检索结果-内蒙古大学图书馆

Health Care Science 2024年第6期3卷 456-474页

作者： Han Yuan Chuan Hong Nguyen Tuan Anh Tran Xinxing Xu Nan Liu Centre for Quantitative Medicine Duke-NUS Medical SchoolSingapore Department of Biostatistics and Bioinformatics Duke UniversityDurhamNorth CarolinaUSA Department of Diagnostic Radiology Singapore General HospitalSingapore Institute of High Performance Computing Agency for ScienceTechnology and ResearchSingapore Programme in Health Services and Systems Research Duke-NUS Medical SchoolSingapore Institute of Data Science National University of SingaporeSingapore

Background:Pneumothorax is a medical emergency caused by the abnormal accumulation of air in the pleural space—the potential space between the lungs and chest *** 2D chest radiographs,pneumothorax occurs within the thoracic cavity and outside of the mediastinum,and we refer to this area as“lung+space.”While deep learning(DL)has increasingly been utilized to segment pneumothorax lesions in chest radiographs,many existing DL models employ an end-to-end *** models directly map chest radiographs to clinician-annotated lesion areas,often neglecting the vital domain knowl-edge that pneumothorax is inherently ***:We propose a novel approach that incorporates the lung+space as a constraint during DL model training for pneumothorax segmentation on 2D chest *** circumvent the need for additional annotations and to prevent potential label leakage on the target task,our method utilizes external datasets and an auxiliary task of lung *** approach generates a specific constraint of lung+space for each chest ***,we have incorporated a discriminator to eliminate unreliable constraints caused by the domain shift between the auxiliary and target ***:Our results demonstrated considerable improvements,with average performance gains of 4.6%,3.6%,and 3.3%regarding intersection over union,dice similarity coefficient,and Hausdorff *** results were con-sistent across six baseline models built on three architectures(U-Net,LinkNet,or PSPNet)and two backbones(VGG-11 or MobileOne-S0).We further con-ducted an ablation study to evaluate the contribution of each component in the proposed method and undertook several robustness studies on hyper-parameter selection to validate the stability of our ***:The integration of domain knowledge in DL models for medical applications has often been *** research underscores the significance of incorporating medical domain kno

关键词： constrained optimization deep transfer learning diagnostic radiology pneumothorax detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

A Generic Reinforced Explainable Framework with Knowledge Graph for Session-based Recommendation 39

A Generic Reinforced Explainable Framework with Knowledge Gr...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Wu, Huizi Fang, Hui Sun, Zhu Geng, Cong Kong, Xinyu Ong, Yew-Soon Shanghai University of Finance and Economics Research Institute for Interdisciplinary Sciences School of Information Management and Engineering China Institute of High Performance Computing Centre for Frontier Ai Research Astar Singapore Ant Group China Nanyang Technological University Astar Centre for Frontier Ai Research Singapore

ISBN: (纸本)9798350322279

Session-based recommendation (SR) has gained increasing attention in recent years. Quite a great amount of studies have been devoted to designing complex algorithms to improve recommendation performance, where deep learning methods account for the majority. However, most of these methods are black-box ones and ignore to provide moderate explanations to facilitate users' understanding, which thus might lead to lowered user satisfaction and reduced system revenues. Therefore, in our study, we propose a generic Reinforced Explainable framework with Knowledge graph for Session-based recommendation (i.e., REKS), which strives to improve the existing black-box SR models (denoted as non-explainable ones) with Markov decision process. In particular, we construct a knowledge graph with session behaviors and treat SR models as part of the policy network of Markov decision process. Based on our particularly designed state vector, reward strategy, and loss function, the reinforcement learning (RL)-based framework not only achieves improved recommendation accuracy, but also provides appropriate explanations at the same time. Finally, we instantiate the REKS in five representative, state-of-the-art SR models (i.e., GRU4REC, NARM, SR-GNN, GCSAN, BERT4REC), whereby extensive experiments towards these methods on four datasets demonstrate the effectiveness of our framework on both recommendation and explanation tasks. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SmartShip: Data Decoding Optimization for Onboard AI Anomaly Detection

SmartShip: Data Decoding Optimization for Onboard AI Anomaly...

引用

International Symposium on Parallel and Distributed computing

作者： Pavle Ivanovic Alexander Windmann Philipp Neumann Chair for High Performance Computing Helmut Schmidt University Hamburg Germany Chair for Computer Science in Mechanical Engineering Helmut Schmidt University Hamburg Germany Deutsches Elektronen-Synchroton Research Group High Performance Computing and Data Science Universität Hamburg Hamburg Germany

ISBN: (数字)9798350369199

ISBN: (纸本)9798350369205

Maritime rescue operations rely on efficient and resilient sea vessels for responding to offshore emergencies. To ensure the availability and prompt deployment of rescue cruisers, system operators need to recognize (and resolve) the failure patterns before they occur onboard. However, many SAR organizations do not have sufficient computing resources for advanced anomaly detection and future fault prediction. This paper details our performant and cost-effective solution for sensor data acquisition, CAN bus decoding, and AI analysis, deployable on typical maritime edge devices. The main focus of our work is enhancing the decoding speed, which is a prerequisite for efficient AI analyses and anomaly detection. Besides elaboration on different optimization strategies, we provide the actual use case for AI anomaly detection based on anomaly scores of electrical, fuel, and cooling system sensors. As a result, we improved the decoding speed by more than two orders of magnitude, allowing edge outlier detection in minutes rather than days.

关键词： performance evaluation System testing Image edge detection Data acquisition Decoding Pattern recognition Artificial intelligence Anomaly detection Optimization Tuning

来源：评论

学校读者我要写书评

暂无评论

DEMon: Decentralized Monitoring for highly Volatile Edge Environments

DEMon: Decentralized Monitoring for Highly Volatile Edge Env...

引用

IEEE International Conference on Utility and Cloud computing (UCC)

作者： Shashikant Ilager Jakob Fahringer Samuel Carlos de Lima Dias Ivona Brandic High Performance Computing Systems Research Group Vienna University of Technology Austria

Monitoring systems play an essential role in efficiently managing resources and application workloads by collecting, storing, and providing requisite information about the state of the resources. However, traditional monitoring systems that collect and store the data in centralized remote servers are infeasible for Edge environments. The centralized architecture increases the communication latency for information storage and retrieval and creates a failure bottleneck. In addition, the Edge resources are arbitrarily (de)provisioned, which creates further challenges for providing quick and trustworthy data. Thus, it is crucial to design and build a monitoring system that is fast, reliable, and trustworthy for such volatile Edge computing systems. Therefore, we propose a Decentralised Edge Monitoring (DEMon) framework, a decentralized, self-adaptive monitoring for highly volatile Edge environments. DEMon, at the core, leverages the stochastic Gossip communication protocol and develops techniques for efficient information dissemination, communication, and retrieval, avoiding a single point of failure and ensuring fast and trustworthy data access. We implement it as a lightweight and portable container-based monitoring system and evaluate it through empirical experiments. The results show that DEMon efficiently decimates and retrieves the monitoring information, addressing the abovementioned challenges.

关键词： Cloud computing Protocols Prototypes Computer architecture Reliability engineering Servers Monitoring

来源：评论

学校读者我要写书评

暂无评论

Approaches and tools for user-driven provenance and data quality information in spatial data infrastructures

引用

International Journal of Digital Earth 2023年第1期16卷 1510-1529页

作者： Julia Fischer Lukas Egli Juliane Groth Caterina Barrasso Steffen Ehrmann Heiko Figgemeier Christin Henzen Carsten Meyer Ralph Müller-Pfefferkorn Arne Rümmler Michael Wagner Lars Bernard Ralf Seppelt Department of Computational Landscape Ecology UFZ—Helmholtz Centre for Environmental ResearchLeipzigGermany Macroecology and Society Group German Centre for Integrative Biodiversity Research(iDiv)Halle-Jena-LeipzigLeipzigGermany Chair of Geoinformatics Technische Universität DresdenDresdenGermany Institute of Biology Leipzig UniversityLeipzigGermany Institute of Geoscience&Geography Martin Luther University Halle-WittenbergHalle(Saale)Germany Center for Information Services and High Performance Computing Technische Universität DresdenDresdenGermany

Geospatial data are fundamental in most global-change and sustainability-related ***,readily accessible information on data quality and provenance is often missing or hardly accessible for users due to technical or perceptual barriers,for example,due to unstructured metadata information or missing *** an interdisciplinary process encompassing perspectives of data users,data producers,and software developers,we identified major needs to facilitate effectivefitness-for-use assessments by data users and developed approaches to address *** provided a stylized analysis of large-scale land use data to showcase selected *** support data users,interoperable quality and provenance information need to be meaningfully *** producers need efficient workflows and tools supporting them in creating high-quality,structured and detailed quality and provenance *** newly developed approaches to increase the availability of structured metadata synthesize new and existing tools to extract metadata or to generate provenance data during *** our approaches to improve interoperability and accessibility we present novel tools to support(i)the creation of curated and linked registers of data quality indicators and thematic terms,and(ii)linked visualization of data quality and provenance *** our approaches increases transparency,facilitatesfitness-for-use assessments,and ultimately improves research quality.

关键词： Dashboard earthsystem science fitness forpurpose ISO 19157 landuseandland cover data ontology

来源：评论

学校读者我要写书评

暂无评论

Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation

arXiv

引用

arXiv 2023年

作者： Zhu, Jiajie Wang, Yan Zhu, Feng Sun, Zhu Macquarie University Australia Ant Group China Institute of High Performance Computing Centre for Frontier AI Research A*STAR Singapore Singapore

The conventional single-target Cross-Domain Recommendation (CDR) aims to improve the recommendation performance on a sparser target domain by transferring the knowledge from a source domain that contains relatively richer information. By contrast, in recent years, dual-target CDR has been proposed to improve the recommendation performance on both domains simultaneously. However, to this end, there are two challenges in dual-target CDR: (1) how to generate both relevant and diverse augmented user representations, and (2) how to effectively decouple domain-independent information from domain-specific information, in addition to domain-shared information, to capture comprehensive user preferences. To address the above two challenges, we propose a Disentanglement-based framework with Interpolative Data Augmentation for dual-target Cross-Domain Recommendation, called DIDA-CDR. In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences. We then propose a disentanglement module to effectively decouple domain-specific and domain-independent information to capture comprehensive user preferences. Both steps significantly contribute to capturing more comprehensive user preferences, thereby improving the recommendation performance on each domain. Extensive experiments conducted on five real-world datasets show the significant superiority of DIDA-CDR over the state-of-the-art *** Codes 68T07 (Primary) Copyright © 2023, The Authors. All rights reserved.

关键词： Clock and data recovery circuits (CDR circuits)

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Journal of Reliable Intelligent Environments 2021年第4期7卷 277-278页

作者： Augusto, Juan Carlos Coronato, Antonio Research Group on Development of Intelligent Environments Department of Computer Science Middlesex University London United Kingdom Institute for High Performance Computing and Networking National Research Council Naples Italy

来源：评论

学校读者我要写书评

暂无评论

Information Extraction: Unstructured to Structured for ESG Reports

Information Extraction: Unstructured to Structured for ESG R...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Zounachuan Sun Ranjan Satapathy Daixue Guo Bo Li Xinyuan Liu Yangchen Zhang Cheng-Ann Tan Ricardo Shirota Filho Rick Siow Mong Goh School of Continuing and Lifelong Education National University of Singapore Singapore Institute of High-Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore DHI Group Singapore

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

The diverse ESG reporting standards adopted worldwide lead to a significant increase in the volume of unstructured reported information, bringing the need for more efficient processing and standardization of ESG information. Our study reveals a significant enhancement in the comprehensiveness of ESG information disclosed by the real estate industry in Singapore, following the SGX’s ESG reporting guidelines. We improved efficiency in collecting and standardizing ESG metrics from reports using an NLP-based automatic extraction algorithm. This project not only streamlines the ESG data extraction process but also contributes to the broader goal of converting unstructured data into structured formats. Furthermore, it sets a valuable precedent for the industry, fostering increased transparency and accountability within Singapore’s corporate landscape and potentially influencing global standards. Using the automatic extraction technique, we are paving the way for a more informed and responsible approach to corporate sustainability reporting.

关键词： Measurement Conferences Real estate industry Information retrieval Data mining Sustainable development Standards Guidelines

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Journal of Reliable Intelligent Environments 2021年第2期7卷 67-67页

作者： Coronato, Antonio Augusto, Juan Carlos Department of Computer Science Research Group on Development of Intelligent Environments Middlesex University London United Kingdom Institute for High Performance Computing and Networking National Research Council Naples Italy

来源：评论

学校读者我要写书评

暂无评论

A Multi-Hyperparameter Prediction Framework for Distributed Energy Trading on Photovoltaic Network

引用

Tsinghua Science and Technology 2025年第2期30卷 864-874页

作者： Chun Chen Yong Zhang Boon Han Lim Li Ning Shengzhong Feng Peng Xie School of Intelligent Manufacturing and Equipment Shenzhen Institute of Information TechnologyShenzhen 518172China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen518055China Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul RahmanKajang 43000Malaysia Shenzhen Institute for Advanced Study Shenzhen 518028China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesBeijing 100864China High-performance Intelligent Computing Research Group Guangdong Institute of Intelligent Science and TechnologyZhuhai 519031China

The rapid evolution of distributed energy resources,particularly photovoltaic systems,poses a formidable challenge in maintaining a delicate balance between energy supply and demand while minimizing *** integrated nature of distributed markets,blending centralized and decentralized elements,holds the promise of maximizing social welfare and significantly reducing overall costs,including computational and communication ***,achieving this balance requires careful consideration of various hyperparameter sets,encompassing factors such as the number of communities,community detection methods,and trading mechanisms employed among *** address this challenge,we introduce a groundbreaking neural network-based framework,the Energy Trading-based Artificial Neural Network(ET-ANN),which excels in performance compared to existing *** experiments underscore the superiority of ET-ANN in minimizing total energy transaction costs while maximizing social welfare within the realm of photovoltaic networks.

关键词： photovoltaic energy trading hyperparameter prediction

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：