检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Yu Chen, Yu Zhang, Xiao Lai, Pan Huang, Lei Jiang, Jianmin The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Department of Computer Science South-Central Minzu University Wuhan430074 China The College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China

Recently, deep learning-based compressed sensing (CS) has achieved great success in reducing the sampling and computational cost of sensing systems and improving the reconstruction quality. These approaches, however, largely overlook the issue of the computational cost;they rely on complex structures and task-specific operator designs, resulting in extensive storage and high energy consumption in CS imaging systems. In this paper, we propose a lightweight but effective deep neural network based on recurrent learning to achieve a sustainable CS system;it requires a smaller number of parameters but obtains high-quality reconstructions. Specifically, our proposed network consists of an initial reconstruction sub-network and a residual reconstruction sub-network. While the initial reconstruction sub-network has a hierarchical structure to progressively recover the image, reducing the number of parameters, the residual reconstruction sub-network facilitates recurrent residual feature extraction via recurrent learning to perform both feature fusion and deep reconstructions across different scales. In addition, we also demonstrate that, after the initial reconstruction, feature maps with reduced sizes are sufficient to recover the residual information, and thus we achieved a significant reduction in the amount of memory required. Extensive experiments illustrate that our proposed model can achieve a better reconstruction quality than existing state-of-the-art CS algorithms, and it also has a smaller number of network parameters than these algorithms. Our source codes are available at: https://***/C66YU/CSRN. © 2023, CC BY-NC-SA.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Collaboration And Versioning Framework – A Systematic Top-Down Approach

Collaboration And Versioning Framework – A Systematic Top-D...

引用

Conference on Model Driven engineering Languages and Systems Companion (MODELS-C)

作者： Jakob Pietron Alexander Raschke Joeri Exelmans Matthias Tichy Institute of Software Engineering and Programming Languages Ulm University Ulm Germany Department of Computer Science University of Antwerp – Flanders Make Antwerp Belgium

CONTEXT: Versioning allows users to efficiently create and evolve artifacts, not only but especially in the domain of model-driven engineering. Due to collaboration tools, the place and time where users jointly work at their artifacts do not play an important role anymore. Objective: We systematically elaborated a classification framework for collaboration and versioning tools. The intention is threefold: First, it should be possible to classify existing approaches. Second, deriving from user goals requirements to be met, and capabilities to be supported by a new tool. Third, given a set of capabilities, highlight which user goals can be achieved. Method: According to Kang and Lee, we systematically elaborated a problem space and a solution space and created mappings between both spaces and their sub-spaces. To demonstrate the applicability, we classified existing VCS like git, Google Docs, and several MDE-specific approaches. Results: The created feature diagram covers 238 features and contains about 87 constraints. Conclusion: The developed framework supports researchers and developers in classifying their tools, revealing new opportunities to improve their tools, and guiding the development of new tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Mobile Robot Localization: Drones-Enhanced Sensor Fusion with Innovative Wireless Communication

Optimizing Mobile Robot Localization: Drones-Enhanced Sensor...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Inam Ullah Deepak Adhikari Habib Khan Shabir Ahmad Christian Esposito Chang Choi Department of Computer Engineering Gachon University Seongnam Republic of Korea University of Electronic Science and Technology of China Chengdu China Department of AI Software Gachon University Seongnam-si South Korea Department of Computer Science University of Salerno Fisciano-Salerno Italy

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

Localization is one of the key techniques for 5G/B5G Wireless Sensor Networks (WSNs) research, which determines the application predictions of WSNs to an excessive range. Non-line-of-sight (NLOS) propagation causes most WSN localization errors in complex network environments, like indoors. Extended Kalman Filter (EKF) is a traditional technique that executes inadequately in an NLOS environment, with a focus on the integration of drones or UAVs. The article evaluates the performance of mobile robot localization using EKF in WSN environments. It highlights the importance of improved Internet of Things (IoT) technologies and examines how enhanced 5G communication capabilities and drones or Unmanned Aerial Vehicles (UAVs) effectively overcome obstacles in indoor networks. EKF is a linear estimation of the standard Kalman Filter (KF) and is competent to operate professionally in non-linear classifications. Generally, EKF is based on an iterative method of approximating the statistics of the current state from the previous form. It is also based on the observation framework's linearization around the mean of the existing condition. It has minor calculation difficulty and involves short memory related to the Bayesian procedures, making it appropriate for low-power mobile objects. In this paper, the authors evaluate the localization and tracking presentation of EKF while considering several attributes, such as (a) position, (b) velocity, (c) time, and (d) coverage. The performance of this technique is evaluated using its features and provided with a high level of accuracy.

关键词： Location awareness Wireless communication Wireless sensor networks Sensor fusion Robot sensing systems Mobile robots Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Exploring Text-Guided Single Image Editing for Remote Sensing Images

arXiv

引用

arXiv 2024年

作者： Han, Fangzhou Si, Lingyu Dong, Hongwei Zhang, Lamei Chen, Hao Du, Bo The Department of Information Engineering Harbin Institute of Technology Harbin China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China The Hubei Luojia Laboratory National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China

Artificial intelligence generative content (AIGC) has significantly impacted image generation in the field of remote sensing. However, the equally important area of remote sensing image (RSI) editing has not received sufficient attention. Deep learning based editing methods generally involve two sequential stages: generation and editing. During the generation stage, consistency in content and details between the original and edited images must be maintained, while in the editing stage, controllability and accuracy of the edits should be ensured. For natural images, these challenges can be tackled by training generative backbones on large-scale benchmark datasets and using text guidance based on vision-language models (VLMs). However, these previously effective approaches become less viable for RSIs due to two reasons: First, existing generative RSI benchmark datasets do not fully capture the diversity of remote sensing scenarios, particularly in terms of variations in sensors, object types, and resolutions. Consequently, the generalization capacity of the trained backbone model is often inadequate for universal editing tasks on RSIs. Second, the large spatial resolution of RSIs exacerbates the problem in VLMs where a single text semantic corresponds to multiple image semantics, leading to the introduction of incorrect semantics when using text to guide RSI editing. To solve above problems, this paper proposes a text-guided RSI editing method that is controllable but stable, and can be trained using only a single image. It adopts a multi-scale training approach to preserve consistency without the need for training on extensive benchmark datasets, while leveraging RSI pre-trained VLMs and prompt ensembling (PE) to ensure accuracy and controllability in the text-guided editing process. High-quality RSI editing results can be achieved by first applying multi-scale training to the target image, followed by text-guided fine-tuning using RSI pre-trained VLMs and PE. Experi

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Significance of State-of-Art Search Engine in Game Development

Significance of State-of-Art Search Engine in Game Developme...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Ritu Dewan Rohith Polishetty Naveen Jagadam Mayank Kumar Goyal Kiran Kumar Ravulakollu Bhagwati Sharan Department of Computer Science and Engineering Galgotias College of Engineering and Technology Greater Noida India Sr. software engineer Migo India limited Hyderabad India CEO N2force Technologies Inc. Naperville IL USA Department of Computer Science & Engineering School of Engineering & Technology Sharda University Greater Noida India School of Technology Woxsen University Hyderabad India Department of Computer Science & Engineering School of Engineering and Sciences SRM University Amaravati AP India

Video game development process is different from other software projects while yet being related to them in software engineering. It is distinctive in that it incorporates the work of teams from several fields (art, music, acting, programming, etc.), and that it seeks to create a compelling gaming experience by using prototypes and iterations. This research study focuses on game development and how it is accomplished utilizing a game engine. The process of creating/developing games from a concept is known as game development. Game engines are software programs that help game developers create games. The literature study discusses about the various game engine. The utility of the “Unity” gaming engine is investigated in this paper. Unity may be utilized in different fields as study subjects, but there can be certain frequent benefits & obstacles of utilizing it in different case studies. Students learn which game engine to use based on their specific requirements.

关键词： Video games Art Prototypes Games Search engines Programming software

来源：评论

学校读者我要写书评

暂无评论

A Review of Semantic-Based Reasoning Framework for Context-Aware Mobile-Crowdsourcing

A Review of Semantic-Based Reasoning Framework for Context-A...

引用

International Conference on Information Technology in Asia (CITA)

作者： Nana Hauwa Abdulsalam Sufri Muhammad Raihani Mohamed Department of Software Engineering and Information System Universiti Putra Malaysia Serdang Selangor Malaysia Department of Computer Science Universiti Putra Malaysia Serdang Selangor Malaysia

Technology has increased the interest and demand for pervasive systems which require contextual information to function at optimal capacity. There have been numbers of research in context-aware systems that has limited focused on the semantic-based approach in the crowdsourcing domain. Thus, it promotes challenges in the context and service acquisition and representation for reasoning control mechanism. This paper aims to review semantic-based reasoning framework with a focus on the mobile crowdsourcing domain. Different domains acquire different contextual information, either extrinsic or intrinsic. The review of the frameworks has help to formulate a process framework that applied semantic approach that has the important component for context-aware reasoning process. The framework can be used in the context-aware mobile crowdsourcing domain or can be generalized to other domain to aid reasoning control. Its advantage over other crowdsourcing frameworks which is focuses not only on context and service acquisition but also the representation on the acquired information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A knowledge-driven framework for synthesizing designs from modular components

arXiv

引用

arXiv 2023年

作者： Chaumet, Constantin Rehof, Jakob Schuster, Thomas Software Engineering by Algorithms and Logic Department of Computer Science TU Dortmund University Otto-Hahn-Str. 12 Dortmund44227 Germany

Creating a design from modular components necessitates three steps: Acquiring knowledge about available components, conceiving an abstract design concept, and implementing that concept in a concrete design. The third step entails many repetitive and menial tasks, such as inserting parts and creating joints between them. Especially when comparing and implementing design alternatives, this issue is compounded. We propose a use-case agnostic knowledge-driven framework to automate the implementation step. In particular, the framework catalogues the acquired knowledge and the design concept, as well as utilizes Combinatory Logic Synthesis to synthesize concrete design alternatives. This minimizes the effort required to create designs, allowing the design space to be thoroughly explored. We implemented the framework as a plugin for the CAD software Autodesk Fusion 360. We conducted a case study in which robotic arms were synthesized from a set of 28 modular components. Based on the case study, the applicability of the framework is analyzed and discussed. © 2023, CC BY-NC-ND.

关键词： Logic Synthesis

来源：评论

学校读者我要写书评

暂无评论

Multi-Path Attention Inverse Discrimination Network for Offline Signature Verification

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3057-3071页

作者： Xiaorui Zhang Yingying Wang Wei Sun Qi Cui Xindong Wei School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing 210044China Department of Electrical and Computer Engineering University of WindsorWindsorN9B 3P4Canada School of Teacher Education Nanjing University of Information Science&TechnologyNanjing210044China

Signature verification,which is a method to distinguish the authenticity of signature images,is a biometric verification technique that can effectively reduce the risk of forged signatures in financial,legal,and other business ***,compared with ordinary images,signature images have the following characteristics:First,the strokes are slim,i.e.,there is less effective ***,the signature changes slightly with the time,place,and mood of the signer,i.e.,it has high intraclass *** challenges lead to the low accuracy of the existing methods based on convolutional neural net-works(CNN).This study proposes an end-to-end multi-path attention inverse dis-crimination network that focuses on the signature stroke parts to extract features by reversing the foreground and background of signature images,which effectively solves the problem of little effective *** solve the problem of high intraclass variability of signature images,we add multi-path attention modules between discriminative streams and inverse streams to enhance the discriminative features of signature ***,a multi-path discrimination loss function is proposed,which does not require the feature representation of the samples with the same class label to be infinitely close,as long as the gap between inter-class distance and the intra-class distance is bigger than the set classification threshold,which radically resolves the problem of high intra-class difference of signature *** addition,this loss can also spur the network to explore the detailed infor-mation on the stroke parts,such as the crossing,thickness,and connection of *** respectively tested on CEDAR,BHSig-Bengali,BHSig-Hindi,and GPDS Synthetic datasets with accuracies of 100%,96.24%,93.86%,and 83.72%,which are more accurate than existing signature verification *** is more helpful to the task of signature authentication in justice and finance.

关键词： Offline signatures biometric verification multi-path discrimination loss attention mechanisms inverse discrimination

来源：评论

学校读者我要写书评

暂无评论

Joint Low-Rank Factor and Sparsity for Detecting Access Jamming in Massive MTC Networks

Joint Low-Rank Factor and Sparsity for Detecting Access Jamm...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Shao-Di Wang Hui-Ming Wang Chen Feng Victor C. M. Leung School of Information and Communications Engineering Xi'an Jiaotong University China Department of Electrical and Computer Engineering The University of British Columbia Canada College of Computer and Software Engineering Shenzhen University China

ISBN: (纸本)9781665435413

Due to the weak security protection capabilities of the low-cost and low-complexity massive access of machine-type devices, massive machine-type communications (mMTC) networks are extremely vulnerable to the access jamming, which can affect the correctness of activity and data detection of legitimate devices and even leads to the paralysis of the mission-critical mMTC applications. This paper studies detection problem of the access jamming in the uplink of mMTC (AJ-UM), and we propose to exploit the characteristics of the joint low-rank factor and sparsity (JLFS) to detect the AJ-UM. Our detection method is motivated by the fact that the JLFS-based feature will be significantly impacted if the AJ-UM happens. We first extract the JLFS-based feature by solving a low-rank maximum likelihood factor analysis problem with sparsity constraint, and then perform the AJ-UM detection in a sequential manner. Moreover, the proposed JLFS-based method does not need to know the accurate prior information of the JLFS-based feature in the presence or absence of the AJ-UM, which can determine the AJ-UM exists as long as there is an abrupt change in the JLFS-based feature. Numerical results are finally presented to confirm the effectiveness of the proposed JLFS-based method.

关键词： Maximum likelihood detection Mission critical systems Feature extraction Physical layer Paralysis Security Global communication

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation by Fusing Key Information of Text

引用

computers, Materials & Continua 2023年第2期74卷 2803-2815页

作者： Shijie Hu Xiaoyu Li Jiayu Bai Hang Lei Weizhong Qian Sunqiang Hu Cong Zhang Akpatsa Samuel Kofi Qian Qiu Yong Zhou Shan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Science and Technology on Altitude Simulation Laboratory Sichuan Gas Turbine Establishment Aero Engine Corporation of ChinaMianyang621000China School of Power and Energy Northwestern Polytechnical UniversityXi’an710072China School of Computer Science Southwest Petroleum UniversityChengdu610500China Department of Chemistry Physics and Atmospheric SciencesJackson State UniversityJacksonMS 39217USA

When the Transformer proposed by Google in 2017,it was first used for machine translation tasks and achieved the state of the art at that *** the current neural machine translation model can generate high quality translation results,there are still mistranslations and omissions in the translation of key information of long *** the other hand,the most important part in traditional translation tasks is the translation of key *** the translation results,as long as the key information is translated accurately and completely,even if other parts of the results are translated incorrect,the final translation results’quality can still be *** order to solve the problem of mistranslation and missed translation effectively,and improve the accuracy and completeness of long sentence translation in machine translation,this paper proposes a key information fused neural machine translation model based on *** model proposed in this paper extracts the keywords of the source language text separately as the input of the *** the same encoding as the source language text,it is fused with the output of the source language text encoded by the encoder,then the key information is processed and input into the *** incorporating keyword information from the source language sentence,the model’s performance in the task of translating long sentences is very *** order to verify the effectiveness of the method of fusion of key information proposed in this paper,a series of experiments were carried out on the verification *** experimental results show that the Bilingual Evaluation Understudy(BLEU)score of the model proposed in this paper on theWorkshop on Machine Translation(WMT)2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test *** experimental results show the advantages of the model proposed in this paper.

关键词： Key information transformer fusion neural machine translation

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：