检索结果-内蒙古大学图书馆

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Manisha Aeri Satya Prakash Yadav Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Mersin Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Mersin Turkey Research Center for AI and IoT Faculty of Engineering University of Kyrenia Kyrenia Mersin Turkey Computer Science and Engineering Graphic Era Hill University Dehradun Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management (GLBITM) Greater Noida India

Globally, 210 nations have been affected by the 2019 Novel Coronavirus (COVID-19), which has been classified as a pandemic. The modern health system, as well as the economic, educational, and social sides of society, have all been severely impacted. While the rate of transmission keeps increasing, several cooperative strategies between stakeholders to create cutting-edge methods of screening and detecting COVID-19 instances among people at a comparable rate have been noticed. Also, the importance of computational models connected to the technologies of the fourth industrial revolution in accomplishing the desired feat has been emphasized. Unfortunately, there is a gap in the precision of COVID-19 case detection, prediction, and contact tracking. For patients with COVID-19 in isolation units, teleultrasound (TUS), particularly with the support of fifth generation (5G) wireless transmission technology, can offer rapid monitoring, quick clinical progress assessment, and assistance with guiding interventional procedures. Also, it helps conserve medical resources like equipment and supplies while lowering the risk of infection among medical personnel. The review of computer models presented in this work can be used to improve the effectiveness of COVID-19 pandemic case detection and prediction. We concentrate on adoptable big data, AI, and nature-inspired computing solutions for the current pandemic. According to the review, models inspired by nature have shown strong performance in feature selection for medical problems. In pandemic-related cases like COVID-19, contact tracing using big data analytics should also be investigated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Suspended Cable Driven Parallel Robots Using the Geometric Variable Strain Approach

Dynamics of Suspended Cable Driven Parallel Robots Using the...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Anup Teejo Mathew Ikhlas Ben Hmida Suad Alhaj Mustafa Ahmed Nader Ahmed Rashid K. Abu Al-Rub Bashar El-Khasawneh Federico Renda Department of Mechanical Engineering Khalifa University of Science and Technology Abu Dhabi UAE Advanced Digital and Additive Manufacturing Center (ADAM) Khalifa University Abu Dhabi UAE Khalifa University Center for Autonomous Robotic Systems (KUCARS) Khalifa University Abu Dhabi UAE

Construction 3D printing technology has recently received significant attention as a method for creating construction components or printing entire buildings. The deployment of Cable Driven Parallel Robots (CDPRs) in large-scale 3D printing is being explored as a potential candidate due to their low cost, high speed, and design modularity. However, the cable's inertial and elastic properties may lead to sagging and vibration, making the system difficult to model. In this paper, we use the Geometric Variable Strain (GVS) model, a geometrically exact approach based on the Cosserat rod theory, to model the dynamics of a CDPR. The Cosserat rod theory accounts for deformation modes that are not considered in other models, while the geometric formulation ensures accurate and fast computation. We compare the dynamic simulation of a small-scale CDPR prototype at different speeds and with an experimental setup. We also study the dynamics of a large-scale system subject to step loading. We show that analyses of CDPR systems using the GVS approach can reveal new perspectives on their control, design, and development.

关键词： Vibrations Parallel robots Computational modeling Loading Prototypes Soft robotics Three-dimensional printing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Text Classification Algorithm Based On Combined Machine Learning Models

Real-Time Text Classification Algorithm Based On Combined Ma...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： G. Ravivarman Sulabh Mahajan Sowmiya S Shitij Goyal Rahul Gupta Kirti H. Wanjale Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Quantum University Research Center Quantum University Roorkee Uttarakhand India Adjunct Faculty School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka Department of Computer Engineering Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Web text categorization is a prominent area of research and a vital technology in the fields of Web information retrieval and data mining. A great deal of attention and quick progress in this field has occurred in recent years. One sort of deep learning model that has been more useful for extracting important characteristics from textual input while reducing model complexity is the convolutional neural network (CNN). In the meanwhile, a time-tested machine learning method known as support vector machine (SVM) has a stellar reputation for reliability and accuracy. By merging an improved CNN with SVM, this research suggests a new method for Web text categorization. Text characteristics are extracted using the CNN model, which has a five-layer network structure. These features are then used for classification as well as forecasting using SVM. This method presents a new approach to Web text categorization using enhanced models by combining the capabilities of convolutional neural networks (CNNs) and support vector machines (SVMs). Applying this method to datasets with mixed text yields outstanding results, all things considered.

关键词： Support vector machines Deep learning Adaptation models Accuracy Machine learning algorithms Text categorization Real-time systems Vectors Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Shock waves in the magnetic reconnection in the flares on the accretion disk of the SGR~A*

arXiv

引用

arXiv 2024年

作者： Zhao, Tian-Le Li, Xiao-Feng Tang, Ze-Yuan Rajiv, Kumar Center For Astrophysics Guangzhou University Guangdong Guangzhou510006 China Great Bay Center National Astronomical Data Center Guangdong Guangzhou510006 China Astronomy Science and Technology Research Laboratory Department of Education of Guangdong Province Guangzhou510006 China CAS Key Laboratory for Research in Galaxies and Cosmology Department of Astronomy University of Science and Technology of China Hefei230026 China School of Computer Science and Information Engineering Changzhou Institute of Technology Jiangsu Changzhou213032 China Harish-Chandra Research Institute Uttar Pradesh Prayagraj211019 India

Sgr A* often shows bright, episodic flares observationally, the mechanism of the flares intermittent brightening is not very clear. Many people believe the flares may formed by the non-thermal particles, which can be a consequence of the magnetic reconnection and shock waves. In this work, we use the larger magnetic loop in the presence of pseudo-Newtonian potential which mimics general relativistic effects. The simulation results show that the reconnection of magnetic field lines passes through a current sheet, which bifurcates into two pairs of slow shocks. We also find the shock waves heat the plasma, especially when the plasma density is low. The shock wave heating effect by the magnetic reconnection is confirmed by the simulation results, and thus the process of instantaneous brightening of the flares on the accretion disk can be explained. © 2024, CC BY.

关键词： Magnetohydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Quantum simulation of QC2D on a 2-dimensional small lattice

arXiv

引用

arXiv 2025年

作者： Yang, Zhen-Xuan Matsuda, Hidefumi Huang, Xu-Guang Kashiwa, Kouji Physics Department Center for Particle Physics and Field Theory Fudan University Shanghai200438 China Zhejiang Institute of Modern Physics Department of Physics Zhejiang University Hangzhou310027 China Fudan University Shanghai200433 China Shanghai Research Center for Theoretical Nuclear Physics National Natural Science Foundation of China Fudan University Shanghai200438 China Department of Computer Science and Engineering Faculty of Information Engineering Fukuoka Institute of Technology Fukuoka811-0295 Japan

We study the Hamiltonian formulation of SU(2) Yang-Mills theory with staggered fermions in a (2+1)-dimensional small lattice system. We construct a gauge-invariant and finite-dimensional Hilbert space for the theory by applying the loop-string-hadron formulation and specifically map the model to a spin system. We classically emulate digital quantum simulation and observe the real-time evolution of the single-site entanglement entropy, the fermion entanglement entropy, and the fermion pair production. Copyright © 2025, The Authors. All rights reserved.

关键词： Fermions

来源：评论

学校读者我要写书评

暂无评论

Proactive Caching in the Edge-Cloud Continuum with Federated Learning

Proactive Caching in the Edge-Cloud Continuum with Federated...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Ivan Zyrianoff Leonardo Montecchiari Angelo Trotta Lorenzo Gigli Carlos Kamienski Marco Di Felice Department of Computer Science and Engineering University of Bologna Italy Advanced Research Center on Electronic Systems “Ercole De Castro”. University of Bologna Italy Technology Innovation Institute (TIl) United Arab Emirates Federal University of ABC (UFABC) Brazil

In edge-cloud IoT scenarios, proactive caching strategies constitute an effective solution to optimize the use of resources while ensuring adequate Age of Information (Aol). However, the implementation of these strategies introduces significant privacy constraints, primarily stemming from the transmission of sensitive data to the cloud. To address such issue, Federated Learning (FL) has emerged as a promising approach which processes data at the edge, transmitting only the model updates to the cloud. This paper introduces CACHUUM (Cache Architecture for Cloud and Heterogeneous edge in the ContinUUM), a proactive and privacy-aware architecture designed to facilitate the deployment of various edge caching strategies within distributed edge environments. Our architecture supports three families of strategies: local, global and federated, each tailored to meet specific privacy requirements. Furthermore, our architecture is continuum-aware, accommodating different data caching locations, whether it be at the edge node, in the cloud, or somewhere in between. We demonstrate the effectiveness of CACHUUM on simulated IoT environments, by collecting metrics on forecast accuracy, caching precision and data overhead, for different strategies. The latter anticipate the optimal cache update timings for each IoT device, ensuring that Aol aligns with application requirements upon data request.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Collaborative Filtering Algorithm and its Application for Recommendations in E-Commerce

引用

computer Modeling in engineering & sciences 2021年第3期126卷 1275-1291页

作者： Jie Zhang Juan Yang Li Wang Yizhang Jiang Pengjiang Qian Yuan Liu School of Design Jiangnan UniversityWuxi214122China Department of Clothing Design and Engineering Nantong UniversityNantong226001China Research Center for Intelligence Information Technology Nantong UniversityNantong226001China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China Management and Science University Shah AlamSelangor40100Malaysia

With the rapid development of the Internet,the amount of data recorded on the Internet has increased *** is becoming more and more urgent to effectively obtain the specific information we need from the vast ocean of *** this study,we propose a novel collaborative filtering algorithm for generating recommendations in *** study has two main ***,we propose a mechanismthat embeds temporal behavior information to find a neighbor set in which each neighbor has a very significant impact on the current user or ***,we propose a novel collaborative filtering algorithm by injecting the neighbor set into probability matrix *** compared the proposed method with several state-of-the-art alternatives on real *** experimental results show that our proposed method outperforms the prevailing approaches.

关键词： Collaborative filtering temporal behavior probability matrix factorization

来源：评论

学校读者我要写书评

暂无评论

An Intelligent MT Data Inversion Method Constrained by Seismic Texture

An Intelligent MT Data Inversion Method Constrained by Seism...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Hongyu Zhou Rui Guo Maokun Li Fan Yang Shenheng Xu Zuzhi Hu Department of Electronic Engineering State Key Laboratory on Microwave and Digital Communications Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China BGP Inc China National Petroleum Corporation Zhuozhou Hebei China

We study an intelligent magnetotelluric (MT) data inversion with the constraint of seismic texture. A convolutional neural network (CNN)-based image style operator is constructed based on a pre-trained VGG19 network, serving as a measurement tool for assessing the texture of the seismic section and the resistivity model. By simultaneously reconstructing a base model and a fine model, the final reconstruction is able to reflect both the macroscopic geo-electric structure and the fine subsurface geological texture. The optimization is performed using Adaptive Moment Estimation (Adam) with the gradient calculated with the automatic differentiation (AD) method. Synthetic experiments demonstrate that the proposed method elevates inversion accuracy and yields a high-resolution resistivity model that bears the patterns of the seismic section.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Glucose Reduced Graphene Oxide Incorporated Green Tea-Leaf Derived Nanoporous Carbon Materials and Their Enhanced Ammonia Sensing Properties

SSRN

引用

SSRN 2022年

作者： Saravanan, Adhimoorthy Huang, Bohr-Ran Kathiravan, Deepa Graduate Institute of Electro-Optical Engineering Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei106 Taiwan Taiwan Building Technology Center National Taiwan University of Science and Technology Taipei106 Taiwan

Herein, we report a hybrid composite nanostructures based on Glucose reduced graphene oxide (G-rGO) nanospheres decorated on green tea-leaf derived micro-meso porous carbon (PC) structure by nitrogen activation and hydrothermal methods. The physical-chemical properties of resultant PC and G-rGO materials were evaluated by several analytical techniques. The systematic analyses such TEM and XPS reveals the successful incorporation of PC and G-rGO materials. The G-rGO nanospheres incorporated porous carbon (G-rGO/PC) based hybrid carbon material is utilized for the ammonia (NH3) gas sensing application, which provides excellent gas sensing response of 11.7% that is superior to as prepared PC and G-rGO materials. This higher gas response towards NH3 are due to their synergistic effect of highly porous structures and electrical conductivity. In addition, N2 gas treatment lead to nitrogen doping in G-rGO/PC hybrid carbon materials. Moreover, the G-rGO/PC offers an efficient pathway for NH3 gas ions to diffuse into the interior porous surfaces. The significant features of these porous nanocarbon and glucose reduced graphene materials are their simple synthesis method, eco-friendly, and reliability, which can be suitable for diverse gas sensing applications. © 2022, The Authors. All rights reserved.

关键词： Glucose

来源：评论

学校读者我要写书评

暂无评论

Lexicon-matched Word Injection for Chinese NER 22

Lexicon-matched Word Injection for Chinese NER

引用

Proceedings of the 2022 5th International Conference on Machine Learning and Machine Intelligence

作者： Qingyu Wang Guokai Sun Jianguo Sun Yuan Zhuang Lu Li Tianyi Gao School of Computer Science and Technology Harbin Engineering University China and Wuhan Sanjiang Aerospace Network Communication Co. LTD China School of Computer Science and Technology Harbin Engineering University China Cyberspace Security Lab Xidian University China Network Security Department Defence Industry Secrecy Examination and Certification Center China Network Security Technology Application Center Wuhan Sanjiang Aerospace Network Communication Co. LTD China

ISBN: (纸本)9781450397551

Recently, Chinese named entity recognition has attracted a lot of attention. Most of the work utilizes words matching with lexicon which integrates potential word information with lattice structure or graph structure. Although existing approaches have been proved to be effective for exploiting abundant word boundary information, it is difficult to model global semantic interactions due to the inherent one-way sequential nature of the DAG structure. Meanwhile, more interfering lexicon words have been introduced leading to word boundary *** address the above issues, this paper proposes a knowledge fusion method based on lexicon matching word injection, which captures sentence context features through a pre-trained learning model and then injects lexicon knowledge into each character. With the power of Transformer and well-designed encoding, it becomes easier to obtain accurate word information using the character encoding vector of transformer encoder model. Besides, the self-attention module integrating characters with different words is fully leveraged to improve recognition accuracy. Experiments on three Chinese public datasets show that the proposed method outperformed other lexicon-based methods in performance and efficiency.

关键词： Chinese named entity recognition Word injection Multi-headed self-attention

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：