检索结果-内蒙古大学图书馆

Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees - Technical Report

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Frank, Daniel Latif, Decky Aspandi Muehlebach, Michael Unger, Benjamin Staab, Steffen Institute for Parallel and Distributed Systems University of Stuttgart Germany Max Planck Institute for Intelligent Systems Germany Stuttgart Center for Simulation Science Germany Institute for Parallel and Distributed Systems University of Stuttgart and Electronics and Computer Science University of Southampton United Kingdom

Recurrent neural networks are capable of learning the dynamics of an unknown nonlinear system purely from input-output measurements. However, the resulting models do not provide any stability guarantees on the input-output mapping. In this work, we represent a recurrent neural network as a linear time-invariant system with nonlinear disturbances. By introducing constraints on the parameters, we can guarantee finite gain stability and incremental finite gain stability. We apply this identification method to learn the motion of a four-degrees-of-freedom ship that is moving in open water and compare it against other purely learning-based approaches with unconstrained parameters. Our analysis shows that the constrained recurrent neural network has a lower prediction accuracy on the test set, but it achieves comparable results on an out-of-distribution set and respects stability conditions. © 2022, CC BY.

关键词： Recurrent neural networks

A Simulative Approach to AMR Fleet Sizing in Decentralized Multi-Robot Task Allocation

学校读者我要写书评

暂无评论

A Simulative Approach to AMR Fleet Sizing in Decentralized M...

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Jana Gödeke Peter Detzner Department for AI and Autonomous Systems Fraunhofer Institute for Material Flow and Logistics Dortmund Germany Ruhr University Bochum Faculty of Computer Science Distributed and Networked Systems Group Bochum Germany

As the Industry 4.0 shifts towards the adoption of autonomous mobile robots (AMRs) in warehouses, decentralized decision-making has become a key design principle. Multi-robot task allocation (MRTA) is a problem that involves assigning tasks to AMRs while optimizing the performance of the system. However, modeling decentralized MRTA applications for optimization without a central instance poses significant challenges due to the autonomy and flexibility of AMRs. In this paper, we propose a simulative approach to address the fleet sizing problem combined with decentralized MRTA applications for AMRs. Based on simulation data, models have been developed that predict key performance indicators (KPIs) for different warehouse layouts and requirements, using techniques from machine learning and mathematical optimization. The model represents KPIs such as constraint satisfaction and utilization rates in a decentralized MRTA scenario including a self-organizing material flow application. Based on this model, we introduce a fleet size selection mechanism. This research contributes to the field of Industry 4.0 by providing a generalizable simulative approach that is adaptable to flexible warehouse environments, allowing for the application of any MRTA algorithm. Moreover, this approach allows the integration of different KPIs, facilitating the adaptation of requirements.

关键词：

Confidential Token-Based License Management 1

学校读者我要写书评

暂无评论

Confidential Token-Based License Management

1st ACM International Workshop on Additive Manufacturing (3D Printing) Security, AMSec 2021

作者： Engelmann, Felix Speichert, Jan Philip God, Ralf Kargl, Frank Bösch, Christoph Department of Computer Science Aarhus University Aarhus Denmark Institute of Aircraft Cabin Systems TUHH Hamburg University of Technology Hamburg Germany Institute of Distributed Systems Ulm University Ulm Germany

ISBN: (纸本)9781450384803

In a global economy with many competitive participants, licensing and tracking of 3D printed parts is desirable if not mandatory for many use-cases. We investigate a blockchain-based approach, as blockchains provide many attractive features, like decentralized architecture and high security assurances. An often neglected aspect of the product life-cycle management is the confidentiality of transactions to hide valuable business information from competitors. To solve the combined problem of trust and confidentiality, we present a confidential licensing and tracking system which works on any publicly verifiable, token-based blockchain that supports tokens of different types representing licenses or attributes of parts. Together with the secure integration of a unique eID in each part, our system provides an efficient, immutable and authenticated transaction log scalable to thousands of transactions per second. With our confidential Token-Based License Management system (cTLM), large industries such as automotive or aviation can license and trace all parts confidentially. © 2021 ACM.

关键词： Blockchain

Cloud Telescope: A distributed architecture for capturing Internet Background Radiation

学校读者我要写书评

暂无评论

Cloud Telescope: A distributed architecture for capturing In...

IEEE International Conference on Cloud Networking (CLOUDNET)

作者： Fabricio Bortoluzzi Barry Irwin Lucas Silvero Beiler Carla Merkle Westphall Cyber Security Programme Noroff University College Kristiansand Norway Postgraduate Programme in Computer Science University of Santa Catarina Florianópolis Brazil Department of Computer Science Rhodes University Grahamstown South Africa Laboratory of Embedded & Distributed Systems University of Vale do Itajai Itajai Brazil

Internet Background Radiation (IBR) comprises a range of unsolicited traffic directed towards Internet hosts. In general, this type of traffic is characterised by high levels of port scanning activity, malware propagation, application exploits, system misconfiguration and denial-of-service attacks. IBR capture is typically undertaken by a system termed a network telescope. This records unfiltered incoming internet traffic for a specific CIDR block in the form of a packet capture (PCAP) file for analysis. This work proposes a novel, cloud-native approach to capturing IBR by the deployment of an ephemeral and reproducible architecture, described as code, distributed across all regions of a cloud service provider. In this paper we discuss the technical and financial viability of using a fleet of small-sized compute instances, in a spot price auction model, to maximise platform collection, capillarity and duration. We also present an overview analysis of the primary characteristics of IBR as collected during a month long proof-of-concept experiment across 26 regions of a cloud service provider in May 2023. Our analysis discusses the aspects of the dataset in quantitative terms: traffic aggregation per protocol, top TCP and UDP ports, top radiation sources and radiation distribution per cloud region. We also provide an overview of the most relevant threats detected. Our results include a formalisation and validation of the cloud telescope, with the corresponding supporting architecture described in Terraform and Ansible. The aggregate dataset amounted to 2.2 GB, and 21.8 million packets. Composition by protocol was 78% TCP, 14% ICMP and 8% UDP.

关键词：

Robust Beamforming for Downlink Multi-Cell systems: A Bilevel Optimization Perspective

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Xingdi Xiong, Yu Yang, Kai Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China

Utilization of inter-base station cooperation for information processing has shown great potential in enhancing the overall quality of communication services (QoS) in wireless communication networks. Nevertheless, such cooperations require the knowledge of channel state information (CSI) at base stations (BSs), which is assumed to be perfectly known. However, CSI errors are inevitable in practice which necessitates beamforming techniques that can achieve robust performance in the presence of channel estimation errors. Existing approaches relax the robust beamforming design problems into semidefinite programming (SDP), which can only achieve a solution that is far from being optimal. To this end, this paper views robust beamforming design problems from a bilevel optimization perspective. In particular, we focus on maximizing the worst-case weighted sum-rate (WSR) in the downlink multi-cell multi-user multiple-input single-output (MISO) system considering bounded CSI errors. We first reformulate this problem into a bilevel optimization problem and then develop an efficient algorithm based on the cutting plane method. A distributed optimization algorithm has also been developed to facilitate the parallel processing in practical settings. Numerical results are provided to confirm the effectiveness of the proposed algorithm in terms of performance and complexity, particularly in the presence of CSI uncertainties. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel state information

Adversarially Robust Spiking Neural Networks Through Conversion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Özdenizci, Ozan Legenstein, Robert Institute of Theoretical Computer Science Graz University of Technology Graz Austria TU Graz - SAL Dependable Embedded Systems Lab Silicon Austria Labs Graz Austria

Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic computing with SNNs expands their use in applications, the problem of adversarial robustness of SNNs becomes more pronounced. To the contrary of the widely explored end-to-end adversarial training based solutions, we address the limited progress in scalable robust SNN training methods by proposing an adversarially robust ANN-to-SNN conversion algorithm. Our method provides an efficient approach to embrace various computationally demanding robust learning objectives that have been proposed for ANNs. During a post-conversion robust finetuning phase, our method adversarially optimizes both layer-wise firing thresholds and synaptic connectivity weights of the SNN to maintain transferred robustness gains from the pre-trained ANN. We perform experimental evaluations in a novel setting proposed to rigorously assess the robustness of SNNs, where numerous adaptive adversarial attacks that account for the spike-based operation dynamics are considered. Results show that our approach yields a scalable state-of-the-art solution for adversarially robust deep SNNs with low-latency. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy efficiency

Distilled Neural Network for Clothes Type Identification

学校读者我要写书评

暂无评论

Distilled Neural Network for Clothes Type Identification

International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Teerapon Chongpiphattanasiri Pramod Wickramatilake Jednipat Moonrinta Mongkol Ekpanyapong Matthew N. Dailey Microelectronics and Embedded Systems Asian Institute of Technology Pathumthani Thailand Artificial Intelligence Center Asian Institute of Technology Pathumthani Thailand Computer Science and Information Management Asian Institute of Technology Pathumthani Thailand

Diverse applications such as criminal forensics and retail customer market segmentation would benefit from the ability to track individuals across multiple cameras. Clothing information is one of the keys to this capability when other identifying information such as the face cannot be reliably extracted. To quickly search for a criminal suspect or re-identify individuals across time and space, filtering by clothing over a given set of cameras for a given time range can dramatically narrow the search. To achieve this capability, we propose a training pipeline that adapts a knowledge distillation neural network to develop a lightweight but effective deep learning model for classifying clothing. The proposed training pipeline produces a small model that achieves 78.70% clothes type classification accuracy on the DeepFashion2 benchmark dataset. An experimental inference time of 0.019 per image on a Nvidia RTX 2070 Super GPU demonstrates that the system has potential for deployment over large-scale camera sensor networks. We expect the new approach to accelerate criminal investigations and enable other analytics requiring reidentification of individuals across multiple cameras at scale.

关键词：

Big Brother is Watching You: Non-Intrusive ZigBee User Profiling

学校读者我要写书评

暂无评论

Big Brother is Watching You: Non-Intrusive ZigBee User Profi...

International Conference on Network and Service Management

作者： Katharina O. E. Müller Delia Datsomor Daria Schumm Bruno Rodrigues Burkhard Stiller Department of Informatics IfI Communication Systems Group CSG University of Zurich UZH Switzerland Embedded Sensing Group ESG Institute of Computer Science in Vorarlberg ICV University of St. Gallen HSG Switzerland

ISBN: (数字)9783903176669

ISBN: (纸本)9798331505158

The rise of the Internet-of-Things (IoT) and smart homes has resulted in the increased use of ZigBee as the communication protocol of choice in home networks, giving ample opportunity for network monitoring and user profiling, as a consequence, raising a major privacy concern. Yet, there has been little exploration of the extractable information solely from network packets, particularly Philips Hue *** as, to the authors’ knowledge, there have been no studies examining whether a single network key provides enough generalization to extract data from other unknown ZigBee networks. To address this gap, this paper proposes StealthProfiler, a passive and real-time Proof-of-Concept (PoC) tool designed to identify, classify, and extract devices and events within a Philips Hue *** a result, the tool was successfully used to extract network events from encrypted Zigbee networks, achieving an accuracy of approximately 94% in identifying devices and events within the network without decrypting network traffic.

关键词： Knowledge engineering Privacy Protocols Zigbee Telecommunication traffic Smart homes Real-time systems Object recognition Data mining Monitoring

Phase-field modeling and effective simulation of non-isothermal reactive transport

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bringedal, Carina Jaust, Alexander Department of Computer science Electrical engineering and Mathematical sciences Western Norway University of Applied Sciences Norway Institute for Modelling Hydraulic and Environmental Systems University of Stuttgart Germany Institute for Parallel and Distributed Systems University of Stuttgart Germany

We consider single-phase flow with solute transport where ions in the fluid can precipitate and form a mineral, and where the mineral can dissolve and release solute into the fluid. Such a setting includes an evolving interface between fluid and mineral. We approximate the evolving interface with a diffuse interface, which is modeled with an Allen-Cahn equation. We also include effects from temperature such that the reaction rate can depend on temperature, and allow heat conduction through fluid and mineral. As Allen-Cahn is generally not conservative due to curvature-driven motion, we include a reformulation that is conservative. This reformulation includes a non-local term which makes the use of standard Newton iterations for solving the resulting non-linear system of equations very slow. We instead apply L-scheme iterations, which can be proven to converge for any starting guess, although giving only linear convergence. The three coupled equations for diffuse interface, solute transport and heat transport are solved via an iterative coupling scheme. This allows the three equations to be solved more efficiently compared to a monolithic scheme, and only few iterations are needed for high accuracy. Through numerical experiments we highlight the usefulness and efficiency of the suggested numerical scheme and the applicability of the resulting *** Codes 35R37, 65M08, 65M22, 76D10, 76D05, 76V05, 80A32, 80M12 © 2023, CC BY.

关键词： Minerals