNN provides an energy-efficient edge computing solution for detecting anomalies in industrial settings. TinySNN can model and extract spatio-temporal features in sensory data, thereby enabling it to identify anomalous inputs with high accuracy. During inference, the spike rate of the TinySNN model acts as an indicator of anomalous patterns within these features. We demonstrate TinySNN’s potential using publicly available vibration datasets, achieving impressive anomaly detection results. TinySNN demonstrates exceptional sensitivity to subtle deviations from normal operation, and can dynamically adapt during online, unsupervised training. We provide a digital implementation of TinySNN on an FPGA for hardware efficiency. The TinySNN hardware can be trained online on real industrial data without requiring power hungry computing architectures like GPUs. This approach presents a promising and practical solution that allows for the dynamic learning of normal industrial operations and assists in mitigating risks through continuous monitoring. TinySNN can help ensure the safe and reliable operation of critical industrial systems through neuromorphic processing.

关键词： Neuromorphics Spiking neural networks computer architecture Feature extraction Hardware Real-time systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

Joint Radar-Communication systems by Optimizing Radar Performance and Quality of Service for Communication Users

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar systems 2024年 2卷 778-790页

作者： Tsinos, Christos G. Arora, Aakash Tsiftsis, Theodoros A. National and Kapodistrian University of Athens Department of Digital Industry Technologies Evripus Campus Euboea 34400 Greece University of Twente Radio Systems Group Faculty of Electrical Engineering Mathematics and Computer Science AE Enschede7500 Netherlands Indian Institute of Technology Delhi Centre for Applied Research in Electronics New Delhi110016 India University of Thessaly Department of Informatics and Telecommunications Lamia35100 Greece Jinan University Zhuhai Campus School of Intelligent Systems Science and Engineering Zhuhai519070 China

In this article, the problem of linear precoding and radar receive beamforming design for joint radar-communication (JRC) systems is studied. A multiple antenna base station (BS) that serves multiple single-antenna user terminals on the downlink is assumed. Furthermore, the BS employs a simultaneous radar function in the form of point-like target detection from the reflected return signals in a signal-dependent interference environment. In this work, we jointly design the JRC linear precoder and the radar receive beamformer, thus aiming to optimize the performance of the radar part while maintaining a desired quality of service (QoS) for the communication one subject to a total transmit power constraint. To that end, we formulate a challenging fractional nonconvex optimization problem via which the optimal precoder and radar receive beamformer are derived. Then, we develop algorithmic solutions based on the majorization-minimization (MM) principle and the semidefinite relaxation (SDR) methodology for the formulated optimization problem. The performance of both the proposed solutions is examined and compared to the one of a system that supports only the radar functionality via numerical results. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Learning in public goods games: the effects of uncertainty and communication on cooperation

引用

Neural Computing and Applications 2025年 1-34页

作者： Orzan, Nicole Acar, Erman Grossi, Davide Rădulescu, Roxana Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh Groningen9747 AG Netherlands Institute for Logic Language and Computation University of Amsterdam Science Park Amsterdam1098XH Netherlands Informatics Institute University of Amsterdam Science Park Amsterdam1098XH Netherlands Amsterdam Center for Law and Economics University of Amsterdam Nieuwe Achtergracht 166 Amsterdam1018 WV Netherlands Intelligent Systems Group Utrecht University Princetonplein 5 Utrecht3584 CC Netherlands Artificial Intelligence Lab Vrije Universiteit Brussel Pleinlaan 2 Brussels1050 Belgium

Communication is a widely used mechanism to promote cooperation in multi-agent systems. In the field of emergent communication, agents are typically trained in specific environments: cooperative, competitive or mixed-motive. Motivated by the idea that real-world settings are characterized by incomplete information and that humans face daily interactions under a wide spectrum of incentives, we aim to explore the role of emergent communication when simultaneously exploited across all these contexts. In this work, we pursue this line of research by focusing on social dilemmas. To do this, we developed an extended version of the Public Goods Game, which allows us to train independent reinforcement learning agents simultaneously in different scenarios where incentives are (mis)aligned to various extents. Additionally, agents experience uncertainty in terms of the alignment of their incentives with those of others. We equip agents with the ability to learn a communication policy and study the impact of emergent communication in the face of uncertainty among agents. Our findings show that in settings where all agents have the same level of uncertainty, communication can enhance the cooperation of the whole group. However, in cases of asymmetric uncertainty, the agents that do not face uncertainty learn to use communication to deceive and exploit their uncertain peers. © The Author(s) 2025.

关键词： Adversarial machine learning

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：