检索结果-内蒙古大学图书馆

2024 SIGGRAPH Asia 2024 Courses, SA Courses 2024

作者： Gobbetti, Enrico Pintore, Giovanni Agus, Marco National Research Center in High-Performance Computing Big Data and Quantum Computing Cagliari Italy Visual and Data-intensive Computing Center for Advanced Studies Research and Development in Sardinia Cagliari Italy College of Science and Engineering Hamad Bin Khalifa University Doha Qatar

ISBN: (纸本)9798400711350

Surround-view panoramic imaging delivers extensive spatial coverage and is widely supported by professional and commodity capture devices. Research on inferring and exploring 3D indoor models from 360° images has recently flourished, resulting in highly effective solutions. Nevertheless, challenges persist due to the complexity and variability of indoor environments and issues with noisy and incomplete data. This course provides an up-to-date integrative view of the field. After introducing a characterization of input sources, we define the structure of output models, the priors exploited to bridge the gap between imperfect input and desired output, and the main characteristics of geometry reasoning and data-driven approaches. We then identify and discuss the main sub-problems in indoor reconstruction from panoramas and review and analyze state-of-the-art solutions for indoor capture, room modeling, integrated model computation, visual representation generation, and immersive exploration. Relevant examples of implemented pipelines are described, focusing on deep-learning solutions. We finally point out relevant research issues and analyze research trends. © 2024 Copyright held by the owner/author(s).

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

MultiPanoWise: holistic deep architecture for multi-task dense prediction from a single panoramic image

MultiPanoWise: holistic deep architecture for multi-task den...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Uzair Shah Muhammad Tukur Mahmood Alzubaidi Giovanni Pintore Enrico Gobbetti Mowafa Househ Jens Schneider Marco Agus ICT Division College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Visual and Data-Intensive Computing CRS4 Italy National Research Center in HPC Big Data and Quantum Computing Italy

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

We present a novel holistic deep-learning approach for multi-task learning from a single indoor panoramic image. Our framework, named MultiPanoWise, extends vision transformers to jointly infer multiple pixel-wise signals, such as depth, normals, and semantic segmentation, as well as signals from intrinsic decomposition, such as reflectance and shading. Our solution leverages a specific architecture combining a transformer-based encoder-decoder with multiple heads, by introducing, in particular, a novel context adjustment approach, to enforce knowledge distillation between the various signals. Moreover, at training time we introduce a hybrid loss scalarization method based on an augmented Chebychev/hypervolume scheme. We illustrate the capabilities of the proposed architecture on public-domain synthetic and real-world datasets. We demonstrate performance improvements with respect to the most recent methods specifically designed for single tasks, like, for example, individual depth estimation or semantic segmentation. To our knowledge, this is the first architecture capable of achieving state-of-the-art performance on the joint extraction of heterogeneous signals from single indoor omnidirectional images.

关键词： Training Reflectivity Computer vision Semantic segmentation Estimation Computer architecture Multitasking

来源：评论

学校读者我要写书评

暂无评论

Advancing delirium classification: A clinical notes-based natural language processing-supported machine learning model

引用

Intelligence-Based Medicine 2024年 9卷 100140-100140页

作者： Amjad, Sobia Holmes, Natasha E. Kishore, Kartik Young, Marcus Bailey, James Bellomo, Rinaldo Verspoor, Karin School of Computing and Information System The University of Melbourne Parkville Melbourne VIC Australia Data Analytics Research and Evaluation (DARE) Centre Austin Health and the University of Melbourne Heidelberg Melbourne Australia Department of Critical Care The University of Melbourne Parkville Melbourne Australia Australian and New Zealand Intensive Care Research Center Monash University Melbourne Australia Department of Intensive Care Austin Hospital Melbourne Australia School of Computing Technologies RMIT University Melbourne Australia

Objective: The study of the epidemiology of delirium in hospitalized patients is challenging. We aimed to identify the presence or absence of delirium from clinical text notes using natural language processing (NLP) techniques and machine learning (ML) models. Materials and methods: We developed a delirium predictive model using 942 clinical notes from hospitalized patients with an ICD-10 delirium hospital discharge code. Moreover, we implemented ML models using a) delirium-suggestive words from an expert-defined dictionary or b) free text in clinical notes. Both strategies considered positive and negative delirium-associated words. Results: At the note level, for the dictionary method, the logistic regression model achieved an area under the receiver-operating curve (AUROC) of 0.917 for positive words and 0.914 for combined positive and negative words. The areas under the precision-recall curve (AUPR) were 0.893 and 0.897, respectively. For the free-text method, the model achieved an AUROC of 0.826 and 0.830 and AUPR of 0.852 and 0.856, respectively. Discussion: NLP-based ML models accurately identified the presence of delirium in clinical notes. The dictionary-based method was superior to the free-text method. The use of negative features improved performance in both methods. Conclusion: Our proposed NLP-based ML model identified delirium in clinical notes. This model could automatically screen millions of notes and facilitate the study of the epidemiology of in-hospital delirium. © 2024

关键词： Delirium Document classification Machine learning Medical dictionary Natural language processing

来源：评论

学校读者我要写书评

暂无评论

An On-Call Shift for Anaesthetist Rostering Problem (ARP): A Mathematical Model

An On-Call Shift for Anaesthetist Rostering Problem (ARP): A...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Norizal Abdullah Masri Ayob Nasser R. Sabar Meng Chun Lam Liu Chian Yong Data Mining and Optimisation Lab Faculty of Information Science and Technology Center for Artificial Intelligence Technology (CAIT) UKM Bangi Selangor Malaysia Department of Computer Science and Information Technology La Trobe University Melbourne Australia Faculty of Information Science and 43600 Mixed Reality and Pervasive Computing Lab Center for Artificial Intelligence Technology (CAIT) UKM Bangi Selangor Malaysia Department of Anaesthesiology & Intensive Care UKM Medical Centre Jalan Yaacob Latiff Bandar Tun Razak Kuala Lumpur Malaysia

This work dealt with a real-world Anaesthetist Rostering Problem (ARP) for an on-call shift. An on-call shift for an anaesthetist had already been resolved under the physician's rostering problem. However, in their work, each individual can be assigned to only one place throughout the daily on-call shift. In addition, no consecutive days are rostered for the on-call shift, and each level of preference for the on-call shift is excluded from the study. This scenario is irrelevant to the real-world ARP of an on-call shift at Hospital Canselor Tuanku Muhriz (HCTM) in Malaysia, as an anaesthetist is rostered for multiple places of the on-call shifts daily. Also, they can be rostered on consecutive days for on-call shifts, and each anaesthetist will be rostered depending on their preference level for the on-call shift. Therefore, this work proposes a new mathematical formulation with constraints, parameters, and an evaluation function. We utilise Mixed-integer programming to formulate and solve the model with IBM ILOG CPLEX Optimization Studio. The quality of the solution generated by our model is measured using our proposed evaluation function to minimise the violation of constraints. A case study of real-world data from the HCTM was run and tested to validate the model. The result shows that a new model can produce a better optimal solution, whilst the current solution methodology at HCTM is unable to do.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-torqued harmonics and attosecond pulses driven by time-delayed relativistic vortex lasers

引用

Physical Review A 2022年第3期106卷 033515-033515页

作者： Jingwei Wang Matt Zepf Yuxin Leng Ruxin Li Sergey G. Rykovanov State Key Laboratory of High Field Laser Physics and Chinese Academy of Sciences Center for Excellence in Ultra-Intense Laser Science Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai 201800 China China-Russian Belt and Road Joint Laboratory on Laser Science Shanghai 201800 China Collaborative Innovation Center of IFSA Shanghai Jiao Tong University Shanghai 200240 China Helmholtz Institute Jena Fröbelstieg 3 07743 Jena Germany Faculty of Physics and Astronomy Friedrich-Schiller-Universität Jena 07743 Jena Germany High Performance Computing and Big Data Laboratory Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow 121205 Russia

Light carrying time-varying orbital angular momentum (OAM) is a recently discovered type of structured electromagnetic field compared with a typical vortex field whose OAM is static. Such so-called self-torqued light is employed for manipulating the fast magnetic, topological, and quantum excitations and increasing its intensity and having access to shorter pulse durations would be of great benefit. Here we theoretically and numerically demonstrate the generation of intense self-torqued harmonics and attosecond pulses in the relativistic regime, driven by two time-delayed relativistic vortex lasers with different OAMs l1 and l2. The OAM of the nth harmonic spans nl1 to nl2, and the OAM of the attosecond pulses changes from l1 to l2. Such intense self-torqued harmonics and attosecond pulses may offer alternative possibilities in ultrafast spectroscopy.

关键词： High intensity laser-plasma interactions High-energy-density plasmas Radiation & particle generation in plasmas Ultrafast phenomena Relativistic plasmas Particle-in-cell methods Relativistic hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Intense harmonics with time-varying orbital angular momentum from relativistic plasma mirrors

arXiv

引用

arXiv 2021年

作者： Wang, Jingwei Zepf, Matt Leng, Yuxin Li, Ruxin Rykovanov, Sergey G. Shanghai 201800 China Collaborative Innovation Center of IFSA Shanghai Jiao Tong University Shanghai 200240 China Helmholtz Institute Jena Fröbelstieg 3 Jena07743 Germany Faculty of Physics and Astronomy Friedrich-Schiller-Universität Jena Jena07743 Germany High Performance Computing and Big Data Laboratory Center for Computational and Data-Intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

In this Letter using three-dimensional particle-in-cell simulations and analytical considerations we demonstrate intense high-order plasma surface harmonics carrying a time-varying orbital angular momentum (OAM) - the self-torque. We show that by using two laser beams with different OAMs l1 and l2 and a certain delay between each other and shooting them obliquely on an overdense plasma target, one can generate harmonics with OAM spanning nl1 to nl2, where n is the order of the harmonic. Such intense self-torqued harmonics can offer new possibilities in ultrafast spectroscopy. © 2021, CC BY.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

The DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications

The DeepHealth Toolkit: A Unified Framework to Boost Biomedi...

引用

International Conference on Pattern Recognition

作者： Michele Cancilla Laura Canalini Federico Bolelli Stefano Allegretti Salvador Carrión Roberto Paredes Jon A. Gómez Simone Leo Marco Enrico Piras Luca Pireddu Asaf Badouh Santiago Marco-Sola Lluc Alvarez Miquel Moreto Costantino Grana Università degli Studi di Modena e Reggio Emilia Italy PRHLT Research Center Universitat Politècnica de València Spain Data-intensive Computing Group CRS4 Italy Barcelona Supercomputing Center Spain Universitat Autònoma de Barcelona Spain Universitat Politècnica de Catalunya Spain

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud computing or heterogeneous High-Performance computing (HPC). The DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. The toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall.

关键词： Deep learning Training Computer vision Cloud computing Pipelines Neural networks Writing

来源：评论

学校读者我要写书评

暂无评论

Tracing the Local Void and its substructure with MeerKAT

Tracing the Local Void and its substructure with MeerKAT

引用

URSI Atlantic Radio Science Conference (URSI AT-RASC)

作者： Sushma Kurapati Renée C. Kraan-Korteweg D.J. Pisano Hao Chen Sambatriniaina H. A. Rajohnson Nadia Steyn Bradley Frank Paolo Serra Sharmila Goedhart Fernando Camilo Department of Astronomy University of Cape Town Private Bag X3 Rondebosch South Africa Research Center for Intelligent Computing Platforms Zhejiang Laboratory Hangzhou China International Centre for Radio Astronomy Research The University of Western Australia 35 Stirling Highway Australia UK Astronomy Technology Centre Royal Observatory Edinburgh Blackford Hill Edinburgh UK South African Radio Astronomy Observatory 2 Fir Street Observatory South Africa The Inter-University Institute for Data Intensive Astronomy University of Cape Town Rondebosch South Africa Via della Scienza 5 INAF - Osservatorio Astronomico di Cagliari Selargius CA Italy

ISBN: (数字)9789463968102

ISBN: (纸本)9798350360257

The Local Void is the nearest large void. Nevertheless its properties are extremely difficult to observe since a major part of the Void is located behind the Galactic bulge. Here, we use Hi $21 \mathrm{~cm}$ emission observations extracted from the SARAO MeerKAT Galactic Plane Survey (SMGPS) to study the Local Void and its surroundings over the Galactic longitude range $329^{\circ}\lt \ell\lt 55^{\circ}$, Galactic latitude $|b|\lt $ 1.5°, and redshift $c z\lt 7500 \mathrm{kms}^{-1}$. We find that the extent of the Void is $\sim 58 \mathrm{Mpc}$ at these low Galactic latitudes. The galaxies in the Void tend to have lower HI masses (by approximately 0.25dex) compared to average density counterparts. We identified several likely small groups of galaxies, of which two groups (with 3 members and 5 members) in the Void show signs of filamentary substructure.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A regional industry intelligence business platform based on adaptive clustering

引用

International Journal of Circuits, Systems and Signal Processing 2020年 14卷 656-660页

作者： Liu, Junjie Cai, Danlin Zhu, Daxin Huang, Siyu Network Information Center Quanzhou Normal University Quanzhou China Fujian University Laboratory of Intelligent Computing and Information Processing Quanzhou China Fujian Provincial Key Laboratory of Data-Intensive Computing Quanzhou China College of Mathematics and Computer Science Quanzhou Normal University Quanzhou China

How to grasp comprehensive, timely, effective and accurate business competitive intelligence has become an urgent and critical issue for regional industrial clusters. Therefore, a Industrial Internet Platform for Regional Economic based on Adaptive Clustering called IIPRE is developed. The multi thread oriented extraction technology is used to collect the business intelligence data of specific industries. The data is clustered by rule-based machine learning, and the business information data model is used for analysis. Finally, the visualization report is generated by big data visualization software. The system uses Intelligent Retrieval technology to automatically complete the functions from acquisition to processing automatically, to generate data information to meet the application requirements, uses Automatic Classification Technology to provide automatic classification function combining machine-based automatic learning and rule-based information, and uses Personalized Display Technology to provide customizable personalized display pages for individuals, to organize and adjust the hot information, thematic information, clustering, related words, early warning, statistics and other information released by the system. The construction of the platform provides enterprises with comprehensive, timely, effective and accurate business competitive intelligence services, improves the strategic planning, competitive intelligence acquisition and industrial information sharing capabilities of regional industrial clusters, and will achieve tremendous economic and social benefits. © 2020, North Atlantic University Union NAUN. All rights reserved.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Application of Multi-objective Evolutionary Algorithm in E-Commerce Recommendation System

Application of Multi-objective Evolutionary Algorithm in E-C...

引用

Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), International Conference on

作者： Siyu Huang Junjie Liu Daxin Zhu Danlin Cai School of Mathmatics and Computer Science Quanzhou Normal University Quanzhou China Network Information Center Quanzhou Normal University Quanzhou China Fujian Provincial Key Laboratory of Data-Intensive Computing Quanzhou China

ISBN: (数字)9781728181431

ISBN: (纸本)9781728181448

Traditional recommendation methods often have incomplete understandings of recommendation evaluation indicators. They are limited to the accuracy of recommendation, but often ignore the diversity, novelty, coverage and other indicators. Therefore, the recommendation system should use more evaluation indicators to meet personalized demands of users so as to obtain satisfactory results. This is closely related to the problem of multi-objective optimization. This paper describes the mathematical expression of the multi-objective optimization problem and uses NSGA-II algorithm to test its accuracy and diversity indexes of Netflix dataset. The experimental results show that NSGA-II algorithm can meet multi-objective requirements of the recommendation system and the experimental results are satisfactory.

关键词：

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：