检索结果-内蒙古大学图书馆

Regression of Instance Boundary by Aggregated CNN and GCN 1

16th European Conference on computer Vision, ECCV 2020

作者： Meng, Yanda Meng, Wei Gao, Dongxu Zhao, Yitian Yang, Xiaoyun Huang, Xiaowei Zheng, Yalin Department of Eye and Vision Science Institute of Life Course and Medical Sciences University of Liverpool Liverpool United Kingdom Cixi Institute of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China China Science IntelliCloud Technology Co. Ltd. Shanghai China Department of Computer Science University of Liverpool Liverpool United Kingdom

ISBN: (数字)9783030585983

ISBN: (纸本)9783030585976

This paper proposes a straightforward, intuitive deep learning approach for (biomedical) image segmentation tasks. Different from the existing dense pixel classification methods, we develop a novel multi-level aggregation network to directly regress the coordinates of the boundary of instances in an end-to-end manner. The network seamlessly combines standard convolution neural network (CNN) with Attention Refinement Module (ARM) and Graph Convolution Network (GCN). By iteratively and hierarchically fusing the features across different layers of the CNN, our approach gains sufficient semantic information from the input image and pays special attention to the local boundaries with the help of ARM and GCN. In particular, thanks to the proposed aggregation GCN, our network benefits from direct feature learning of the instances’ boundary locations and the spatial information propagation across the image. Experiments on several challenging datasets demonstrate that our method achieves comparable results with state-of-the-art approaches but requires less inference time on the segmentation of fetal head in ultrasound images and of optic disc and optic cup in color fundus images. © 2020, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A quantum algorithm for minimum steiner tree problem

arXiv

引用

arXiv 2019年

作者： Miyamoto, Masayuki Iwamura, Masakazu Kise, Koichi Computer Science Course College of Engineering Osaka Prefecture University Department of Computer Science and Intelligent Systems Graduate School of Engineering Osaka Prefecture University

Minimum Steiner tree problem is a well-known NP-hard problem. For the minimum Steiner tree problem in graphs with n vertices and k terminals, there are many classical algorithms that take exponential time in k. In this paper, to the best of our knowledge, we propose the first quantum algorithm for the minimum Steiner tree problem. The complexity of our algorithm is O∗(1.812k). A key to realize the proposed method is how to reduce the computational time of dynamic programming by using a quantum algorithm because existing classical (non-quantum) algorithms in the problem rely on dynamic programming. Fortunately, dynamic programming is realized by a quantum algorithm for the travelling salesman problem, in which Grover's quantum search algorithm is introduced. However, due to difference between their problem and our problem to be solved, recursions are different. Hence, we cannot apply their technique to the minimum Steiner tree problem in that shape. We solve this issue by introducing a decomposition of a graph proposed by Fuchs et al. Copyright © 2019, The Authors. All rights reserved.

关键词： Quantum theory

来源：评论

学校读者我要写书评

暂无评论

Laboratory assignment problems with tie on students’ preferences

引用

Transactions of the Japanese Society for Artificial Intelligence 2019年第3期34卷

作者： Fujii, Tatsuki Itou, Yasunobu Nabesima, Hidetomo Computer Science and Engineering Course Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi Japan Sansei Computer System Co.Ltd. Japan Department of Research Interdisciplinary Graduate School of Medicine and Engineering University of Yamanashi Japan

We consider the laboratory assignment problem in which laboratories have minimum and maximum quotas. MSDA proposed by Fragiadakis, et al., is an efficient algorithm to solve the laboratory assignment problem, but it is incomplete to find a fair assignment. In this paper, we show three extensions of the laboratory assignment problem and translations from the extensions to constraint optimization problems. The first extension enables a completeness to find a fair assignment if it exists, but loses strategy-proofness. The original and first extended laboratory assignment problem may have no fair assignment. This is caused by redundant claims of an empty seat. The second extension based on the first one ensures that the laboratory assignment problem has at least one fair assignment by making a claim of an empty seat stricter. The third extension introduces tied ranks to students’ preferences over laboratories, for example, students can specify multiple laboratories as their first choice. This extension gives the flexibility to specify students’ preferences and makes it possible to find more desirable assignments. The experimental results show that our approaches requires more computational time compared with MSDA, but can always find a fair assignment and a more desirable one. © 2019, Japanese Society for Artificial Intelligence. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Phoneme Sequence Extraction of Learner’s Pronunciation Errors for Foreign Language Learning

Phoneme Sequence Extraction of Learner’s Pronunciation Erro...

引用

IEEE Pacific Rim Conference on Communications, computers and Signal Processing

作者： Kohei Kamimura Kosuke Takano Graduate School of Engineering Kanagawa Institute of Technology Course of Information and Computer Sciences Atsugi Kanagawa Japan Department of Information and Computer Sciences Kanagawa Institute of Technology Atsugi Kanagawa Japan

This paper presents a method for extracting phoneme sequences in foreign language pronunciation learning that a learner is likely to mispronounce. Some conventional methods show a learner's phoneme errors using speech recognition technology. Those systems simply show only one phoneme error that the learner makes; they show no analytical results of phoneme errors that arise from previous or later phoneme sequences. A feature of the proposed method is the ability to extract a phoneme that a learner is likely to mispronounce as an n-gram sequence rather than a single phoneme. We confirm the feasibility of our method with several experiments using a prototype of our learning system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in multimodal learning analytics: A systematic literature review

引用

computers and Education: Artificial Intelligence 2025年 8卷

作者： Mehrnoush Mohammadi Elham Tajik Roberto Martinez-Maldonado Shazia Sadiq Wojtek Tomaszewski Hassan Khosravi School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia Department of Educational Psychology and Learning Systems Florida State University Tallahassee USA Centre for Learning Analytics at Monash Faculty of Information Technology Monash University Melbourne Australia Australian Research Council Centre of Excellence for Children and Families Over the Life Course The University of Queensland Brisbane Australia Institute for Social Science Research The University of Queensland Brisbane Australia Institute for Teaching and Learning Innovation The University of Queensland Brisbane Australia

The proliferation of educational technologies has generated unprecedented volumes of diverse, multimodal learner data, offering rich insights into learning processes and outcomes. However, leveraging this complex, multimodal data requires advanced analytical methods. While Multimodal Learning Analytics (MMLA) offers promise for exploring this data, the potential of Artificial Intelligence (AI) to enhance MMLA remains largely unexplored. This paper bridges these two evolving domains by conducting the first systematic literature review at the intersection of AI and MMLA, analyzing 43 peer-reviewed papers from 11 reputable databases published between 2019 and 2024. The findings indicate a growing trend in AI-enhanced MMLA studies published predominantly in high-quality venues, led by education researchers with a predominant focus on tertiary education targeting diverse stakeholders. Guided by a novel conceptual framework, our analysis highlights the transformative role of AI across the MMLA process, particularly in model learning and feature engineering. However, it also uncovers significant gaps, including limited AI implementation in components requiring deep integration with learning theories, insufficient application of advanced AI techniques, and lack of large-scale studies in authentic learning environments. The review identifies key benefits, such as enhanced personalization and real-time feedback, while also addressing challenges related to ethical considerations, data integration, and scalability. Our study contributes by offering comprehensive recommendations for future research, emphasizing international collaboration, multi-level studies, and ethical AI implementation. These findings advance the theoretical understanding of AI's role in education, providing a foundation for developing sophisticated, interpretable, and scalable AI-enhanced MMLA approaches, potentially revolutionizing personalized learning across diverse educational settings.

关键词： AI Multimodal data Learning analytics Multimodal learning analytics Systematic review

来源：评论

学校读者我要写书评

暂无评论

P2PIoT: A Peer-To-Peer Communication Model for the Internet of Things

P2PIoT: A Peer-To-Peer Communication Model for the Internet ...

引用

Workshop on Communication Networks and Power Systems (WCNPS)

作者： Fabio L. L. de Mendonça Dayanne F. da Cunha Bruno J. G. Praciano Mateus da Rosa Zanatta Joao Paulo C. L. da Costa Rafael T. de Sousa University of Brasilia (UnB) Brasília Brazil Computer Engineering Course Educational Society Três de Maio Três de Maio RS Brazil

The following topics are dealt with: Internet of Things; power generation control; power transmission lines; power system simulation; protocols; power engineering computing; computer network security; optimisation; le...

关键词：

来源：评论

学校读者我要写书评

暂无评论

P120 The relationship between digital technology and sleep-wake behaviour in children aged 5-8 years

引用

Sleep Advances 2024年第SUPPLEMENT_1期5卷 A70–A70页

作者： Pattinson, C Edmed, S Rossa, K Mann, D MacKenzie, J de Waal, L Smith, S Child Health Research Centre The University of Queensland South Brisbane Australia The Australian Research Council Centre of Excellence for Children and Families over the Life Course The University of Queensland Brisbane Australia The Australian Research Council Centre of Excellence for the Digital Child The University of Queensland Brisbane Australia School of School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia The Australian Research Council Centre of Excellence for the Digital Child Queensland University of Technology Brisbane Australia Institute for Social Science Research The University of Queensland Indooroopilly Australia

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Virtual Machine Placement by Using Live Migration

An Evaluation of Virtual Machine Placement by Using Live Mig...

引用

International Conference on Information Technology (INCIT)

作者： Kunihiko Sakurai Hiroshi Sano Phonepadith Phoummavong Hiroshi Ishii Course of Information and Telecommunication Engineering Tokai University Tokyo Japan Dept. of Communication and Network Engineering Tokai University Tokyo Japan Dept. of Computer Engineering and Information Technology. National University of Laos Vientiane LAO

ISBN: (纸本)9781728110202

Virtualisation technology which can decrease the number of physical machines to use the resources effectively has become a research trend. Several methods of Live Migration (LM) for Virtual Machine (VM) Placement have been proposed. However, existing LM methods do not well take into account, such as transfer time and Random-Access Memory (RAM) usage of each VM. Considering this situation, we have already proposed a method of LM in case of “on-premise” system structure to balance the load of each physical server considering total RAM usage by VMs in a physical server and the bit transfer time proportional to Round-Trip Delay Time (RTT). Also, through a preliminary evaluation, we have shown that our method has a possibility to make the total processing time shorter. Based on this result, this paper revisits the proposal, evaluates it by giving additional conditions and shows its effectiveness.

关键词： Virtual machine Live migration Load balancing virtual machines Load balancing transfer time random access machine Voltmeter round-trip delay CCDC26 gene FAM103A1 gene

来源：评论

学校读者我要写书评

暂无评论

Single Image Super Resolution Based on Generative Adversarial Networks

Single Image Super Resolution Based on Generative Adversaria...

引用

2019第十一届数字图像处理国际会议

作者： Kai Li Ye Liang Shenghao Yang Jinfang Jia Jianqiang Huang Xiaoying Wang State Key Laboratory of Plateau Ecology and Agriculture Department of Computer Technology and ApplicationQinghai University Rocket Force University of Engineering Basic Course DepForeign language Office

Deep neural networks based on SRGAN single image super-resolution reconstruction can generate more realistic images than CNN-based super-resolution deep neural ***,when the network is deeper and more complex,unpleasant artifacts can *** a lot of experiments,we can use the ESRGAN model to avoid such *** using the ESRGAN model for super-resolution reconstruction,the perceived index of the resulting results does not reach a lower *** are two reasons for this:（1）ESRGAN does not expand the feature *** uses 128*128 to obtain the feature information of the image by default,and can’t get more image information better.（2） ESRGAN did not re-optimize the generated ***,we propose ESRGAN-Pro to optimize ESRGAN for the above two aspects,combined with a large amount of training data,and get a better perception index and texture.

关键词： Generative Adversarial Networks super resolution deep learning framework image processing

来源：评论

学校读者我要写书评

暂无评论

An anti-counterfeit complete RFID tag grouping proof generation protocol

引用

International Journal of Network Security 2019年第6期21卷 889-896页

作者： Shen, Gao-Feng Gu, Shu-Min Liu, Dao-Wei Department of Computer Science Zhengzhou University of Light Industry Zhengzhou450002 China Department of Basic Course College of Information and Business Zhongyuan University of Technology China Department of Computer Science and Engineering Guangzhou College of Technology and Business China

Most existing radio frequency identification group tags prove that the generation protocol does not meet the lightweight Gen-2 standard and there are existing security issues such as rapid brute-force cracking, proof forgery, and incomplete authentication. To tackle with these problems, an improved anti-counterfeit complete RFID tag grouping proof generation protocol was designed. The protocol adopted a one-way pseudo-random function that conformed to the low-cost Gen-2 standard as the basic encryption algorithm to implement complete tripartite authentication, label group proof generation and verification. The encryption authorization Mark identification was used by the database and the cipher-text transmission mechanism was ures to avoid multiple malicious attacks on the protocol. Finally, the feasibility of the protocol was approved by the GNY logic, and the security attack description indicated that the improved protocol met the security standards. Performance comparison analysis showed that the protocol was in line with low-cost applications. © 2019 Femto Technique Co., Ltd.

关键词： Radio frequency identification (RFID)

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：