检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Bae, Sang Won Banerjee, Sandip Baral, Arpita Mahapatra, Priya Ranjan Sinha Yoon, Sang Duk Division of Computer Science and Engineering Kyonggi University Korea Republic of Institute of Informatics University of Wroclaw Poland Durgapur India Department of Computer Science and Engineering University of Kalyani India Department of Service and Design Engineering Sungshin Women's University Korea Republic of

Given a set of n colored points with k colors in the plane, we study the problem of computing a maximum-width rainbow-bisecting empty annulus (of objects specifically axis-parallel square, axis-parallel rectangle and circle) problem. We call a region rainbow if it contains at least one point of each color. The maximum-width rainbow-bisecting empty annulus problem asks to find an annulus A of a particular shape with maximum possible width such that A does not contain any input points and it bisects the input point set into two parts, each of which is a rainbow. We compute a maximum-width rainbow-bisecting empty axis-parallel square, axis-parallel rectangular and circular annulus in O(n3) time using O(n) space, in O(k2n2 log n) time using O(n log n) space and in O(n3) time using O(n2) space respectively. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach to Predict Alzheimer's Disease through Magnetic Resonance Images

Deep Learning Approach to Predict Alzheimer's Disease throug...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Ramadhan, Gilang Titah Pusparani, Yori Farady, Isack Furqon, Elvin Nur Lin, Chih-Yang Chao, Wen-Hung Rani Alex, John Sahaya Aparajeeta, Jeetashree Lung, Chi-Wen Asia University Department of Computer Science and Information Engineering Taichung Taiwan Budi Luhur University Department of Visual Communication Design Jakarta Indonesia Asia University Department of Digital Media Design Taichung Taiwan Mercu Buana University Electrical Engineering Jakarta Indonesia Department of Electrical Engineering Yuan Ze University Chung-Li Taiwan National Central University Department of Mechanical Engineering Taoyuan Taiwan Innovation and Research Vellore Institute of Technology Division of Healthcare Advancement Tamil Nadu India Vellore Institute of Technology School of Electronics Engineering Tamil Nadu India Asia University Department of Creative Product Design Taichung Taiwan

ISBN: (纸本)9798350324174

Alzheimer's disease is the most common type of dementia that causes many of the functions of the human brain to be severely weakened. To date, there has not been a cure for Alzheimer's disease. Therefore, early diagnosis is needed using MRI images with the help of a classification program. Deep learning using the Convolutional Neural Network (CNN) method is receiving increasing attention because of its excellent performance. Its architecture can be modified according to user needs based on the data to be processed and the approach for classifying, detecting, and segmenting visual objects. In this paper, we offer a classification of Alzheimer's disease using one of the architectures on CNN, namely Visual Geometry Group-19 (VGG-19), with a sagittal view of MRI images with an image size of 229 x 229 pixels. The classification accuracy of the described method is 94% for the validation set. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Maximum-Width Rainbow-Bisecting Empty Annulus∗

SSRN

引用

SSRN 2023年

作者： Banerjee, Sandip Baral, Arpita Mahapatra, Priya Ranjan Sinha Bae, Sang Won Yoon, Sang Duk Division of Computer Science and Engineering Kyonggi University Korea Republic of Institute of Informatics University of Wroclaw Poland Department of Computer Science and Engineering University of Kalyani India Department of Service and Design Engineering Sungshin Women's University April 4 2023 Korea Republic of

Given a set of $n$ colored points with $k$ colors in the plane,we study the problem of computing a maximum-width rainbow-bisecting empty annulus (of objects specifically axis-parallel square, axis-parallel rectangle and circle) problem. We call a region \emph{rainbow} if it containsat least one point of each color. The maximum-width rainbow-bisecting emptyannulus problem asks to find an annulus $A$ of a particular shape with maximum possible width such that $A$ does not contain any input points and it bisects the input point set into two parts, each of which is a \emph{rainbow}.We compute a maximum-width rainbow-bisecting empty axis-parallel square, axis-parallel rectangular and circular annulus in $O(n^3)$ time using $O(n)$ space, in $O(k^2n^2\log n)$ time using $O(n\log n)$ spaceand in $O(n^3)$ time using $O(n^2)$ space respectively. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparkling Silence: Practices and Challenges of Livestreaming Among Deaf or Hard of Hearing Streamers

arXiv

引用

arXiv 2023年

作者： Cao, Beiyan He, Changyang Zhou, Muzhi Fan, Mingming The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Division of Social Science The Hong Kong University of Science and Technology Hong Kong Hong Kong Division of Integrative Systems and Design Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Understanding livestream platforms' accessibility challenges for minority groups, such as people with disabilities, is critical to increasing the diversity and inclusion of those platforms. While prior work investigated the experiences of streamers with vision or motor loss, little is known about the experiences of deaf or hard of hearing (DHH) streamers who must work with livestreaming platforms that heavily depend on audio. We conducted semi-structured interviews with DHH streamers to learn why they livestream, how they navigate livestream platforms and related challenges. Our findings revealed their desire to break the stereotypes towards the DHH groups via livestream and the intense interplay between interaction methods, such as sign language, texts, lip language, background music, and viewer characteristics. Major accessibility challenges include the lack of real-time captioning, the small sign language reading window, and misinterpretation of sign language. We present design considerations for improving the accessibility of the livestream platforms. © 2023, CC BY-NC-ND.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

INTRA-VIDEO POSITIVE PAIRS IN SELF-SUPERVISED LEARNING FOR ULTRASOUND

arXiv

引用

arXiv 2024年

作者： VanBerlo, Blake Wong, Alexander Hoey, Jesse Arntfield, Robert Cheriton School of Computer Science University of Waterloo Waterloo Canada Department of Systems Design Engineering University of Waterloo Waterloo Canada Division of Critical Care Medicine Western University London Canada

Self-supervised learning (SSL) is one strategy for addressing the paucity of labelled data in medical imaging by learning representations from unlabelled images. Contrastive and non-contrastive SSL methods produce learned representations that are similar for pairs of related images. Such pairs are commonly constructed by randomly distorting the same image twice. The videographic nature of ultrasound offers flexibility for defining the similarity relationship between pairs of images. In this study, we investigated the effect of utilizing proximal, distinct images from the same B-mode ultrasound video as pairs for SSL. Additionally, we introduced a sample weighting scheme that increases the weight of closer image pairs and demonstrated how it can be integrated into SSL objectives. Named Intra-Video Positive Pairs (IVPP), the method surpassed previous ultrasound-specific contrastive learning methods’ average test accuracy on COVID-19 classification with the POCUS dataset by ≥ 1.3%. Detailed investigations of IVPP’s hyperparameters revealed that some combinations of IVPP hyperparameters can lead to improved or worsened performance, depending on the downstream task. Guidelines for practitioners were synthesized based on the results, such as the merit of IVPP with task-specific hyperparameters, and the improved performance of contrastive methods for ultrasound compared to non-contrastive counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Glaucoma Detection Using U-Net and U-Net+ Architectures Using Deep Learning Techniques

SSRN

引用

SSRN 2025年

作者： Kumar, B.P. Pradeep Rangaiah, Pramod K.B. Augustine, Robin Department of Computer Science and Design Atria Institute of Technology Bengaluru560024 India Microwaves in Medical Engineering Group Division of Solid State Electronics Department of Electrical Engineering Uppsala University Box 65 UppsalaSE-751 03 Sweden

This study compares multiple image processing and deep learning methods to demonstrate an enhanced approach to glaucoma diagnosis. The approach focuses on noise reduction using median filtering and optic disc segmentation utilizing the U-Net and U-Net+ architectures. Capsule Networks were utilized for feature extraction and Extreme Learning Machines (ELM) for diagnostic classification. Three datasets were evaluated, including DRISHTI-GS, DRIONS-DB, and HRF, utilizing important parameters such as accuracy, sensitivity, and specificity. The findings revealed that median filtering reduced noise by 97.88\%, with a peak signal-to-noise ratio of 44.99. U-Net beat U-Net+ in optic disc in the process of segmentation with a Dice coefficient of 0.8557, a Jaccard index of 0.7307, and higher segmentation accuracy. The suggested model has great diagnostic accuracy, scoring 99\% for DRISHTI-GS, 99.5\% for DRIONS-DB, and 98.5\% for HRF. These findings show that using deep learning approaches can increase glaucoma diagnosis accuracy and reliability, with important implications for healthcare applications and patient outcomes. © 2025, The Authors. All rights reserved.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

arXiv

引用

arXiv 2024年

作者： Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Development and product trials of a cost-effective cloud-based thermal camera body temperature measurement system 21

Development and product trials of a cost-effective cloud-bas...

引用

9th International Conference on computer and Communications Management, ICCCM 2021

作者： Fung, Kwong Chiu Mow, Wai Ho Au, Kam Hei Mok, Yim To Chim, Ho Yin Division of Integrative Systems and Design The Hong Kong University of Science and Technology Hong Kong Intelligent Design Technology Limited Hong Kong Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9781450390071

Amid the COVID-19 pandemic, body temperature monitoring is an effective measure to reduce the risk of COVID-19 spreading in the community. Two common ways to measure body temperature in public settings include non-contact infrared thermometers and thermal imaging systems. The use of non-contact infrared thermometers involves physical proximity, additional manpower and time, whereas the existing thermal imaging systems are either inaccurate or expensive. To address the above problems, we present an accurate and low-cost automatic fever screening system to assist in preliminary health assessment. Our system involves the integration of a RGB camera, a thermal camera, an embedded system board, and a cloud analytics platform. By utilizing temperature measurement and face detection, our system can extract forehead temperature and assess if the person being evaluated is wearing a mask or not. The system has conducted trial runs in various crowded settings including schools, restaurants, community centres, and commercial buildings. In this study, we manage to lower the cost of developing an effective self-checking station for fever screening by hardware trade-off and software optimization, resulting in a market acceptance price. This makes our solution widely accessible to serve the local community during the COVID-19 period. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Body Temperature Measurement Face Detection Coronavirus COVID-19 Thermal Imaging

来源：评论

学校读者我要写书评

暂无评论

Minimum-Width Double-Slabs and Widest Empty Slabsin High Dimensions

SSRN

引用

SSRN 2024年

作者： Ahn, Taehoon Chung, Chaeyoon Ahn, Hee-Kap Bae, Sang Won Cheong, Otfried Yoon, Sang Duk Graduate School of Artificial Intelligence Pohang University of Science and Technology Pohang Korea Republic of Department of Computer Science Pohang University of Science and Technology Pohang Korea Republic of Graduate School of Artificial Intelligence Department of Computer Science Pohang University of Science and Technology Pohang Korea Republic of Division of Computer Science and Engineering Kyonggi University Suwon Korea Republic of SCALGO Aarhus Denmark Department of Service and Design Engineering Sungshin Women’s University Seoul Korea Republic of

A slab in d-dimensional space R^d is the set of points enclosed by two parallel hyperplanes. We consider the problem of finding an optimal pair of parallel slabs, called a double-slab, that covers a given set P of n points in R^d. We address two optimization problems in R^d for any fixed dimension d >= 3: the minimum-width double-slab problem, in which one wants to minimize the maximum width of the two slabs of the resulting double-slab, and the widest empty slab problem, in which one wants to maximize the gap between the two slabs. Our results include the first nontrivial exact algorithms that solve the former problem for d>=3, and the latter problem for d>=4. © 2024, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Norm-Optimal Control of Discrete Repetitive Processes

Data-Driven Norm-Optimal Control of Discrete Repetitive Proc...

引用

IEEE Conference on Decision and Control

作者： Kevin L. Moore Bing Chu Paolo Rapisarda Design and Society and the Department of Electrical Engineering Division of Engineering Colorado School of Mines 1500 Illinois St. Golden CO USA School of Electronics and Computer Science University of Southampton SO17 1BJ UK

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We present a data-driven, model-free approach to norm-optimal control of discrete repetitive processes, exploiting Willems’ fundamental lemma. The algorithm is described in detail, and a rigorous analysis of its convergence properties is performed. A numerical example is provided to demonstrate the effectiveness of the proposed design methodology.

关键词： design methodology Optimal control Prediction algorithms Numerical simulation Numerical models Convergence Predictive control

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：