检索结果-内蒙古大学图书馆

Deep Rank-Based Average Pooling Network for Covid-19 Recognition

computers, Materials & Continua 2022年第2期70卷 2797-2813页

作者： Shui-Hua Wang Muhammad Attique Khan Vishnuvarthanan Govindaraj Steven L.Fernandes Ziquan Zhu Yu-Dong Zhang School of Mathematics and Actuarial Science University of LeicesterLE17RHUK Department of Computer Science HITEC University TaxilaTaxilaPakistan Department of Biomedical Engineering Kalasalingam Academy of Research and Education626126Tamil NaduIndia Department of Computer Science Design&JournalismCreighton UniversityOmahaNebraskaUSA Science in Civil Engineering University of FloridaGainesvilleFloridaFL 32608USA School of Informatics University of LeicesterUK

(Aim)To make a more accurate and precise COVID-19 diagnosis system,this study proposed a novel deep rank-based average pooling network(DRAPNet)model,i.e.,deep rank-based average pooling network,for COVID-19 recognition.(Methods)521 subjects yield 1164 slice images via the slice level selection *** the 1164 slice images comprise four categories:COVID-19 positive;community-acquired pneumonia;second pulmonary tuberculosis;and healthy *** method firstly introduced an improved multiple-way data ***,an n-conv rankbased average pooling module(NRAPM)was proposed in which rank-based pooling—particularly,rank-based average pooling(RAP)—was employed to avoid ***,a novel DRAPNet was proposed based on NRAPM and inspired by the ***-CAM was used to generate heatmaps and gave our AI model an explainable analysis.(Results)Our DRAPNet achieved a micro-averaged F1 score of 95.49%by 10 runs over the test *** sensitivities of the four classes were 95.44%,96.07%,94.41%,and 96.07%,*** precisions of four classes were 96.45%,95.22%,95.05%,and 95.28%,*** F1 scores of the four classes were 95.94%,95.64%,94.73%,and 95.67%,***,the confusion matrix was given.(Conclusions)The DRAPNet is effective in diagnosing COVID-19 and other chest infectious *** RAP gives better results than four other methods:strided convolution,l2-norm pooling,average pooling,and max pooling.

关键词： COVID-19 rank-based average pooling deep learning deep neural network

来源：评论

学校读者我要写书评

暂无评论

Self-timed Fused Multiplier-Adder Pipeline Optimization

Self-timed Fused Multiplier-Adder Pipeline Optimization

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Igor Sokolov Yuri Stepchenkov Yuri Diachenko Institute of Informatics Problems of FRC "Computer Science and Control" of Russian Academy of Sciences Moscow Russia

Self-timed circuits are optimal for implementing computing systems operating under extreme conditions. They function reliably under any changes in environmental and power conditions, detect all constant faults, and are more resistant to soft errors than synchronous counterparts. The article considers the problem of correct practical self-timed implementation of the operation of multiplying two operands with subsequent third operand addition and subtraction without intermediate product rounding as a pipeline with multiplexing of its parallel sections. Statistical analysis shows that in 64% of cases the operation result does not depend on the product, and in 29% of cases it does not depend on the third operand, which allows not performing a number of intermediate data transformations. Branching the pipeline reduces power consumption and improves its performance with the appropriate values of the input operands due to the lower complexity of the alternative path's stages. An active path marker FIFO (First Input First Output) guarantees the correct sequence of the operation results. The program ASPECT, analyzing circuits for semi-modularity, proves the self-timing of the described implementation.

关键词： Resistance Multiplexing Power demand Statistical analysis Pipelines Probability Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 19-23页

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Faculty of Computing and Data Science FLAME University Maharashtra Pune India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023 The Authors

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Allocation in 5G Networks Through Downlink and Uplink Decoupling

Optimizing Resource Allocation in 5G Networks Through Downli...

引用

International Conference on Ultra Modern Telecommunications and Workshops (ICUMT)

作者： Christos Bouras Charalampos Chatzigeorgiou Vasileios Kokkinos Apostolos Gkamas Philippos Pouyioutas Computer Engineering & Informatics Dept University of Patras Greece Computer Science Dept University Ecclisiastical Academy of Vella Greece Computer Science Dept University of Nicosia

This research paper sets out to explore the multi-faceted and complex topic of decoupling downlink and uplink in 5G networks, with a view to optimizing resource allocation. Drawing on an extensive range of current literature and industry trends, the authors conduct a comprehensive and in-depth analysis of the potential benefits and drawbacks of decoupling, taking into account the impact on network capacity, flexibility, and user experience. Additionally, the article offers valuable insights into the practical implementation of decoupling in real-world 5G networks, including an exploration of the challenges and considerations that may arise, and potential future developments in this field. Through a rigorous and meticulous examination of the topic, the authors aim to provide an understanding of the subject, offering valuable guidance and insights to future researchers and developers working in this area. With a focus on depth and detail, this paper represents a vital contribution to the ongoing dialogue surrounding decoupling in 5G networks and has the potential to drive significant advancements in the field in the years to come.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Network Performance in 5G Systems with Downlink and Uplink Decoupling

Optimizing Network Performance in 5G Systems with Downlink a...

引用

International Conference on Advanced Communication Technologies and Networking (CommNet)

This research paper presents a comprehensive investigation into the optimization of resource allocation in 5G networks through the technique of Downlink and Uplink Decoupling (DUDe). With the growing need for accurate modeling and scenario planning in 5G systems, DUDe allows for the configuration of an additional, lower frequency signal on the uplink to complement the existing uplink signal, rebalancing the uplink/downlink difference at the cell edge and enhancing coverage and network capacity. Drawing on extensive literature and industry trends, this study explores the benefits and challenges of DUDe, considering its impact on network performance, user experience, and future developments. The paper also introduces a simulation-based methodology and experiments to evaluate the effectiveness of DUDe in improving coverage, capacity, latency, and energy efficiency. The findings contribute to the understanding of DUDe’s potential in optimizing 5G networks, providing valuable insights for researchers and network operators in designing and deploying efficient resource allocation strategies for enhanced network performance in various scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Local Feature Extraction Mechanism for Effective Content Based Image Retrieval 2

A Local Feature Extraction Mechanism for Effective Content B...

引用

2nd International Conference on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET 2022

作者： Kumar, Sumit Singhal, Manya Revthi, R. School of Computer Science University of Petroleum and Energy Studies Informatics Cluster Dehradun India Tech Mahindra India Karpagam Academy of Higher Education Coimbatore India

ISBN: (数字)9781665488754

ISBN: (纸本)9781665488754

A CBIR system works on the primitive visual features extracted from the images of a concerned database. A CBIR system should provide better results and need to have a close resemblance with human perception. So, to keep these points in mind, in this paper, we have proposed a CBIR system that works on local image features to provide better efficiency. In contrast, the HSV color model has been incorporated as it is closest to human perception. Various statistical parameters are evaluated from H and S components for the color features extraction. Now, for texture and shape features BDIP and BVLC are deployed. This work has been validated through various benchmark databases, and overlying results are capable enough to demonstrate its superiority over contemporaries. © 2022 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A computer Search of New OBZCPs of Lengths up to 49

arXiv

引用

arXiv 2024年

作者： Kazakov, Peter Liu, Zilong Institute of Mathematics and Informatics Bulgarian Academy of Sciences Bulgaria School of Computer Science and Electronic Engineering University of Essex United Kingdom

This paper aims to search for new optimal and sub-optimal Odd Binary Z-Complimentary Pairs (OBZCPs) for lengths up to 49. As an alternative to the celebrated binary Golay complementary pairs, optimal OBZCPs are the best almost-complementary sequence pairs having odd lengths. We introduce a computer search algorithm with time complexity O(2N), where N denotes the sequence length and then show optimal results for all 27 ≤ N ≤ 33 and N = 37,41,49. For those sequence lengths (i.e., N = 35,39,43,45,47) with no optimal pairs, we show OBZCPs with largest zero-correlation zone (ZCZ) widths (i.e., Z-optimal). Finally, based on the Pursley–Sarwate criterion (PSC), we present a table of OBZCPs with smallest combined auto-correlation and cross-correlation. Copyright © 2024, The Authors. All rights reserved.

关键词： Data obfuscation

来源：评论

学校读者我要写书评

暂无评论

Modified SDRE Method for Finite-time Nonlinear Optimal Control Problem

Modified SDRE Method for Finite-time Nonlinear Optimal Contr...

引用

2022 International Russian Automation Conference, RusAutoCon 2022

作者： Kabanov, Aleksey A. Department of Informatics and Control in Technical Systems Sevastopol State University Russia Federal Research Center 'Computer Science and Control' of Russian Academy of Sciences Moscow Russia

ISBN: (数字)9781665466554

ISBN: (纸本)9781665466554

the optimal control problem on a finite-time interval for a nonlinear system with state-dependent coefficients is considered in this paper. The most common method for such systems is the state-dependent Riccati equation (SDRE) method. Ehe implementation of SDRE in a finite-time interval requires the solution of the state-dependent Riccati differential equation (SDDRE). Since the initial conditions for the SDDRE are set at a final time moment, the numerical solution requires integration from right to left. The lack of information about the system state at future time points does not allow this integration to be performed. This complexity can be overcome through an approximate solution based on the state-dependent Lyapunov differential equation. However, this approximate solution may be less accurate, for example, compared to Riccati Sequence Approximate Method (ASRE). A modification of the SDRE method based on preliminary calculations of the system matrices by solving an auxiliary terminal control problem on the inverse time interval is presented. In such a situation, the backward integration of the auxiliary problem on the specified time interval will take place in direct time for the original problem. Two examples of the application of this method in nonlinear problems are shown. © 2022 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Real-time testing of vision-based systems for AGVs with ArUco markers

Real-time testing of vision-based systems for AGVs with ArUc...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Filus, Katarzyna Sobczak, Lukasz Domanska, Joanna Domanski, Adam Cupek, Rafal Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Gliwice Poland

ISBN: (纸本)9781665480451

Automated Ground Vehicles (AGVs) use deep-learning-based vision systems to perceive the surrounding environment and extract relevant information about it. Although deep learning models offer high capabilities, they require large amounts of data to be properly trained and tested. Testing is especially important when off-the-shelf models are used by the AGVs - to examine whether they can meet the demands of complex environments such as the production halls of automated factories. One area of such perception algorithms is object recognition. To test such systems, we propose a solution based on ArUco fiducial markers used for automatic labeling of objects. Our solution can be used to test deep learning systems in real time directly on a robot. Our solution requires minimal interference with the environment and additional infrastructure - the desired objects only need to be marked with a marker printed on a home printer. Therefore, the presented testing procedure can be used for testing of AGVs in real-life environments during a real ride from an actual robot perspective. Data gathered during the online testing can be used for the offline comparison of the accuracy of different deep learning models. Although we focus on the online and offline testing in our study, we also incorporated a marker masking procedure. Therefore, the resulting datasets may also be used for training. © 2022 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf 38

Learning to Discuss Strategically: A Case Study on One Night...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jin, Xuanfa Wang, Ziyan Du, Yali Fang, Meng Zhang, Haifeng Wang, Jun Institute of Automation Chinese Academy of Sciences China Cooperative AI Lab Department of Informatics King's College London United Kingdom School of Artificial Intelligence University of Chinese Academy of Sciences China University of Liverpool United Kingdom Nanjing Artificial Intelligence Research of IA China AI Centre Department of Computer Science UCL United Kingdom

Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework. The project page of our paper: ***. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：