检索结果-内蒙古大学图书馆

IEEE International Conference on Automation Science and engineering (CASE)

作者： Hongxin Zhang Jiaxin Liu Ying Tang Gang Xiong State Key Lab of CAD & CG Zhejiang University China College of Software Engineering Zhejiang University of Technology China State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

Predicting traffic flow is one of the fundamental issue to smart cities. However it is still challenging in vehicular cyber-physical systems because of ever-increasing urban traffic data. Most previous models for traffic flow prediction suffers the problem with variance error depends on time and location. In this paper, a novel graph convolution network (GCN) approach is proposed for predicting citywide traffic flow. Our key idea is to introduce spatial and temporal attention to the GCN model to lessen the impact of urban data complexity. A framework of flow-based graph convolutional network is established to improve traffic flow prediction while investigating the spatial and temporal correlation of traffic flow. We further propose practical strategies that efficiently learn parameters of the model. Experimental results demonstrate that the proposed approach to traffic flow prediction outperforms state-of-the-art approaches.

关键词： Predictive models Data models Analytical models Convolution Urban areas Chebyshev approximation Roads

来源：评论

学校读者我要写书评

暂无评论

Correction: Deep Transfer Learning-Based Automated Diabetic Retinopathy Detection Using Retinal Fundus Images in Remote Areas

引用

International Journal of Computational Intelligence systems 2024年第1期17卷 1-1页

作者： Jabbar, Ayesha Naseem, Shahid Li, Jianqiang Mahmood, Tariq Jabbar, Muhammad Kashif Rehman, Amjad Saba, Tanzila Faculty of Information Technology Beijing University of Technology Beijing China College of Electronics and Information Engineering Shenzhen University Shenzhen China Faculty of Information Sciences University of Education Lahore Pakistan Beijing Engineering Research Center for IoT Software and Systems Beijing China Artificial Intelligence and Data Analytics (AIDA) Lab CCIS Prince Sultan University Riyadh Saudi Arabia Faculty of Information Sciences University of Education Vehari Pakistan

来源：评论

学校读者我要写书评

暂无评论

Fine-grained image analysis with deep learning: A survey

arXiv

引用

arXiv 2021年

作者： Wei, Xiu-Shen Song, Yi-Zhe Aodha, Oisin Mac Wu, Jianxin Peng, Yuxin Tang, Jinhui Yang, Jian Belongie, Serge PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China University of Surrey United Kingdom The University of Edinburgh United Kingdom The State Key Laboratory for Novel Software Technology Nanjing University China Peking University China Nanjing University of Science and Technology China The University of Copenhagen The Pioneer Centre for AI Denmark

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas – fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community. © 2021, CC BY.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Towards a Circular Economy of Industrial software

引用

Procedia CIRP 2020年 90卷 37-42页

作者： Vladimir Kutscher Sebastian Ruland Patrick Müller Nathan Wasser Malte Lochau Reiner Anderl Andy Schürr Mira Mezini Reiner Hähnle Department of Computer Integrated Design TU Darmstadt Otto-Berndt-Str. 2 Darmstadt 64287 Germany Real-Time Systems Lab TU Darmstadt Magdalenenstr. 4 64289 Darmstadt Germany Software Technology Group TU Darmstadt Hochschulstr. 10 Darmstadt 64287 Germany Software Engineering Group TU Darmstadt Hochschulstr. 10 Darmstadt 64287 Germany

software has become an indispensable part of industrial production and thus influences the life cycle of manufacturing systems, as many of these systems have to be replaced or evolved due to changing requirements. software adaptation through continuous evolution extends the service time of these systems and thus saves valuable resources. In this paper we present an interdisciplinary methodology for reengineering legacy software to increase the productive lifetime. Our proposed approach systematically reuses implicit domain knowledge to evolve, validate and commission new software from legacy code. The approach is evaluated on a CNC machine as a special type of industrial system.

关键词： software reengineering Industrial software Digital twin Industry 4.0 Legacy system Computerized numerical control Circular economy

来源：评论

学校读者我要写书评

暂无评论

StickyPillars: Robust and efficient feature matching on point clouds using graph neural networks

arXiv

引用

arXiv 2020年

作者： Fischer, Kai Simon, Martin Ölsner, Florian Milz, Stefan Groß, Horst-Michael Mäder, Patrick Valeo Schalter und Sensoren GmbH Kronach Germany Spleenlab GmbH Saalburg-Ebersdorf Germany Neuroinformatics and Cognitive Robotics Lab Ilmenau University of Technology Germany Software Engineering for Safety-Critical Systems Ilmenau University of Technology Germany

Robust point cloud registration in real-time is an important prerequisite for many mapping and localization algorithms. Traditional methods like ICP tend to fail without good initialization, insufficient overlap or in the presence of dynamic objects. Modern deep learning based registration approaches present much better results, but suffer from a heavy run-time. We overcome these drawbacks by introducing StickyPillars, a fast, accurate and extremely robust deep middle-end 3D feature matching method on point clouds. It uses graph neural networks and performs context aggregation on sparse 3D key-points with the aid of transformer based multi-head self and cross-attention. The network output is used as the cost for an optimal transport problem whose solution yields the final matching probabilities. The system does not rely on hand crafted feature descriptors or heuristic matching strategies. We present state-of-art art accuracy results on the registration problem demonstrated on the KITTI dataset while being four times faster then leading deep methods. Furthermore, we integrate our matching system into a LiDAR odometry pipeline yielding most accurate results on the KITTI odometry dataset. Finally, we demonstrate robustness on KITTI odometry. Our method remains stable in accuracy where state-of-the-art procedures fail on frame drops and higher speeds. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SiMPOSE - Configurable N-Way Program Merging Strategies for Superimposition-Based Analysis of Variant-Rich software

SiMPOSE - Configurable N-Way Program Merging Strategies for ...

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Dennis Reuling Udo Kelter Sebastian Ruland Malte Lochau Software Engineering Group University of Siegen Germany Real-Time Systems Lab TU Darmstadt Germany

Modern software often exists in many different, yet similar versions and/or variants, usually derived from a common code base (e.g., via clone-and-own). In the context of product-line engineering, family-based analysis has shown very promising potential for improving efficiency in applying quality-assurance techniques to variant-rich software, as compared to a variant-by-variant approach. Unfortunately, these strategies rely on a product-line representation superimposing all program variants in a syntactically well-formed, semantically sound and variant-preserving manner, which is manually hard to obtain in practice. We demonstrate the SiMPOSE methodology for automatically generating superimpositions of N given program versions and/or variants facilitating family-based analysis of variant-rich software. SiMPOSE is based on a novel N-way model-merging technique operating at the level of control-flow automata (CFA) representations of C programs. CFAs constitute a unified program abstraction utilized by many recent software-analysis tools. We illustrate different merging strategies supported by SiMPOSE, namely variant-by-variant, N-way merging, incremental 2-way merging, and partition-based N/2-way merging, and demonstrate how SiMPOSE can be used to systematically compare their impact on efficiency and effectiveness of family-based unit-test generation. The SiMPOSE tool, the demonstration of its usage as well as related artifacts and documentation can be found at http://***/projects/variance/simpose.

关键词： Merging Tools Testing software Automata Encoding Analytical models

来源：评论

学校读者我要写书评

暂无评论

Sharing of vulnerability information among companies - A survey of Swedish companies

arXiv

引用

arXiv 2019年

作者： Olsson, Thomas Hell, Martin Host, Martin Franke, Ulrik Borg, Markus Software and Systems Engineering Lab RISE Research Institutes of Sweden Lund Dept. of Electrical and Information Technology Lund University Lund Dept. of Computer Science Lund University Lund Software and Systems Engineering Lab RISE Research Institutes of Sweden Kista

software products are rarely developed from scratch and vulnerabilities in such products might reside in parts that are either open source software or provided by another organization. Hence, the total cybersecurity of a product often depends on cooperation, explicit or implicit, between several organizations. We study the attitudes and practices of companies in software ecosystems towards sharing vulnerability information. Furthermore, we compare these practices to contemporary cybersecurity recommendations. This is performed through a questionnairebased qualitative survey. The questionnaire is divided into two parts: the providers' perspective and the acquirers' perspective. The results show that companies are willing to share information with each other regarding vulnerabilities. Sharing is not considered to be harmful neither to the cybersecurity nor their business, even though a majority of the respondents consider vulnerability information sensitive. However, the companies, despite being open to sharing, are less inclined to proactively sharing vulnerability information. Furthermore, the providers do not perceive that there is a large interest in vulnerability information from their customers. Hence, the companies' overall attitude to sharing vulnerability information is passive but open. In contrast, contemporary cybersecurity guidelines recommend active disclosure and sharing among actors in an ecosystem. Copyright © 2019, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A Hybrid RSA algorithm in support of IoT greenhouse applications 2

A Hybrid RSA algorithm in support of IoT greenhouse applicat...

引用

2nd IEEE International Conference on Industrial Internet Cloud, ICII 2019

作者： Aledhari, Mohammed Parizi, Reza M. Dehghantanha, Ali Choo, Kim-Kwang Raymond College of Computing and Software Engineering Kennesaw State University GA United States Cyber Science Lab School of Computer Science University of Guelph ON Canada Department of Information Systems and Cyber Security University of Texas at San Antonio TX United States

ISBN: (纸本)9781728129778

Internet of Things (IoT) is being utilized in a plethora of applications, many of which aim to improve system performance. IoT nodes suffer from several limitations, such as power supply, computational capability, and information security. The current state of IoT information and the potential for security breaches represent a significant untoward condition, especially regarding the organizational necessity for confidentiality and privacy. In this paper, we propose a strong, simple and energy conserving three-stage data encryption algorithm with a focus on securing IoT data in support of greenhouse applications. The stages include: (1) a novel implementation of the K-Map substitution functions;(2) the utilization of a chaotic equation to generate a sequence of random numbers, which are added to the result of the first stage;(3) the third stage incorporates the Rivest, Shamir, and Adelman (RSA) algorithm, performed on feeds from the output of the second stage, resulting in encrypted data, requiring private key decryption. The proposed algorithm eliminates the handshaking of the traditional RSA to exchange the keys (private and public) between IoT nodes and the cloud (server), then reduce the transmission time by 30%. The proposed cryptography algorithm is implemented and tested using two evaluation methods: a single micro-controller (standalone) and on a server (cloud). The algorithm is tested in both directions up/down link, and provides an acceptable and stable performance with 1.3 faster than the original RSA. © 2019 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Bottom-up Paradigm for Traffic Scene Graph Representation 2020

A Bottom-up Paradigm for Traffic Scene Graph Representation

引用

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Zhixuan Zhang Chi Zhang Yuehu Liu Yuanqi Su Ping Li Jinzi Zheng School of Software Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China and Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (纸本)9781450387835

With increasing hardware computing power and model capacity, visual tasks for scene cognitive understanding have attracted more attention, such as visual relationships inference. The scene graph representation formed by a coupling of objects, attributes and relationships nodes displayed by different modalities of information, including original image, foreground things, background stuff and scene attributes, strongly promotes the progress of research area. In this paper, we address the scene graph representation of traffic scenarios for autonomous driving. It should be noted that the universal representation are the specific needs of cognitive understanding of traffic scenes: on the one hand, there is a lack of fine-grained description of key objects and attributes; on the other hand, there are redundant descriptions of objects and relationships. To tackle these problems, we take advantage of the fine-grained instance-level annotation of the traffic scene, proposing a bottom-up representation paradigm. It makes full use of the hierarchical structure of the traffic scene and the sparsity of element classes. In addition, on the basis of the existing methods, we optimize the relationship list of traffic scene graph representation. Moreover, we improve the scene graph annotation methods, proposing a "ground-vision joint location method" to better describe the spatially-distributed visual knowledge. The case analysis showed that compared with existing methods, our paradigm for scene graph can represent more abundant traffic scene information.

关键词： visual relationship description traffic knowledge representation autonomous driving Scene graph

来源：评论

学校读者我要写书评

暂无评论

Motion Planning for Heterogeneous Unmanned systems under Partial Observation from UAV

Motion Planning for Heterogeneous Unmanned Systems under Par...

引用

2020 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Ci Chen Yuanfang Wan Baowei Li Chen Wang Guangming Xie Huanyu Jiang College of Biosystems Engineering and Food Science Zhejiang University Hangzhou China Southern University of Science and Technology Shenzhen China The State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

For heterogeneous unmanned systems composed of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), using UAVs serve as eyes to assist UGVs in motion planning is a promising research direction due to the UAVs' vast view scope. However, its limitations on flight altitude prevent the UAVs from observing the global map. Thus motion planning in the local map becomes a Partially Observable Markov Decision Process (POMDP) problem. This paper proposes a motion planning algorithm for heterogeneous unmanned systems under partial observation from UAV without reconstruction of global maps. Our algorithm consists of two parts designed for perception and decision-making, respectively. For the perception part, we propose the Grid Map Generation Network (GMGN), which is used to perceive scenes from UAV's perspective and classify the pathways and obstacles. For the decision-making part, we propose the Motion Command Generation Network (MCGN). Due to the addition of the memory mechanism, MCGN has planning and reasoning abilities under partial observation from UAVs. We evaluate our proposed algorithm by comparing it with baseline algorithms. The results show that our method effectively plans the motion of heterogeneous unmanned systems and achieves a relatively high success rate.

关键词： Decision making Markov processes Unmanned aerial vehicles Land vehicles Planning Classification algorithms Intelligent robots

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：