检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sevastopoulos, Christos Konstantopoulos, Stasinos Department of Computer Science and Computer Engineering University of Texas at Arlington ArlingtonTX United States Institute of Informatics and Telecommunications NCSR Demokritos Agia Paraskevi Greece

Traversability illustrates the difficulty of driving through a specific region and encompasses the suitability of the terrain for traverse based on its physical properties, such as slope and roughness, surface condition, etc. In this survey we highlight the merits and limitations of all the major steps in the evolution of traversability estimation techniques, covering both non-trainable and machine-learning methods, leading up to the recent proliferation of deep learning literature. We discuss how the nascence of Deep Learning has created an opportunity for radical improvement in traversability estimation. Finally, we discuss how self- supervised learning can help satisfy deep methods' increased need for (challenging to acquire and label) large-scale datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

UMS: Live Migration of Containerized Services across Autonomous Computing Systems

arXiv

引用

arXiv 2023年

作者： Chanikaphon, Thanawat Salehi, Mohsen Amini HPCC Lab School of Computing and Informatics University of Louisiana LafayetteLA United States HPCC Lab Computer Science and Engineering Department University of North Texas United States

Containerized services deployed within various computing systems, such as edge and cloud, desire live migration support to enable user mobility, elasticity, and load balancing. To enable such a ubiquitous and efficient service migration, a live migration solution needs to handle circumstances where users have various authority levels (full control, limited control, or no control) over the underlying computing systems. Supporting the live migration at these levels serves as the cornerstone of interoperability, and can unlock several use cases across various forms of distributed systems. As such, in this study, we develop a ubiquitous migration solution (called UMS) that, for a given containerized service, can automatically identify the feasible migration approach, and then seamlessly perform the migration across autonomous computing systems. UMS does not interfere with the way the orchestrator handles containers and can coordinate the migration without the orchestrator involvement. Moreover, UMS is orchestrator-agnostic, i.e., it can be plugged into any underlying orchestrator platform. UMS is equipped with novel methods that can coordinate and perform the live migration at the orchestrator, container, and service levels. Experimental results show that for single-process containers, the service-level approach, and for multi-process containers with small ( Copyright © 2023, The Authors. All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Solving the influence maximization problem by using entropy and weight of edges 12

Solving the influence maximization problem by using entropy ...

引用

12th International Conference on computer and Knowledge engineering, ICCKE 2022

作者： Kazemzadeh, Farzaneh Karian, Amir Mirzarezaee, Mitra Safaei, Ali Asghar Islamic Azad University Department of Computer Engineering Science and Research Branch Tehran Iran Islamic Azad University Central Tehran Branch Department of Industrial Design Iran Tarbiat Modares University Faculty of Medical Sciences Department of Medical Informatics Tehran Iran

ISBN: (数字)9781665476133

ISBN: (纸本)9781665476133

The Problem of Maximizing diffusion was raised to find the number of K nodes as a subset of all social network nodes. Many other social network nodes can be activated to get information by obtaining the right nodes in this set. Solving this problem optimally will improve and increase marketing and widely transfer any information on social networks. Although many studies have investigated this issue, there are a few studies on this algorithm for providing an optimal solution. Moreover, less attention has been paid to the difference between edges and their weights in society. Therefore, this study set a score appropriate to the conditions of each node according to the topological criteria and entropy, the level of communication, and the degree of neighbors around nodes. Then, K seeds with the highest influence was carefully identified according to the scores and their measurement. © 2022 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Indoors Traversability Estimation with Less Labels for Mobile Robots

Indoors Traversability Estimation with Less Labels for Mobil...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Christos Sevastopoulos Michail Theofanidis Mohammad Zaki Zadeh Sneh Acharya Stasinos Konstantopoulos Vangelis Karkaletsis Fillia Makedon Department of Computer Science & Computer Engineering University of Texas at Arlington Arlington TX USA NCSR “Demokritos” Institute of Informatics and Telecommunications Agia Paraskevi Attica Greece

ISBN: (纸本)9781665472616

We present a method for binary (go/no-go) indoors traversability estimation from 2D images. Our method exploits the power of a pre-trained Vision Transformer (ViT) which we fine-tune on our own dataset. We conduct experiments using a mobile robotic platform to gather image data. Our fine-tuning approach includes the use of a pre-trained Vision Transformer (ViT) en route towards developing a semi-supervised deep learning technique to enhance indoor traversability estimation for scenarios where only a small amount of data is available. We evaluate the accuracy and generalization power of our method against well-established state-of-the-art deep architectures for image classification such as ResNet, and show improved performance.

关键词： Deep learning Navigation Lasers Estimation Transformers Mobile robots Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-label transfer learning for identifying lung diseases using chest X-rays 2

Multi-label transfer learning for identifying lung diseases ...

引用

2nd IEEE International Conference on Electronic engineering, ICEEM 2021

作者： El-Fiky, Azza Shouman, Marwa Ahmed Hamada, Salwa El-Sayed, Ayman Karar, Mohamed Esmail Electronics Research Institute Department of Informatics Cairo Egypt Menoufia University Faculty of Electronic Engineering Department of Computer Science and Engineering Minuf Egypt Menoufia University Faculty of Electronic Engineering Dept. Industrial Electronics and Control Engineering Minuf Egypt

ISBN: (纸本)9781665418423

Chest radiography presents one of the main medical imaging modalities for diagnosing lung diseases. To assist radiologists during interventional procedures, this paper aims at proposing a transfer learning-based classifier to automatically identify 14 different thoracic diseases in Chest X-ray (CXR) images. The proposed method is relied on deep residual neural networks with 50 layers (ResNet-50) to accomplish the diagnostic task of many chest diseases. In this study, a public dataset of 112, 120 frontal radiograph images for Chest X-ray has been used for validating the proposed deep learning classifier. It achieved the best performance of multi-label classification of normal and 14 different lung diseases with an average area under curve (AUC) of 0.911 and F1-score of 0.66. This study demonstrated that the proposed ResNet-50 classifier as a transfer learning model outperforms other relevant methods in the previous studies for automatic multi-label classification of chest X-rays. © 2021 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

DREAM: Domain Invariant and Contrastive Representation for Sleep Dynamics

DREAM: Domain Invariant and Contrastive Representation for S...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Seungyeon Lee Thai-Hoang Pham Ping Zhang Department of Computer Science and Engineering The Ohio State University USA Department of Biomedical Informatics The Ohio State University USA

Sleep staging is a key challenge in diagnosing and treating sleep-related diseases due to its labor-intensive, time-consuming, costly, and error-prone. With the availability of large-scale sleep signal data, many deep learning methods are proposed for automatic sleep staging. However, these existing methods face several challenges including the heterogeneity of patients’ underlying health conditions and the difficulty modeling complex interactions between sleep stages. In this paper, we propose a neural network architecture named DREAM to tackle these issues for automatic sleep staging. DREAM consists of (i) a feature representation network that generates robust representations for sleep signals via the variational auto-encoder framework and contrastive learning and (ii) a sleep stage classification network that explicitly models the interactions between sleep stages in the sequential context at both feature representation and label classification levels via Transformer and conditional random field architectures. Our experimental results indicate that DREAM significantly outperforms existing methods for automatic sleep staging on three sleep signal datasets.

关键词： Training Analytical models Sleep Neural networks Predictive models Brain modeling Transformers

来源：评论

学校读者我要写书评

暂无评论

A New, Reconfigurable Circuit Offering Functionality of AND and OR Logic Gates for Use in Algorithms Implemented in Hardware 33

A New, Reconfigurable Circuit Offering Functionality of AND ...

引用

33rd IEEE International Conference on Microelectronics, MIEL 2023

作者： Talaska, Tomasz Dlugosz, Rafal Nikolic, Tatjana Nikolic, Goran Stefanski, Tomasz Dlugosz, Michal Talaska, Michal Bydgoszcz University of Science and Technology Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz85-796 Poland Aptiv Services Poland Kraków30-399 Poland University of Niš Faculty of Electronic Engineering Niš18000 Serbia Gdanśk Univeristy of Technology Faculty of Electronics Telecommunications and Informatics Gdanśk80-233 Poland Poznan University of Technology Faculty of Control Robotics and Electrical Engineering Poznan60-965 Poland Complex of Electronics Schools Bydgoszcz85-092 Poland

ISBN: (纸本)9798350347760

The paper presents a programmable (using a 1-bit signal) digital gate that can operate in one of two OR or AND modes. A circuit of this type can also be implemented using conventional logic gates. However, in the case of the proposed circuit, compared to conventional solutions, the advantage is a much smaller number of transistors necessary for its implementation. Circuit is also much faster than its conventional counterpart. The logic gate was implemented in the 180nm CMOS technology and verified using Hspice simulations. There are many possible applications for this gate, mostly in artificial intelligence and pattern recognition algorithms implemented at the transistor level. © 2023 IEEE.

关键词： Logic gates

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Super-Resolution and Denoising on MRI via Conditional Stochastic Normalizing Flow

Simultaneous Super-Resolution and Denoising on MRI via Condi...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Zhenhong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences The Department of Computer Science School of Engineering The University of Manchester United Kingdom Department of Cardiovascular Sciences The Department of Electrical Engineering Ku Leuven Leuven Belgium Lan Turing Institute London United Kingdom

ISBN: (纸本)9798350337488

Magnetic resonance imaging (MRI) scans often suffer from noise and low-resolution (LR), which affect the diagnosis and treatment results obtained for patients. LR images and noise come together with MRI, and the existing methods solve image super-resolution (SR) reconstruction and denoising tasks in a step-by-step manner, which influences the overall real distribution of the MRI data. In this paper, we present a simultaneous SR and denoising algorithm based on a stochastic normalizing flow (SNF), named the MR image SR and denoising model based on an SNF (SRDSNF). SRDSNF adds the encoded information of the input image as the conditional information to each reverse step of the stochastic normalizing flow, which realizes a consistent description of the spatial distribution between the reconstruction result and the input image. We introduce rangenull space decomposition and subsequence sampling strategies to enhance the consistency of the input and output data and increase the generation speed of the model. Simultaneous SR and denoising tasks experiment is carried out using the BrainWeb and NFBS datasets. The experimental results show that good SR and denoising results are obtained with fewer sampling steps, these results are consistent with the ground truths, and the structural similarity and peak signal-to-noise ratio of the results are also higher than those of the comparison methods. The proposed method demonstrates potential clinical promise. © 2023 IEEE.

关键词： Denoising Diffusion model MR image Stochastic normalizing flow Super-resolution

来源：评论

学校读者我要写书评

暂无评论

DRASCLR: A SELF-SUPERVISED FRAMEWORK OF LEARNING DISEASE-RELATED AND ANATOMY-SPECIFIC REPRESENTATION FOR 3D MEDICAL IMAGES

arXiv

引用

arXiv 2023年

作者： Yu, Ke Sun, Li Chen, Junxiang Reynolds, Max Chaudhary, Tigmanshu Batmanghelich, Kayhan School of Computing and Information University of Pittsburgh United States Department of Electrical and Computer Engineering Boston University United States Department of Biomedical Informatics University of Pittsburgh United States

Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only uses unlabeled data. Recently, SSL methods based on instance discrimination have gained popularity in the medical imaging domain. However, SSL pre-trained encoders may use many clues in the image to discriminate an instance that are not necessarily disease-related. Moreover, pathological patterns are often subtle and heterogeneous, requiring the ability of the desired method to represent anatomy-specific features that are sensitive to abnormal changes in different body parts. In this work, we present a novel SSL framework, named DrasCLR, for 3D medical imaging to overcome these challenges. We propose two domain-specific contrastive learning strategies: one aims to capture subtle disease patterns inside a local anatomical region, and the other aims to represent severe disease patterns that span larger regions. We formulate the encoder using conditional hyper-parameterized network, in which the parameters are dependant on the anatomical location, to extract anatomically sensitive features. Extensive experiments on large-scale computer tomography (CT) datasets of lung images show that our method improves the performance of many downstream prediction and segmentation tasks. The patient-level representation improves the performance of the patient survival prediction task. We show how our method can detect emphysema subtypes via dense prediction. We demonstrate that fine-tuning the pre-trained model can significantly reduce annotation efforts without sacrificing emphysema detection accuracy. Our ablation study highlights the importance of incorporating anatomical context into the SSL framework. © 2023, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification

arXiv

引用

arXiv 2023年

作者： Song, Youngjae Shyn, Sung Kuk Kim, Kwang-Su Department of Computer Science and Engineering Sungkyunkwan University Korea Republic of Department of Artificial Intelligence Sungkyunkwan University Korea Republic of Department of Computing and Informatics Sungkyunkwan University Korea Republic of

Traditional tabular classifiers provide explainable decision-making with interpretable features(concepts). However, using their explainability in vision tasks has been limited due to the pixel representation of images. In this paper, we design Img2Tabs that classify images by concepts to harness the explainability of tabular classifiers. Img2Tabs encode image pixels into tabular features by StyleGAN inversion. Since not all of the resulting features are class-relevant or interpretable due to their generative nature, we expect Img2Tab classifiers to discover class-relevant concepts automatically from the StyleGAN features. Thus, we propose a novel method using the Wasserstein-1 metric to quantify class-relevancy and interpretability simultaneously. Using this method, we investigate whether important features extracted by tabular classifiers are class-relevant concepts. Consequently, we determine the most effective classifier for Img2Tabs in terms of discovering class-relevant concepts automatically from StyleGAN features. In evaluations, we demonstrate concept-based explanations through importance and visualization. Img2Tab achieves top-1 accuracy that is on par with CNN classifiers and deep feature learning baselines. Additionally, we show that users can easily debug Img2Tab classifiers at the concept level to ensure unbiased and fair decision-making without sacrificing accuracy. © 2023, CC BY.

关键词： Decision making

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：