检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yongchao Yang Jianxin Zhang Qian Wang Bin Liu Key Lab of Advanced Design and Intelligent Computing (Ministry of Education) Dalian University Dalian China School of Computer Science and Engineering Dalian Minzu University Dalian China International School of Information Science and Engineering (DUT-RUISE) Dalian University of Technology Dalian China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Deep hashing has recently been attracting more and more attentions for large-scale image retrieval task owing to its superior performance of search efficiency and less storage space requirements. Among deep hashing models, asymmetric deep hashing performs feature learning on query dataset and directly generates hash code on database images, significantly improving the retrieval performance of deep hashing models. Meanwhile, recently works also establish that high-order statistic of deep features are helpful to obtain more discriminant representations of images. Therefore, to boost the retrieval capability of deep hashing, this work tries to integrate merits of the high-order statistic module and the asymmetric deep hashing architecture, and it further proposes a novel deep high-order asymmetric supervised hashing (DHoASH) for image retrieval. More specifically, we utilize a powerful global covariance pooling module based on matrix power normalization to compute the second-order statistic features of input images, which is fluently embedded into an asymmetric hashing architecture in an end-to-end manner, leading to the generation of more discriminant binary hashing code. Experiment results on two benchmarks illuminates the effectiveness of the proposed DHoASH, which also achieves very competitive retrieval accuracy compared to the state-of-the-art methods.

关键词： Covariance matrices Feature extraction Matrix decomposition Image retrieval Task analysis Convolutional codes

来源：评论

学校读者我要写书评

暂无评论

Smartphone camera oximetry in an induced hypoxemia study

arXiv

引用

arXiv 2021年

作者： Hoffman, Jason S. Viswanath, Varun Ding, Xinyi Thompson, Matthew J. Larson, Eric C. Patel, Shwetak N. Wang, Edward Paul G. Allen School of Computer Science and Engineering University of Washington United States Department of Electrical and Computer Engineering University of California San Diego United States The Design Lab University of California San Diego United States Department of Computer Science Southern Methodist University United States Department of Family Medicine University of Washington United States Department of Electrical and Computer Engineering University of Washington United States

Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO2) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health, as well as improve physicians’ ability to remotely diagnose and treat respiratory conditions. In this work, we take a step towards this goal by performing the first clinical development validation on a smartphone-based SpO2 sensing system using a varied fraction of inspired oxygen (FiO2) protocol, creating a clinically relevant validation dataset for solely smartphone-based methods on a wide range of SpO2 values (70%-100%) for the first time. This contrasts with previous studies, which evaluated performance on a far smaller range (85%-100%). We build a deep learning model using this data to demonstrate accurate reporting of SpO2 level with an overall MAE=5.00% SpO2 and identifying positive cases of low SpO22 monitoring, and we provide the data from the FiO2 study in open-source format, so that others may build on this work. © 2021, CC BY-NC-ND.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Feasibility analysis for a novel dew point air cooler applied in warm and humid climate: a case study in Beijing

引用

Energy Procedia 2019年 158卷 2126-2131页

作者： Peng Xu Xiaoli Ma Xudong Zhao Yaxuan Xiong Yanbing Sun Beijing Key Lab of Heating Gas Supply Ventilating and Air Conditioning Engineering Beijing University of Civil Engineering and Architecture Beijing China 100044 School of Engineering and Computer Science University of Hull UK HU6 7RX Zibo Architectural Design and Research Institute Zibo Shandong China 255037

The air humidity and temperature greatly impact the water evaporation efficiency. It is commonly doubted whether the evaporative cooling technology is suitable for the humid climate as well as the public’s care about the water consumption for cooling. This paper provids a feasibility study for the use of a DPC (dew point air cooler) in Beijing, a representative city in warm and humid climate. The overall analyses include an hourly cooling performance analysis in a typical cooling day, annual energy performance prediction and economic analysis based on an experimentally validated simulation tool. With detailed analyses of the real weather data all year round, it is found the outdoor air must be dehumidified to meet the humidity requirement in most of the cooling hours for any air conditioning means. Thus, the superiority of evaporative cooling would be prominent comparing to the conventional mechanical cooling. The water consumption is little especially considering the fact that the conventional power generation consumes large quantity of water and the DPC saves large sales of power. The results proved the feasibility for the DPC applied in Beijing. The success in application of the proposed DPC in the warm and humid region promises more opportunities of the dew point cooling technology.

关键词： dew point air cooler evaporative cooling warm humid cooling perfomance economic analysis

来源：评论

学校读者我要写书评

暂无评论

A KNOWLEDGE-BASED IDEATION APPROACH FOR BIO-INSPIRED design 24

A KNOWLEDGE-BASED IDEATION APPROACH FOR BIO-INSPIRED DESIGN

引用

24th International Conference on engineering design, ICED 2023

作者： Chen, Liuqing Cai, Zebin Jiang, Zhaojun Long, Qi Sun, Lingyun Childs, Peter Zuo, Haoyu Department of Computer Science and Technology Zhejiang University Hangzhou310030 China Singapore Innovation and Ai Joint Research Lab Zhejiang University Hangzhou310030 China School of Mechanical Engineering Tianjin University Tianjin300350 China Zhejiang University-University of Illinois at Urbana-Champaign Institute Haining314400 China Dyson School of Design Engineering Imperial College London LondonSW7 2AZ United Kingdom

Bio-inspired design (BID) involves generating innovative ideas for engineering design by drawing inspiration from natural biological phenomena and systems, using a form of design-by-analogy. Despite its many successes, BID approaches encounter research challenges including unstructured data and existing models that hinder comprehension and processing, limited focus on finding biological knowledge compared to defined problems, and insufficient guidance of the ideation process with algorithms. This paper proposes a knowledge-based approach to address the challenges. The approach involves transforming unstructured data into structured knowledge, including information about natural sources, their benefits, and applications. The structured knowledge is then used to construct a semantic network, enabling designers to retrieve information for BID in two ways. Furthermore, a three-step ideation method is developed to encourage divergent thinking and explore additional potential solutions by drawing inspiration and utilizing knowledge. The knowledge-based BID approach is implemented as a tool and design cases are conducted to illustrate the process of applying this tool for BID. © The Author(s), 2023. Published by Cambridge University Press.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Examining interaction with general-purpose object recognition in LEGO OASIS

Examining interaction with general-purpose object recognitio...

引用

IEEE Symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Ryder Ziola Shweta Grampurohit Nate Landes James Fogarty Beverly Harrison Computer Science & Engineering DUB Group University of Washington Seattle WA USA Visual Design DUB Group University of Washington Seattle WA USA Lab126 Cupertino CA USA

Improvements in cameras, computer vision, and machine learning are enabling real-time object recognition in interactive systems. Reliable recognition of uninstrumented objects opens up exciting new scenarios using the real-world objects that surround us. At the same time, it introduces the need to understand and manage the uncertainty and ambiguities that are inherent to such sensing. This paper examines this problem in the context of LEGO OASIS, a camera and projector-based system that recognizes LEGO toys and augments them with projected digital content. We focus on an interaction language to model the creation and manipulation of relationships between physical objects and their digital capabilities. We use this set of abstractions to examine different notions of recognition errors and explore interactive approaches to overcoming fundamental challenges in interactive object-aware systems.

关键词： Object recognition Fires Cameras Prototypes computer vision Interactive systems Joining processes

来源：评论

学校读者我要写书评

暂无评论

User-Centric Crowdsourcing Approach to Improve Urban Accessibility Data Collection

User-Centric Crowdsourcing Approach to Improve Urban Accessi...

引用

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Tyler Ortiz Vicky Tang Karla Sutton Grove School of Engineering Computer Science The City College of New York CUNY New York New York School of Constructed Environments Parsons School of Design New York New York Department of Computer Science Lab School for Collaborative Studies New York New York

ISBN: (数字)9798331531003

ISBN: (纸本)9798331531010

While crowdsourcing is an effective method for collecting large-scale datasets, it often faces challenges related to data quality and quantity. This study employs crowdsourcing to collect comprehensive urban accessibility data, focusing on storefront accessibility information in a large city. This task presents significant challenges in terms of data completeness and quality. To address these issues, we propose a user-centric, request-driven crowdsourcing approach that gathers accessibility data based on requests from individuals who are blind or have low vision (BLV). This approach strengthens the user-volunteer feedback loop, increasing volunteer engagement and enhancing user experience. It allows BLV individuals to effectively utilize the collected storefront accessibility data for independent travel. A preliminary user study confirms the effectiveness of the proposed approach.

关键词： Crowdsourcing Feedback loop Navigation Data integrity Visual impairment Urban areas Refining Focusing Data collection User experience

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Workflow Scheduling Over Yarn Cluster Using Deep Reinforcement Learning

Towards Efficient Workflow Scheduling Over Yarn Cluster Usin...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have available resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contextual Affordances for Safe Exploration in Robotic Scenarios

arXiv

引用

arXiv 2024年

作者： Ye, William Z. Sandoval, Eduardo B. Carreno-Medrano, Pamela Cruz, Francisco The School of Computer Science and Engineering University of New South Wales SydneyNSW Australia The School of Art & Design Creative Robotics Lab University of New South Wales SydneyNSW Australia The Faculty of Engineering Monash University Australia

Robotics has been a popular field of research in the past few decades, with much success in industrial applications such as manufacturing and logistics. This success is led by clearly defined use cases and controlled operating environments. However, robotics has yet to make a large impact in domestic settings. This is due in part to the difficulty and complexity of designing mass-manufactured robots that can succeed in the variety of homes and environments that humans live in and that can operate safely in close proximity to humans. This paper explores the use of contextual affordances to enable safe exploration and learning in robotic scenarios targeted in the home. In particular, we propose a simple state representation that allows us to extend contextual affordances to larger state spaces and showcase how affordances can improve the success and convergence rate of a reinforcement learning algorithm in simulation. Our results suggest that after further iterations, it is possible to consider the implementation of this approach in a real robot manipulator. Furthermore, in the long term, this work could be the foundation for future explorations of human-robot interactions in complex domestic environments. This could be possible once state-of-the-art robot manipulators achieve the required level of dexterity for the described affordances in this paper. Copyright © 2024, The Authors. All rights reserved.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

DenseNet for Breast Tumor Classification in Mammographic Images 1st

DenseNet for Breast Tumor Classification in Mammographic Ima...

引用

1st International Conference on Bioengineering and Biomedical Signal and Image Processing, BIOMESIP 2021

作者： Jiménez Gaona, Yuliana Rodriguez-Alvarez, María José Espino-Morato, Hector Castillo Malla, Darwin Lakshminarayanan, Vasudevan Departamento de Química y Ciencias Exactas Universidad Técnica Particular de Loja San Cayetano Alto s/n CP1101608 Loja Ecuador Valencia46022 Spain Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science Waterloo Canada Department of Systems Design Engineering Physics and Electrical and Computer Engineering University of Waterloo WaterlooONN2L3G1 Canada Valencia46022 Spain

ISBN: (纸本)9783030881627

Breast cancer screening is an efficient method to detect breast lesions early. The common screening techniques are tomosynthesis and mammography images. However, the traditional manual diagnosis requires an intense workload for pathologists, and hence is prone to diagnostic errors. Thus, the aim of this study was to build a deep convolutional neural network method for automatic detection, segmentation, and classification of breast lesions in mammography images. Based on deep learning the Mask-CNN (RoIAlign) method was developed to automate RoI segmentation. Then feature extraction, selection and classification were carried out by the DenseNet architecture. Finally, the precision and accuracy of the model was evaluated by the AUC, accuracy and precision metrics. To summarize, the findings of this study show that the methodology may improve the diagnosis and efficiency in automatic tumor localization through medical image classification. © 2021, Springer Nature Switzerland AG.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

The HRC model set for human-robot collaboration research

arXiv

引用

arXiv 2017年

作者： Zeylikman, Sofya Widder, Sarah Roncone, Alessandro Mangin, Olivier Scassellati, Brian Center for Engineering Innovation and Design Yale University New HavenCT06511 United States Social Robotics Lab Computer Science Department Yale University New HavenCT06511 United States

In this paper, we present a model set for designing human-robot collaboration (HRC) experiments. It targets a common scenario in HRC, which is the collaborative assembly of furniture, and it consists of a combination of standard components and custom designs. With this work, we aim at reducing the amount of work required to set up and reproduce HRC experiments, and we provide a unified framework to facilitate the comparison and integration of contributions to the field. The model set is designed to be modular, extendable, and easy to distribute. Importantly, it covers the majority of relevant research in HRC, and it allows tuning of a number of experimental variables that are particularly valuable to the field. Additionally, we provide a set of software libraries for perception, control and interaction, with the goal of encouraging other researchers to proactively contribute to our work. Copyright © 2017, The Authors. All rights reserved.

关键词： Robots

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：