检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Qiliang Gu Shuo Zhao Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Shandong Engineering Research Center of Big Data Applied Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

To address the challenges associated with insufficiently extracting and utilizing features at different levels, overlooking the connection between label meanings and text, and facing problems of over-compression or information loss when extracting global information using recurrent neural networks in the field of multi-label text categorization, this paper introduces an innovative model known as MFFLEN (MultiFeature Fusion and Label Embedding Neural Network). First, a back-translated enhanced label set is constructed by back-translated splicing enhancement of the original label set. This set, together with the text, is then input into the embedding layer, which consists of the pre-trained model of bert-baseChinese, thus establishing the initial connection between the text and the labels within the same vector space. Then, to comprehensively extract multi-level semantic features, the model uses a convolutional layer to extract local features and an embedding layer to extract sentence-level features. A bidirectional attention embedded GRU (BAE-GRU) layer is used to extract hybrid finegrained features, which are then fed into the attention layer to further extract hybrid labeled features based on labeling information. Finally, these three different types of features are fused and multi-label text classification results are obtained using a classifier. The experiments proved that the MFFLEN model achieved 73.82% and 88.44% macro-F1 and 88.00% and 88.86% micro-F1 on the two datasets CAIL 2018 Small and CAIL 2018 Split, respectively, which is better than other baseline models.

关键词： Measurement Recurrent neural networks Splicing Text categorization Semantics Multi label classification Logic gates Feature extraction Vectors Data mining

来源：评论

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

引用

International Conference on computer Supported Cooperative Work in design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language Processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Shuo Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.

关键词： computer vision Fuses Image matching Semantics Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Path to 6G Technological Advances: Assessment and Perspective

Path to 6G Technological Advances: Assessment and Perspectiv...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Myasar Mundher Adnan A. Krishna Kumar Rishabh Chaturvedi Amandeep Kaur Z. Beknozarova Murli Manohar Department Of Computers Techniques Engineering College Of Technical Engineering The Islamic University Najaf Iraq Department of Civil Engineering Karpagam Academy of Higher Education Coimbatore India Department of Mechanical Engineering GLA University Mathura India Department of Computer Application Chandigarh Engineering College Chandigarh Group of Colleges Mohali Punjab India Department of Physics and Chemistry Tashkent Institute of Irrigation and Agricultural Mechanization Engineers" National Research University Tashkent Uzbekistan Department of Electronics & Communication Engineering IES College of Technology Bhopal M.P. India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

At this moment the 5G is very mature in communication as many nations has implemented its fifth generation mobile technological innovation and significant consumers of it, so that essentially commerce (and acadamia) could little redirect to next question. A more interesting feature of the time has been what technology communication looks like now and a prediction of interactions in future. This paper has tried to provide a high-level review of the sixth edition: system requirements, use cases, design paradigms and major presentation figures as well as supporting technologies. For one, we probably think of the question: "Is 6G needed?" by listing the main drivers. Until 2030, we expect the boisterous and polished wave of advanced cell interactions to kick in and envision potential uses as well as challenge conditions. Next, we contrast the key metrics of 6G and 5G through mathematical their characteristics After that we provide a preliminary roadmap in terms of definitions, constraints stability as well as regulation with brief snippets on recent state-of-the-art research services and projects undertaken by various specifiers firms cities countries. At last, we catalog 12 next attainable devices together with their crucial experience, attributes, bugs and the general public groundwork tensions. Lastly, decisions are fashioned as to "what would be the like of 6G?". The aim of this evaluation is to build an knowledgeable context for reviving both interest and curiosity, as wellas paving the way for upcoming study and developmentof 6G.

关键词： 6G mobile communication Technological innovation 5G mobile communication Reviews Urban areas Solids Software Telecommunication computing Software measurement Vehicles

来源：评论

学校读者我要写书评

暂无评论

Towards Fast and Accurate Federated Learning with non-IID Data for Cloud-Based IoT applications

arXiv

引用

arXiv 2022年

作者： Liu, Tian Ding, Jiahao Wang, Ting Pan, Miao Chen, Mingsong The MoE Engineering Research Center of Software Hardware Co-Design Technology and Application East China Normal University Shanghai200062 China The Department of Information Science and Engineering Zaozhuang University Zaozhuang277160 China The Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States

As a promising method of central model training on decentralized device data while securing user privacy, Federated Learning (FL) is becoming popular in Internet of Things (IoT) design. However, when the data collected by IoT devices are highly skewed in a non-independent and identically distributed (non-IID) manner, the accuracy of vanilla FL method cannot be guaranteed. Although there exist various solutions that try to address the bottleneck of FL with non-IID data, most of them suffer from extra intolerable communication overhead and low model accuracy. To enable fast and accurate FL, this paper proposes a novel data-based device grouping approach that can effectively reduce the disadvantages of weight divergence during the training of non-IID data. However, since our grouping method is based on the similarity of extracted feature maps from IoT devices, it may incur additional risks of privacy exposure. To solve this problem, we propose an improved version by exploiting similarity information using the Locality-Sensitive Hashing (LSH) algorithm without exposing extracted feature maps. Comprehensive experimental results on well-known benchmarks show that our approach can not only accelerate the convergence rate, but also improve the prediction accuracy for FL with non-IID data. Copyright © 2022, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Understanding the predictability of path flow distribution in urban road networks using an information entropy approach

引用

Multimodal Transportation 2024年第2期3卷

作者： Guo, Bao Huang, Zhiren Zheng, Zhihao Zhang, Fan Wang, Pu School of Traffic and Transportation Engineering Rail Data Research and Application Key Laboratory of Hunan Province Central South University Changsha China Shandong Provincial Communications Planning and Design Institute Group Co. Ltd Jinan China Department of Computer Science Aalto University Helsinki Finland Department of Civil Engineering McGill University Montreal H3A 0C3 QC Canada Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Predicting the distributions of path flow between origin-destination (OD) pairs in an urban road network is crucial for developing efficient traffic control and management strategies. Here, we use the large-scale taxi GPS trajectory data of San Francisco and Shenzhen to study the predictability of path flow distribution in urban road networks. We develop an approach to project the time-varying path flow distributions into a high-dimensional space. In the high-dimensional space, information entropy is used to measure the predictability of path flow distribution. We find that the distributions of path flow between OD pairs are in general characterized with a high predictability. In addition, we analyze the factors affecting the predictability of path flow distribution. Finally, an n-gram model incorporating high-order gram and low-order gram is proposed to predict the distribution of path flow. A relatively high prediction accuracy is achieved. © 2024

关键词： Human mobility Information entropy Path flow distribution Predictability

来源：评论

学校读者我要写书评

暂无评论

OVERCONSTRAINED LOCOMOTION

arXiv

引用

arXiv 2023年

作者： Sun, Haoran Huang, Bangchao Zhang, Zishang Xu, Ronghan Huang, Guojing Feng, Shihao Huang, Guangyi Yin, Jiayi Qiu, Nuofan Chen, Hua Zhang, Wei Pan, Jia Wan, Fang Song, Chaoyang Department of Mechanical and Energy Engineering Southern University of Science and Technology China Department of Computer Science The University of Hong Kong Hong Kong School of Design Southern University of Science and Technology China ZJU-University of Illinois Urbana-Champaign Institute Zhejiang University China System Design and Intelligent Manufacturing Southern University of Science and Technology China Design & Learning Research Group Southern University of Science and Technology China

This paper studies the design, control, and learning of a novel robotic limb that produces overconstrained locomotion by employing the Bennett linkage for motion generation, capable of parametric reconfiguration between a reptile- and mammal-inspired morphology within a single quadruped. In contrast to the prevailing focus on planar linkages, this research delves into adopting overconstrained linkages as the limb mechanism. The overconstrained linkages have solid theoretical foundations in advanced kinematics but are under-explored in robotic applications. This study showcases the morphological superiority of Overconstrained Robotic Limbs (ORLs) that can transform into planar or spherical limbs, exemplified using the simplest case of a Bennett linkage as an ORL. We apply Model Predictive Control (MPC) to simulate a range of overconstrained locomotion tasks, revealing its superiority in energy efficiency against planar limbs when considering foothold distances and speeds. The results are further verified in overconstrained locomotion policies optimized from Reinforcement Learning (RL). From an evolutionary biology perspective, these findings highlight the mechanism distinctions in limb design between reptiles and mammals and represent the first documented instance of ORLs outperforming planar limb designs in dynamic locomotion. Future studies will focus on deploying the model-based and learning-based overconstrained locomotion skills in the robotic hardware to close the Sim2Real gap for developing evolutionary-inspired, energy-efficient control of novel robotic limbs. © 2023, CC BY-NC-ND.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Implementing Final Step Transitions throughout Outbreaks

Implementing Final Step Transitions throughout Outbreaks

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： I. B. Sapaev Dikendra Kumar Verma Kamal Sharma Ramy Riad Al-Fatlawy Anjali Niharika Varshney «Physics and Chemistry» Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University Tashkent Uzbekistan Scientific Researcher Western Caspian University Baku Azerbaijan Department of Electronics & Communication Engineering Graphic Era Hill University India Department of Mechanical Engineering GLA University Mathura India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Application Chandigarh Engineering College Chandigarh Group of Colleges Mohali Punjab India Department of Electrical Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The worldwide supply system for products had weak areas that were exposed by the COVID-19 pandemic. More specifically, medical supplies as well as personal protection equipment have been inaccessible to people worldwide, even in the most developed countries. A shortage of necessities exacerbates unproductive behaviors like stockpiling and price gouging by raising anxiety and uncertainty. If left up to market forces, these unjust behaviors would probably make difficulties worse and result in more deaths. To help all residents get through difficult times, it is imperative that food and other necessities be distributed safely to them. In order to do this, we suggest a simple, reasonably priced, and a system of robotics that operates without touch to produce and distribute food and emergency packs among community members. The approach incorporates protections against hoarding and cost gouge. The system has been designed, simulated, and validated to ensure that it is prepared for real-world application. This project forms component of a free to download effort, and individual plans may be requested by groups that want to implementing it for the advantage of those living nearby.

关键词： COVID-19 Road transportation Automation Uncertainty Pandemics Supply chains Telecommunication computing Security Protection Robots

来源：评论

学校读者我要写书评

暂无评论

Optimization of Managing Resources in Edge-Cloud Networks

Optimization of Managing Resources in Edge-Cloud Networks

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Saloni Bansal Amit Mittal Mohammed I. Habelalmateen Saloni Manhas A. Achilov Alankrita Joshi Department of Computer Engineering and Applications GLA University Mathura India School of Allied Sciences Graphic Era Hill University Bhimtal Campus Uttarakhand India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Application Chandigarh Engineering College Chandigarh Group of Colleges Mohali Punjab India Docent Department of Physics and Chemistry Tashkent Institute of Irrigation and Agricultural Mechanization Engineers" National Research University Tashkent Uzbekistan Scientific Researcher Western Caspian University Baku Azerbaijan Department of Electronics & Comm. Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

computer services provided by the cloud and edge may improve performance for mobile devices. Although the cloud is capable of handling large processing demands, the edge's local computing power may help reduce the process' delay. Their cooperation is crucial to edge-cloud computational business models as it has the potential to improve guarantee QoS utilization. This paper proposes an efficient solution that enables computing resources to be exchanged between the cloud and edge in the form of buyback and wholesale. We outline the difficulties in controlling computing resources for the cloud in order to determine wholesale price, the distribution of local resources, and buyback procedures for the process of sharing computer ***, we tackle these issues from two angles:(i)maximizing societal welfare and(ii)maximizing profit for *** have proposed an ideal and shown the concavity welfare in order to optimize. Since it is challenging to directly show the convexity of the fundamental problem, we first illustrated the attention to the wholesale price for ii). After that, we created the best possible pricing plan and controlled cloud computing resources to maximize their profitability. Numerical evaluations suggest that although maximizing societal welfare may maximize total profit, optimal pricing may maximize individual gains.

关键词： Performance evaluation Cloud computing Profitability System performance Process control Pricing Delays Telecommunication computing Servers Resource management

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Technology in Peruvian Higher Education: Influence of University Tenure

Virtual Reality Technology in Peruvian Higher Education: Inf...

引用

Virtual Campus (JICV), X International Conference on

作者： Diego Vergara-Rodríguez Ronald Melgarejo Solis Álvaro Antón-Sancho Carlos Edmundo Navarro Depaz Pablo Fernández-Arias Agariadne Dwinggo Samala Technology Instruction and Design in Engineering and Education Research Group (TiDEE.rg) Catholic University of Ávila Ávila Spain Department of Virtual Education Web Digital School University Lima Penú Dept. System Engineering and Computer Science San Marcos University Lima Perú Facuity of Engineering Universitas Negeri Padang Padang West Sumatera Indonesia

ISBN: (数字)9798350343441

ISBN: (纸本)9798350343458

The use of virtual reality (VR) technologies in higher education has been growing in recent years due to their didactic potential in the most diverse areas of knowledge. However, the implementation of VR in universities is affected by several factors, including the level of digitization of the country or the tenure, private or public, of the universities. In this paper, a quantitative, descriptive and correlational research is carried out on the assessments of a group of professors in Peru about the use of VR in their lectures and on the differences in these perceptions according to the tenure of the university of the participants. For this purpose, a validated questionnaire was used, and its responses were statistically analyzed. The results reveal that professors express high ratings for the use of VR but show insufficient levels of digital skills for its use. In addition, professors from private universities give higher ratings of the didactic and usability aspects of VR. It is suggested that VR equipment and faculty training should be strengthened.

关键词： Training Virtual reality Usability

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：