检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha410082 China College of Engineering and Design Hunan Normal University Changsha410082 China

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Laundry Cluster Management Using Cloud 18

Laundry Cluster Management Using Cloud

引用

18th Conference on computer Science and Intelligence Systems, FedCSIS 2023

作者： Salach, Mateusz Trybus, Bartosz Pawlowicz, Bartosz Hubacz, Marcin Department of Complex Systems Rzeszow University of Technology Al. Powstancow Warszawy 12 Rzeszow35-959 Poland Department of Computer and Control Engineering Rzeszow University of Technology Al. Powstancow Warszawy 12 Rzeszow35-959 Poland Department of Electronic and Telecommunications Systems Rzeszow University of Technology Al. Powstancow Warszawy 12 Rzeszow35-959 Poland

ISBN: (纸本)9788396744784

Electronic devices in the 21st century have numerous network components, including wireless or wired Internet access modules. Connecting devices to networks and cloud services enables them to access new functionalities and unlock system updates and device security enhancements. The article presents the concept of an intelligent laundry management system based on RFID and cloud computing. The Internet connection not only unlocks additional features of the washing machine, such as different washing modes, but also allows for selecting the appropriate detergent level and washing parameters based on the textile material being washed. Additionally, the paper presents the solution and measurement studies on the accuracy of textile identification. © 2023 Polish Information Processing Society.

关键词： Washing

来源：评论

学校读者我要写书评

暂无评论

MDI-QKD with resource-efficient polarization compensation

MDI-QKD with resource-efficient polarization compensation

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Bedroya, Olinka Li, Chenyang Wang, Wenyuan Hu, Jianyong Lo, Hoi-Kwong Qian, Li University of Toronto Centre for Quantum Information and Quantum Control Dept. of Physics TorontoONM5S 3G4 Canada University of Toronto Centre for Quantum Information and Quantum Control Dept. of Electrical & Computer Engineering TorontoONM5S 3G4 Canada University of Hong Kong Department of Physics Pokfulam Hong Kong 100 College St TorontoON1M5G 1L5 Canada

ISBN: (纸本)9781957171180

We implemented MDI-QKD with a novel polarization compensation scheme using discarded bits without reducing the key-sharing cycle or demanding additional resources. Polarization drift was maintained below 0.13 rad over a 40 km unisolated fibre spool for four hours, and the average secret key rate generated was 7.45×10-6bits per pulse. © 2023 The Author(s).

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

LIN-MM: Multiplexed Message Authentication Code for Local Interconnect Network message authentication in road vehicles

arXiv

引用

arXiv 2022年

作者： Oberti, Franco Sanchez, Ernesto Savino, Alessandro Parisi, Filippo Brero, Mirco Di Carlo, Stefano Control and Computer Engineering Department Politecnico di Torino Torino Italy PUNCH Softronix S.r.l. Torino Italy

The automotive market is profitable for cyberattacks with the constant shift toward interconnected vehicles. Electronic control Units (ECUs) installed on cars often operate in a critical and hostile environment. Hence, both carmakers and governments have supported initiatives to mitigate risks and threats belonging to the automotive domain. The Local Interconnect Network (LIN) is one of the most used communication protocols in the automotive field. Today's LIN buses have just a few light security mechanisms to assure integrity through Message Authentication Codes (MAC). However, several limitations with strong constraints make applying those techniques to LIN networks challenging, leaving several vehicles still unprotected. This paper presents LIN Multiplexed MAC (LIN-MM), a new approach for exploiting signal modulation to multiplex MAC data with standard LIN communication. LIN-MM allows for transmitting MAC payloads, maintaining full-back compatibility with all versions of the standard LIN protocol. © 2022, CC BY-NC-SA.

关键词： control systems

来源：评论

学校读者我要写书评

暂无评论

Optimal 3D Path Planning for the Delivery Quadcopters Operating in a City Airspace 4

Optimal 3D Path Planning for the Delivery Quadcopters Operat...

引用

4th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2020

作者： Taha, Mohammed Yaseen Mohamed, Mohamed Jasim Ucan, Osman Nuri Altinbas University Department of Electrical And Computer Engineering Turkey University of technology-Iraq Department of Control engineering Iraq

ISBN: (纸本)9781728190907

Path planning is a path used in guiding Unmanned Aerial Vehicles (UAVs), the three dimensional optimal path is calculated by A-star and Dijkstra algorithms proposed in the three dimensional environments. Simulation environments consist of a hypothetical environment and a realistic environment and including static obstacles or the shapes of modern buildings. This paper is to find the shortest path and avert obstacles to from the starting off node to the landing node and finding the shortest optimal path on the network nodes using algorithms proposed through the formation of a three dimensional network by connecting link nodes with adjacent starting off node and landing node so that robots can perform their tasks as quickly possible in the environment. The simulation environment has been established to evaluate the performance of the A-star and Dijkstra algorithms. The results proved that A-star algorithm outperformed Dijkstra's algorithm in the execution time factor in finding the optimal path only, but they are similar in distance factor and passe nodes in the optimal path in all cases considered. © 2020 IEEE.

关键词： (Path planning algorithms for the robot A and Dijkstra algorithms coordinates hypothetical and realistic 3D environment node Quadcopter) UAVs

来源：评论

学校读者我要写书评

暂无评论

Improving Software Defined Network controllers in a Multi-Vendor Environment

SSRN

引用

SSRN 2023年

作者： Deneke, Bereketeab Berhanu Beyene, Asrat Mulatu Haile, Endalew Ayenew Department of Computer Science School of Graduate Studies St. Mary’s University Addis Ababa Ethiopia High Performance Computing & Big Data Analytics CoE Department of Electrical and Computer Engineering Addis Ababa Science and Technology University Addis Ababa Ethiopia Adama Science and Technology University School of Electrical Engineering and Computing Electrical Power and Control Engineering Adama Ethiopia

Software Defined Networking (SDN) is an emerging networking paradigm with the potential to foster innovation through programmable networks. SDNs are characterized by the separation of control and data planes where, in a logically centralized controller, it’s possible to make routing decisions on behalf of forwarding elements. For this, there are different protocols used like Open Flow, Forward and control Element Separation (FORCES), Path Computation Element Protocol (PCEP), Network Configuration Protocol (NETCONF), and Interface to Routing System (IRS). Border Gateway Protocol (BGP) is one such protocol that can enable the network programmability promised by SDNs. The controllers used in BGP as control plane protocol leverages RESTCONF (RFC 8040) as management plane protocol to interact with physical routers, switches, and network service firewalls. Therefore, the aim of this work is to improve the performance of SDN controllers using BGP enabling a multi-vendor environment without requiring infrastructure upgrade showcasing how interoperability can be achieved. The proposed system is implemented using OpenDaylight controllers. The performance of the prototype is evaluated using Latency, Throughput, CPU consumption, and TTL (Time to Live). Based on the simulation results it is observed that the SDN controllers that use BGP show improvements in terms of Latency and Throughput. © 2023, The Authors. All rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Convergence of ease-controlled Random Reshuffling gradient Algorithms under Lipschitz smoothness

arXiv

引用

arXiv 2022年

作者： Seccia, Ruggiero Coppola, Corrado Liuzzi, Giampaolo Palagi, Laura Department of Computer Control and Management Engineering A. Ruberti Sapienza University of Rome Via Ariosto 25 RM Rome00185 Italy

In this work, we consider minimizing the average of a very large number of smooth and possibly nonconvex functions and we focus on two widely used minibatch frameworks to tackle this optimization problem: Incremental Gradient (IG) and Random Reshuffling (RR). We define ease-controlled modifications of the IG/RR schemes, which require a light additional computational effort but can be proved to converge under weak and standard *** particular, we define two algorithmic schemes in which the IG/RR iteration is controlled by using a watchdog rule and a derivative-free linesearch that activates only sporadically to guarantee convergence. The two schemes differ in the watchdog and the linesearch, which are performed using either a monotonic or a non-monotonic rule. The two schemes also allow controlling the updating of the stepsize used in the main IG/RR iteration, avoiding the use of pre-set rules that may drive the stepsize to zero too fast, reducing the effort in designing effective updating rules of the stepsize. We prove convergence under the mild assumption of Lipschitz continuity of the gradients of the component functions and perform extensive computational analysis using different deep neural architectures and a benchmark of varying-size datasets. We compare our implementation with both a full batch gradient method (i.e. L-BFGS) and an implementation of IG/RR methods, proving that our algorithms require a similar computational effort compared to the other online algorithms and that the control on the learning rate may allow a faster decrease of the objective *** Codes *** Copyright © 2022, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Empowering ADAS With Driver-Supervised Learning Of Preferences: Parameterization And Human-Machine Interaction 49

Empowering ADAS With Driver-Supervised Learning Of Preferenc...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Wang, Yikai Debernard, Serge Popieul, Jean-Christophe Simon, Philippe Floris, Jerome Univ. Polytechnique Hauts-de-France Cnrs Umr 8201 - Lamih Automation Control Mechanical Engineering and Computer Science Laboratory of Industrial and Human ValenciennesF-59313 France Univ. Poly Technique Hauts-de-France Lamih Cnrs Umr 8201 ValenciennesF-59313 France Insa Hauts-de-France ValenciennesF-59313 France

ISBN: (纸本)9798350331820

The development and widespread use of advanced driver assistance systems (ADAS) has made considerable progress;however, in order for drivers to be confident in delegating driving tasks to these systems, there is a need to further improve their acceptance and trust. One approach to achieve this goal is to provide the driving system with the ability to autonomously learn a driver's preferences under the driver's supervision through a human-machine interface (HMI). This requires first of all identifying these driving preferences, which are derived from the driving situation to be managed, and from the driver's behavior. This paper presents the first results of an experiment conducted on a full-scale simulator in order to validate the parameterization of driving preferences and to identify future interactions through the HMI between drivers and the proposed new driving assistance system. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Voiceprint Diagnosis of Flames: Extraction and Optimization of Acoustic Features

SSRN

引用

SSRN 2024年

作者： Wang, Yuan Ge, Shenwei Yao, Pengbo Shen, Guoqing School of Energy Power and Mechanical Engineering North China Electric Power University No. 2 Beinong Road Huilongguan Changping Beijing102206 China School of Control and Computer Engineering North China Electric Power University No. 2 Beinong Road Huilongguan Changping Beijing102206 China

The sound generated by combustion can directly reflect its state changes. This paper proposes a combustion sound feature extraction method based on acoustic pattern technology, extracts sound features corresponding to various combustion conditions and cold conditions in the laboratory, and compares the robustness and accuracy of the combustion sound model by calculating the Gini index of the combustion sound features and optimizing the amount of its features by adding pink noise. The recognition results show that the combustion acoustic signature feature extraction proposed in this paper has good robustness and recognition rate in the recognition task;in the original data, the recognition rate before optimization can be up to 97.17%, and the recognition rate after optimization is increased to 98.26%.The prediction results show that the optimized flame acoustic pattern extraction method can accurately predict the continuous combustion state changes and provide guidance for boiler combustion monitoring. © 2024, The Authors. All rights reserved.

关键词： Combustion

来源：评论

学校读者我要写书评

暂无评论

Quantitative benefits of the digital product passport and data sharing in remanufacturing 56

Quantitative benefits of the digital product passport and da...

引用

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Szaller, Ádám Gallina, Viola Gal, Barna Gaal, Alexander Fries, Christian Institute for Computer Science and Control Kende str. 13-17 Budapest1111 Hungary EPIC InnoLabs Nonprofit Ltd. Kende str. 13-17 Budapest1111 Hungary Fraunhofer Austria Research GmbH Theresianumgasse 7 WienA-1040 Austria Fraunhofer Institute for Manufacturing Engineering and Automation IPA Nobelstr. 12 Stuttgart70569 Germany

As a part of the circular economy - which aims at closing the loop of materials - remanufacturing is getting more and more attention in recent years. With remanufacturing, companies are carrying out a recovery operation of used products with the aim of rebuilding a like-new condition. As various members of the supply chain are involved in this process, and product data needed for optimal operation is often missing, remanufacturing processes can become uncertain and hard to optimize. The goal of a new European Commission initiative, the digital product passport (DPP), is to facilitate information exchange between stakeholders, in order to reduce uncertainties. DPP, assigned to a product, could contain information about e.g., its origin, composition, repair and dismantling possibilities. In the paper, the essence of DPP is introduced, and a case study is presented to show the qualitative benefits of the increased amount of information about the product. A discrete event-based simulation model of three real production lines that are (re)manufacturing cylinder heads is presented. Experiments are also conducted, where quantitative benefits of using DPP are highlighted, such as decreasing unnecessary production time, increasing ratio of remanufactured parts and increasing output. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference on Manufacturing Systems 2023.

关键词： data sharing, simulation digital product passport remanufacturing simulation

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：