检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yan, Yuping Shao, George Song, Dennis Song, Mason Jin, Yaochu Trustworthy and General AI Lab School of Engineering Westlake University Hangzhou310024 China Mind Network Singapore Faculty of Informatics Department of Computeralgebra Budapest1117 Hungary Ethereum Foundation Zug Switzerland Department of Computer Science University of Surrey Surry GuildfordGU2 7XH United Kingdom

Blockchain transactions have gained widespread adoption across various industries, largely attributable to their unparalleled transparency and robust security features. Nevertheless, this technique introduces various privacy concerns, including pseudonymity, Sybil attacks, and potential susceptibilities to quantum computing, to name a few. In response to these challenges, innovative privacy-enhancing solutions like zero-knowledge proofs, homomorphic encryption, and stealth addresses (SA) have been developed. Among the various schemes, SA stands out as it prevents the association of a blockchain transaction's output with the recipient's public address, thereby ensuring transactional anonymity. However, the basic SA schemes have exhibited vulnerabilities to key leakage and quantum computing attacks. To address these shortcomings, we present a pioneering solution ' Homomorphic Encryption-based Dual-Key Stealth Address Protocol (HE-DKSAP), which can be further extended to Fully HE-DKSAP (FHE-DKSAP). By leveraging the power of homomorphic encryption, HE-DKSAP introduces a novel approach to safeguarding transaction privacy and preventing potential quantum computing attacks. This paper delves into the core principles of HE-DKSAP, highlighting its capacity to enhance privacy, scalability, and security in programmable blockchains. Through a comprehensive exploration of its design architecture, security analysis, and practical implementations, this work establishes a privacy-preserving, practical, and efficient stealth address protocol via additively homomorphic encryption. © 2023, CC BY.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

MGN-Net: A multi-view graph normalizer for integrating heterogeneous biological network populations

arXiv

引用

arXiv 2021年

作者： Gürbüz, Mustafa Burak Rekik, Islem BASIRA lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom

With the recent technological advances, biological datasets, often represented by networks (i.e., graphs) of interacting entities, proliferate with unprecedented complexity and heterogeneity. Although modern network science opens new frontiers of analyzing connectivity patterns in such datasets, we still lack data-driven methods for extracting an integral connectional fingerprint of a multi-view graph population, let alone disentangling the typical from the atypical variations across the population samples. We present the multi-view graph normalizer network (MGN-Net1), a graph neural network based method to normalize and integrate a set of multi-view biological networks into a single connectional template that is centered, representative, and topologically sound. We demonstrate the use of MGN-Net by discovering the connectional fingerprints of healthy and neurologically disordered brain network populations including Alzheimer's disease and Autism spectrum disorder patients. Additionally, by comparing the learned templates of healthy and disordered populations, we show that MGN-Net significantly outperforms conventional network integration methods across extensive experiments in terms of producing the most centered templates, recapitulating unique traits of populations, and preserving the complex topology of biological networks. Our evaluations showed that MGN-Net is powerfully generic and easily adaptable in design to different graph-based problems such as identification of relevant connections, normalization and integration. © 2021, CC BY-NC-SA.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Brain graph super-resolution using adversarial graph neural network with application to functional brain connectivity

arXiv

引用

arXiv 2021年

作者： Isallari, Megi Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom

Brain image analysis has advanced substantially in recent years with the proliferation of neuroimaging datasets acquired at different resolutions. While research on brain image super-resolution has undergone a rapid development in the recent years, brain graph super-resolution is still poorly investigated because of the complex nature of non-Euclidean graph data. In this paper, we propose the first-ever deep graph super-resolution (GSR) framework that attempts to automatically generate high-resolution (HR) brain graphs with N0 nodes (i.e., anatomical regions of interest (ROIs)) from low-resolution (LR) graphs with N nodes where N 0. First, we formalize our GSR problem as a node feature embedding learning task. Once the HR nodes' embeddings are learned, the pairwise connectivity strength between brain ROIs can be derived through an aggregation rule based on a novel Graph U-Net architecture. While typically the Graph U-Net is a node-focused architecture where graph embedding depends mainly on node attributes, we propose a graph-focused architecture where the node feature embedding is based on the graph topology. Second, inspired by graph spectral theory, we break the symmetry of the U-Net architecture by super-resolving the low-resolution brain graph structure and node content with a GSR layer and two graph convolutional network layers to further learn the node embeddings in the HR graph. Third, to handle the domain shift between the ground-truth and the predicted HR brain graphs, we incorporate adversarial regularization to align their respective distributions. Our proposed AGSR-Net framework outperformed its variants for predicting high-resolution functional brain graphs from low-resolution ones. Our AGSR-Net code is available on GitHub at https://***/basiralab/AGSR-Net. © 2021, CC BY-NC-SA.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Generic Drone Simulator: Design, Development and User Testing in a Virtual Search and Rescue Mission

引用

IEEE computer Graphics and Applications 2025年 PP卷 PP页

作者： Pappas, Georgios Lappas, Dimitrios Karampelas, Panagiotis Siegel, Joshua E. Templalexis, Ioannis Stavrou, Stavros Krishnan, Sriram Open University of Cyprus Lab of Educational Material and Methodology Latsia Nicosia Cyprus University of the Aegean Learning Technology and Educational Engineering Laboratory Rhodes Greece Hellenic Air Force Academy Department of Informatics & Computers Dekelia Attiki Greece Michigan State University Department of Computer Science and Engineering East LansingMI United States Hellenic Air Force Academy Department of Thermodynamics Propulsion and Power Systems Dekelia Attiki Greece Open University of Cyprus Cybersecurity and Telecommunications Research Lab Latsia Nicosia Cyprus Indian Institute of Technology The Energy Consortium Madras India

This study addresses the need for scenario-specific drone simulators to enhance research, education, pilot training, and performance evaluation across diverse mission contexts. A gamified simulator was developed for the joint master's degree program "Security and Defence" between the Open University of Cyprus (OUC) and the Hellenic Air Force Academy (HAFA), with a focus on Search and Rescue mission training and planning. The simulator balances interface design, physics accuracy, and environmental realism to support specialized professional training and research. A survey-based evaluation involving 57 participants –pilots, engineers, and air traffic controllers –demonstrated the tool's ability to provide realistic experiences for trained pilots and meaningful learning opportunities for novices. Statistical analysis revealed significant correlations between gaming familiarity, task completion times, and participant expertise. © 1981-2012 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Discriminative Radial Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Huang, Zenan Wen, Jun Chen, Siheng Zhu, Linchao Zheng, Nenggan The Qiushi Academy for Advanced Studies Zhejiang University Zhejiang Hangzhou310007 China The College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310007 China The Department of Biomedical Informatics Harvard Medical School BostonMA02115 United States Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China Shanghai AI Laboratory Shanghai200240 China College of Computer Science and Technology Zhejiang University Hangzhou China and Zhejiang Lab Zhejiang Hangzhou311121 China

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability. In this paper, we propose Discriminative Radial Domain Adaptation (DRDA) which bridges source and target domains via a shared radial structure. It’s motivated by the observation that as the model is trained to be progressively discriminative, features of different categories expand outwards in different directions, forming a radial structure. We show that transferring such an inherently discriminative structure would enable to enhance feature transferability and discriminability simultaneously. Specifically, we represent each domain with a global anchor and each category a local anchor to form a radial structure and reduce domain shift via structure matching. It consists of two parts, namely isometric transformation to align the structure globally and local refinement to match each category. To enhance the discriminability of the structure, we further encourage samples to cluster close to the corresponding local anchors based on optimal-transport assignment. Extensively experimenting on multiple benchmarks, our method is shown to consistently outperforms state-of-the-art approaches on varied tasks, including the typical unsupervised domain adaptation, multi-source domain adaptation, domain-agnostic learning, and domain generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Real Time Sound Source Localization Using von-Mises ResNet

Real Time Sound Source Localization Using von-Mises ResNet

引用

IEEE/SICE International Symposium on System Integration

作者： Mert Bozkurtlar Benjamin Yen Katsutoshi Itoyama Kazuhiro Nakadai Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Department of Industrial Engineering Faculty of Management Istanbul Technical University Harbiye Maçka/Beşiktaş/İstanbul Türkiye Department of Computer Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Ayazaga Sariyer/İstanbul Türkiye Japan Society for the Promotion of Science (JSPS) at the Nakadai Lab Tokyo Institute of Technology Honda Research Institute Japan Co. Ltd Saitama Japan

This paper addresses the task of learning periodic information using deep neural networks to achieve real-time, environment-independent sound source localization. Previous papers showed phase data is the most significant cue in sound source localization tasks and the proposed vM-B DNN was validated to be able to handle such periodic information using on synthesized data. However, they haven't shown its effectiveness and robustness in realistic use cases. This paper introduces a more complex model based on residual networks and adapts vM-B activation function for convolutional layers for use cases that require real-time predictions in dynamically changing environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

Automatic detection of lung nodule in CT scan slices using C...

引用

2022 International Conference on Machine Learning and Data Engineering, ICMLDE 2022

作者： Kadry, Seifedine Herrera-Viedma, Enrique Crespo, Rubén González Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Andalusian Granada Spain Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases;(i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods. © 2023 The Authors. Published by Elsevier B.V.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

Deep and handcrafted feature supported diabetic retinopathy ...

引用

2022 International Conference on Machine Learning and Data Engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes;(i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database. © 2022 Elsevier B.V.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MESD: Exploring optical flow assessment on edge of motion objects with motion edge structure difference

arXiv

引用

arXiv 2021年

作者： Liao, Bin Hu, Jinlong College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

The optical flow estimation has been assessed in various applications. In this paper, we propose a novel method named motion edge structure difference(MESD) to assess estimation errors of optical flow fields on edge of motion objects. We implement comparison experiments for MESD by evaluating five representative optical flow algorithms on four popular benchmarks: MPI Sintel, Middlebury, KITTI 2012 and KITTI 2015. Our experimental results demonstrate that MESD can reasonably and discriminatively assess estimation errors of optical flow fields on motion edge. The results indicate that MESD could be a supplementary metric to existing general assessment metrics for evaluating optical flow algorithms in related computer vision applications. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Real Waiting Time in Single-Server Resource Queue with Markovian Arrival Process 21st

引用

21st International Conference on Information Technologies and Mathematical Modelling. Queueing Theory and Applications, ITMM 2022

作者： Nazarov, Anatoly Moiseev, Alexander Lapatin, Ivan Paul, Svetlana Lizyura, Olga Pristupa, Pavel Peng, Xi Chen, Li Bai, Bo Institute of Applied Mathematics and Computer Science National Research Tomsk State University 36 Lenina Avenue Tomsk634050 Russia Theory Lab Central Research Center 2012Labs Huawei Tech. Investment Co. Ltd. 8/F Bio-informatics Center No. 2 Science Park West Avenue Hong Kong Science Park Pak Shek Kok Shatin N.T. Hong Kong

ISBN: (纸本)9783031329890

We consider single-server queue, which models a telecommunication node. Packets arrive in the system according to the Markovian arrival process (MAP). The packets bring some amount of information, which is stored in a continuous-type unlimited buffer before it will be transmitted out of the system. We consider the system with fluid manner of service, which means that the server takes the information from the buffer with constant speed. Our aim is to derive the probability distribution of the real waiting time in the system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Probability distributions

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：