检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Park, Juhyung Park, Dongwon Shin, Hyeong-Geol Choi, Eun-Jung An, Hongjun Kim, Minjun Shin, Dongmyung Chun, Se Young Lee, Jongho Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Electrical Engineering Ulsan National Institute of Science and Technology Ulsan Korea Republic of Department of Radiology Johns Hopkins University School of Medicine BaltimoreMD United States F.M. Kirby Research Center for Functional Brain Imaging Kennedy Krieger Institute BaltimoreMD United States AI Engineering Division RadiSen Co. Ltd. Seoul Korea Republic of

Denoising of magnetic resonance images is beneficial in improving the quality of low signal-to-noise ratio images. Recently, denoising using deep neural networks has demonstrated promising results. Most of these networks, however, utilize supervised learning, which requires large training images of noise-corrupted and clean image pairs. Obtaining training images, particularly clean images, is expensive and time-consuming. Hence, methods such as Noise2Noise (N2N) that require only pairs of noise-corrupted images have been developed to reduce the burden of obtaining training datasets. In this study, we propose a new self-supervised denoising method, Coil2Coil (C2C), that does not require the acquisition of clean images or paired noise-corrupted images for training. Instead, the method utilizes multichannel data from phased-array coils to generate training images. First, it divides and combines multichannel coil images into two images, one for input and the other for label. Then, they are processed to impose noise independence and sensitivity normalization such that they can be used for the training images of N2N. For inference, the method inputs a coil-combined image (e.g., DICOM image), enabling a wide application of the method. When evaluated using synthetic noise-added images, C2C shows the best performance against several self-supervised methods, reporting comparable outcomes to supervised methods. When testing the DICOM images, C2C successfully denoised real noise without showing structure-dependent residuals in the error maps. Because of the significant advantage of not requiring additional scans for clean or paired images, the method can be easily utilized for various clinical applications. © 2022, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split Federated Learning Scheme for Non-IID Data

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split...

引用

Cyber Security in Networking Conference (CSNet)

作者： Mohamad Arafeh Mohamad Wazzeh Hakima Ould-Slimane Chamseddine Talhi Azzam Mourad Hadi Otrok Department of Software and IT engineering Ecole de Technologie Superieure (ETS) Montreal Canada Department of Mathematics and Computer Science Universite de Quebec a Trois-Rivieres (UQTR) Canada Division of Science New York University Abu Dhabi UAE Department of CSM Cyber Security Systems and Applied AI Research Center Lebanese American University Beirut Lebanon Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE

This paper proposes a scheme addressing the challenges of integrating privacy-preserving distributed machine learning in the Internet of Things (IoT) context while improving the efficiency of the learning process and accelerating the convergence of the model. Specifically, it addresses the presence of non-independent and identically distributed (Non-IID) data and device heterogeneity, which occurs during parallel training and are common characteristics of IoT environments. In this context, SplitFed is a privacy-preserving technique that combines Federated Learning (FL) and Split Learning (SL) to enable fast and privacy-preserving model training on IoT devices. Through parallelism, FL allows fast and parallel model training. Furthermore, SL enables weak devices to train models through model splitting. However, SplitFed suffers from the increasing convergence time due to the FL parallelism introducing Non-IID and stragglers issues. In this paper, we aim to address the aforementioned problems by proposing a clustering parallelization scheme. As such, similar clients are combined based on their weight divergence and considered a single FL unit addressing the Non-IID problem. Moreover, to improve time efficiency and overcome the stragglers' presence, we offer a second clustering stage that separates clients by efficiency and uses FedAsync for model aggregation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What and When to Look?: Temporal Span Proposal Network for Video Relation Detection

arXiv

引用

arXiv 2021年

作者： Woo, Sangmin Noh, Junhyug Kim, Kangil The School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of The Computational Engineering Division Lawrence Livermore National Laboratory CA94550 United States The School of Electrical Engineering and Computer Science The AI Graduate School Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of

Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many constraints in the video domain due to challenging dynamics of spatio-temporal interactions (e.g., between which objects are there an interaction? when do relations start and end?). To date, two representative methods have been proposed to tackle Video Visual Relation Detection (VidVRD): segment-based and window-based. We first point out limitations of these methods and propose a novel approach named Temporal Span Proposal Network (TSPN). TSPN tells what to look: it sparsifies relation search space by scoring relationness of object pair, i.e., measuring how probable a relation exist. TSPN tells when to look: it simultaneously predicts start-end timestamps (i.e., temporal spans) and categories of the all possible relations by utilizing full video context. These two designs enable a win-win scenario: it accelerates training by 2× or more than existing methods and achieves competitive performance on two VidVRD benchmarks (ImageNet-VidVDR and VidOR). Moreover, comprehensive ablative experiments demonstrate the effectiveness of our approach. Codes are available at https://***/sangminwoo/ Temporal-Span-Proposal-Network-VidVRD. © 2021, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions

arXiv

引用

arXiv 2021年

In this work, we seek new insights into the underlying challenges of the Scene Graph Generation (SGG) task. Quantitative and qualitative analysis of the Visual Genome dataset implies - 1) Ambiguity: even if inter-object relationship contains the same object (or predicate), they may not be visually or semantically similar, 2) Asymmetry: despite the nature of the relationship that embodied the direction, it was not well addressed in previous studies, and 3) Higher-order contexts: leveraging the identities of certain graph elements can help to generate accurate scene graphs. Motivated by the analysis, we design a novel SGG framework, Local-to-Global Interaction Networks (LOGIN). Locally, interactions extract the essence between three instances of subject, object, and background, while baking direction awareness into the network by explicitly constraining the input order of subject and object. Globally, interactions encode the contexts between every graph component (i.e., nodes and edges). Finally, Attract & Repel loss is utilized to fine-tune the distribution of predicate embeddings. By design, our framework enables predicting the scene graph in a bottom-up manner, leveraging the possible complementariness. To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed. Experimental results demonstrate that LOGIN can successfully distinguish relational direction than existing methods (in BRC task), while showing state-of-the-art results on the Visual Genome benchmark (in SGG task). © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rapid Initial-State Preparation for the Quantum Simulation of Strongly Correlated Molecules

引用

PRX Quantum 2025年第2期6卷 020327-020327页

作者： Dominic W. Berry Yu Tong Tanuj Khattar Alec White Tae In Kim Guang Hao Low Sergio Boixo Zhiyan Ding Lin Lin Seunghoon Lee Garnet Kin-Lic Chan Ryan Babbush Nicholas C. Rubin School of Mathematical and Physical Sciences Macquarie University Sydney New South Wales 2109 Australia Institute of Quantum Information and Matter California Institute of Technology Pasadena California 91125 USA Department of Mathematics Duke University Durham North Carolina 27708 USA Department of Electrical and Computer Engineering Duke University Durham North Carolina 27708 USA Google Quantum AI Venice California 90291 USA Quantum Simulation Technologies Inc. Boston Massachusetts 02135 USA Department of Chemistry Seoul National University Seoul 08826 Republic of Korea Department of Mathematics University of California Berkeley California 94720 USA Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California 91125 USA

Studies on quantum algorithms for ground-state energy estimation often assume perfect ground-state preparation; however, in reality the initial state will have imperfect overlap with the true ground state. Here, we address that problem in two ways: by faster preparation of matrix-product-state (MPS) approximations and by more efficient filtering of the prepared state to find the ground-state energy. We show how to achieve unitary synthesis with a Toffoli complexity about 7× lower than that in prior work and use that to derive a more efficient MPS-preparation method. For filtering, we present two different approaches: sampling and binary search. For both, we use the theory of window functions to avoid large phase errors and minimize the complexity. We find that the binary-search approach provides better scaling with the overlap at the cost of a larger constant factor, such that it will be preferred for overlaps less than about 0.003. Finally, we estimate the total resources to perform ground-state energy estimation of Fe-S cluster systems, including the FeMo cofactor by estimating the overlap of different MPS initial states with potential ground states of the FeMo cofactor using an extrapolation procedure. With a modest MPS bond dimension of 4000, our procedure produces an estimate of approximately 0.9 overlap squared with a candidate ground state of the FeMo cofactor, producing a total resource estimate of 7.3×1010 Toffoli gates; neglecting the search over candidates and assuming the accuracy of the extrapolation, this validates prior estimates that have used perfect ground-state overlap. This presents an example of a practical path to prepare states of high overlap in a challenging-to-compute chemical system.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Rapid initial state preparation for the quantum simulation of strongly correlated molecules

arXiv

引用

arXiv 2024年

作者： Berry, Dominic W. Tong, Yu Khattar, Tanuj White, Alec Kim, Tae In Boixo, Sergio Lin, Lin Lee, Seunghoon Chan, Garnet Kin-Lic Babbush, Ryan Rubin, Nicholas C. School of Mathematical and Physical Sciences Macquarie University SydneyNSW2109 Australia Institute of Quantum Information and Matter California Institute of Technology PasadenaCA91125 United States Department of Mathematics Duke University DurhamNC27708 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Google Quantum AI VeniceCA90291 United States Department of Chemistry Seoul National University Seoul08826 Korea Republic of Department of Mathematics University of California BerkeleyCA94720 United States Division of Chemistry and Chemical Engineering California Institute of Technology PasadenaCA91125 United States

Studies on quantum algorithms for ground state energy estimation often assume perfect ground state preparation;however, in reality the initial state will have imperfect overlap with the true ground state. Here we address that problem in two ways: by faster preparation of matrix product state (MPS) approximations, and more efficient filtering of the prepared state to find the ground state energy. We show how to achieve unitary synthesis with a Toffoli complexity about 7× lower than that in prior work, and use that to derive a more efficient MPS preparation method. For filtering we present two different approaches: sampling and binary search. For both we use the theory of window functions to avoid large phase errors and minimise the complexity. We find that the binary search approach provides better scaling with the overlap at the cost of a larger constant factor, such that it will be preferred for overlaps less than about 0.003. Finally, we estimate the total resources to perform ground state energy estimation of Fe-S cluster systems, including the FeMo cofactor by estimating the overlap of different MPS initial states with potential ground-states of the FeMo cofactor using an extrapolation procedure. With a modest MPS bond dimension of 4000, our procedure produces an estimate of ∼ 0.9 overlap squared with a candidate ground-state of the FeMo cofactor, producing a total resource estimate of 7.3×1010 Toffoli gates;neglecting the search over candidates and assuming the accuracy of the extrapolation, this validates prior estimates that used perfect ground state overlap. This presents an example of a practical path to prepare states of high overlap in a challenging-to-compute chemical system. Copyright © 2024, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Measuring poverty in India with machine learning and remote sensing

arXiv

引用

arXiv 2021年

作者： Daoud, Adel Jordan, Felipe Sharma, Makkunda Johansson, Fredrik Dubhashi, Devdatt Paul, Sourabh Banerjee, Subhashis Institute for Analytical Sociology Department of Management and Engineering Linköping University Norrköping Sweden The Division of Data Science and Artificial Intelligence The Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden UC Santa Barbara Santa BarbaraCA United States Wadhwani AI Computer Science Indian Institute of Technology Delhi India Humanities & Social Sciences Indian Institute of Technology Delhi India Computer Science and Engineering Indian Institute of Technology Delhi India

In this paper, we use deep learning to estimate living conditions in India. We use both census and surveys to train the models. Our procedure achieves comparable results to those found in the literature, but for a wid... 详细信息

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions

arXiv

引用

arXiv 2023年

作者： Sami, H. Hammoud, A. Arafeh, M. Wazzeh, M. Arisdakessian, S. Chahoud, M. Wehbi, O. Ajaj, M. Mourad, A. Otrok, H. Abdel Wahab, O. Mizouni, R. Bentahar, J. Talhi, C. Dziong, Z. Damiani, E. Guizani, M. Concordia Institute for Information Systems Engineering Concordia University MontréalQC Canada Department of Electrical Engineering École de Technologie Supérieure Montréal Canada Department of Software and IT engineering École de Technologie Supérieure Montréal Canada Department of Computer and Software Engineering Polytechnique Montréal Montreal Canada Cyber Security Systems and Applied AI Research Center Department of CSM Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi United Arab Emirates Department of EECS Khalifa University Abu Dhabi United Arab Emirates Department of ML Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

The Metaverse offers a second world beyond reality, where boundaries are non-existent, and possibilities are endless through engagement and immersive experiences using the virtual reality (VR) technology. Many disciplines can benefit from the advancement of the Metaverse when accurately developed, including the fields of technology, gaming, education, art & culture, socialization, commerce, and businesses. Nevertheless, developing the Metaverse environment to its full potential is an ambiguous task that needs proper guidance and directions. Existing surveys on the Metaverse focus only on a specific aspect and discipline of the Metaverse and lack a holistic view of the entire process. Moreover, most surveys refrain from providing detailed guidance about the development process of the metaverse, including its impact on technologies, businesses, existing challenges, and potential research directions due to their lack of a macro and micro perception of such a topic. To this end, a more holistic, multi-disciplinary, in-depth, and academic and industry-oriented review is required to provide a thorough study of the Metaverse development pipeline and fill the gap in existing Metaverse surveys. To address these issues, we present in this survey a novel multi-layered pipeline ecosystem composed of (1) the Metaverse computing, networking, communications and hardware infrastructure, (2) environment digitization, and (3) user interactions. For every layer, we discuss the components that detail the steps of its development. Also, for each of these components, we examine the impact of a set of enabling technologies and empowering domains (e.g., Artificial Intelligence, Security & Privacy, Blockchain, Business, Ethics, and Social) on its advancement. In addition, we explain the importance of these technologies to support decentralization, interoperability, user experiences, interactions, and monetization. Our presented study highlights the existing challenges for each component, fo

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Correction to: Pose pattern mining using transformer for motion classification

引用

Applied Intelligence 2024年第22期54卷 12036-12036页

作者： Lee, Seo-El Yoo, Hyun Chung, Kyungyong Department of Public Safety Bigdata Kyonggi University Suwon-si South Korea Contents Convergence Software Research Institute Kyonggi University Suwon-si South Korea Division of AI Computer Science and Engineering Kyonggi University Suwon-si South Korea

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach Towards Data optimization for Cloud Based IoT Environment

A Hybrid Approach Towards Data optimization for Cloud Based ...

引用

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Souvik Pal N. Z. Jhanjhi D. Akila Monir Abdullah Memona Humayun Sandeep Kumar Rahul Kumar Dept. of Management IS Saveetha College of Liberal Arts & Sciences Saveetha Institute of Medical & Tech. Sciences Chennai India Dept. of CS and Engineering Sister Nivedita University Kolkata India School of Computer Science SCS Taylor's University Subang Jaya Malaysia Dept. of Computer Applications Saveetha College of Liberal Arts & Sciences SIMATS Deemed University hennai India Department of CS and AI College of Computing & IT University of Bisha Bisha Saudi Arabia Department of Computing School of Arts Humanities & Social Sciences University of Roehampton London United Kingdom Division of Research and Development Lovely Professional University Phagwara-144411 India KKR and KSR Institute of Technology and Sciences Guntur Andhra Pradesh India

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

An innovative method for data optimization in the Internet of Things (IoT) assister sensing devices is presented in this research. The many elements of the cloud platform with IoT assistance are addressed. A fresh design for IoT-aided sensor networks is introduced to monitor the environment. A Data Optimisation in Cloud Internet of Things (DO-CIoT) is proposed in this paper to optimize the data stored in the cloud and presents methods to access the data in end devices. The suggested technique uses a membership function to improve data allocation while considering all node data. The suggested model is assessed regarding performance ratios, reliability percentage, coverage ratios, and sensing error and contrasted with two-stage efficiency enhancement. A mean performance ratio of 89%, reliability of 91%, coverage of 89

关键词： Performance evaluation Cloud computing computer network reliability Market research Sensors Internet of Things Reliability Resource management Optimization Monitoring

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：