检索结果-内蒙古大学图书馆

Evaluation of the thermal processes and simulation methods for additive manufacturing based on the geometry voxel representation

学校读者我要写书评

暂无评论

Key engineering Materials 2018年第1期771卷 91-96页

作者： Ripetskiy, Andrey Zelenov, Sergey Kuznetsova, Ekaterina Rabinskiy, Lev Department of Engineering and Computer Graphics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Department of Engineering Graphics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Faculty of Applied Mechanics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Department of Advanced Materials and Technologies for Aerospace Application Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia

Currently, the technological and hardware base additive production technologies are actively developing. The emergence of new developments in the field of materials science and their possibilities for the creation of products using layer-by-layer method promotes the development of innovative solutions that increase the efficiency of complex technical parts and improves their quality. This paper describes simulation methods based on the Model Voxel Representation part discretization allowing evaluating thermal processes during 3D printing process. The simulation model was extended taking into consideration the following criteria: heat conduction coefficient as a constant;temperature in the center of the elementary volume equals to the temperature at the volume border;temperature of the powder surrounding the item taken as a constant. It was determined that the convergence is affected by numerous factors: temperature in the machine chamber, material properties, heat exchange and the processes running into the chamber of the certain machines. © 2018 Trans Tech Publications, Switzerland.

关键词： 3D printers

Deep learning - A first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Egger, Jan Pepe, Antonio Gsaxner, Christina Jin, Yuan Li, Jianning Kern, Roman Institute of Computer Graphics and Vision Faculty of Computer Science and Biomedical Engineering Graz University of Technology Graz Austria Computer Algorithms for Medicine Laboratory Graz Austria Department of Oral and Maxillofacial Surgery Medical University of Graz Graz Austria University Medicine Essen Essen Germany Research Center for Connected Healthcare Big Data Zhejiang Lab Zhejiang Hangzhou China Research Unit Experimental Neurotraumatology Department of Neurosurgery Medical University of Graz Graz Austria Knowledge Discovery Know-Center Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term 'deep learning', and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image,

关键词： Surveys

Medical deep learning-A systematic meta-review

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Egger, Jan Gsaxner, Christina Pepe, Antonio Pomykala, Kelsey L. Jonske, Frederic Kurz, Manuel Li, Jianning Kleesiek, Jens Institute of Computer Graphics and Vision Faculty of Computer Science and Biomedical Engineering Graz University of Technology Inffeldgasse 16 Styria Graz8010 Austria Department of Oral & Maxillofacial Surgery Medical University of Graz Auenbruggerplatz 5/1 Styria Graz8036 Austria Computer Algorithms for Medicine Laboratory Styria Graz Austria University Medicine Essen Girardetstraße 2 Essen45131 Germany University Medicine Essen Hufelandstraße 55 Essen45147 Germany Partner Site Essen Hufelandstraße 55 Essen45147 Germany

Deep learning has remarkably impacted several different scientific disciplines over the last few years. For example, in image processing and analysis, deep learning algorithms were able to outperform other cutting-edge methods. Additionally, deep learning has delivered state-of-the-art results in tasks like autonomous driving, outclassing previous attempts. There are even instances where deep learning outperformed humans, for example with object recognition and gaming. Deep learning is also showing vast potential in the medical domain. With the collection of large quantities of patient records and data, and a trend towards personalized treatments, there is a great need for automated and reliable processing and analysis of health information. Patient data is not only collected in clinical centers, like hospitals and private practices, but also by mobile healthcare apps or online websites. The abundance of collected patient data and the recent growth in the deep learning field has resulted in a large increase in research effort s. In Q2/2020, the search engine PubMed returned already over 11,000 results for the search term 'deep learning', and around 90% of these publications are from the last three years. However, even though PubMed represents the largest search engine in the medical field, it does not cover all medical-related publications. Hence, a complete overview of the field of 'medical deep learning' is almost impossible to obtain and acquiring a full overview of medical sub-fields is becoming increasingly more difficult. Nevertheless, several review and survey articles about medical deep learning have been published within the last few years. They focus, in general, on specific medical scenarios, like the analysis of medical images containing specific pathologies. With these surveys as a foundation, the aim of this article is to provide the first high-level, systematic meta-review of medical deep learning surveys. Copyright © 2020, The Authors. All rights res

关键词： Generative adversarial networks

CG-SENSE revisited: Results from the first ISMRM reproducibility challenge

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Maier, Oliver Baete, Steven H. Fyrdahl, Alexander Hammernik, Kerstin Harrevelt, Seb Kasper, Lars Karakuzu, Agah Loecher, Michael Patzig, Franz Tian, Ye Wang, Ke Gallichan, Daniel Uecker, Martin Knoll, Florian Institute of Medical Engineering Graz University of Technology Graz Austria Center for Biomedical Imaging New York University School of Medicine New YorkNY United States Department of Clinical Physiology Karolinska University Hospital Karolinska Institutet Stockholm Sweden Department of Computing Imperial College London London United Kingdom Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands Institute for Biomedical Engineering ETH Zurich University of Zurich Zurich Switzerland Translational Neuromodeling Unit Institute for Biomedical Engineering University of Zurich ETH Zurich Zurich Switzerland NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montréal Montréal Canada Department of Radiology Stanford University StanfordCA United States Department of Radiology and Imaging Sciences University of Utah Salt Lake CityUT United States Ming Hsieh Department of Electrical and Computer Engineering Viterbi School of Engineering University of Southern California Los AngelesCA United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Cardiff University Brain Research Imaging Centre Cardiff United Kingdom Institute for Diagnostic and Interventional Radiology University Medical Center Göttingen Göttingen Germany Germany University of Göttingen Germany University of Göttingen Germany

Purpose The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of "Advances in sensitivity encoding with arbitrary k-space trajectories" by Pruessmann et al. Methods The task of the challenge was to reconstruct radially acquired multi-coil k-space data (brain/heart) following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions (Matlab/Python). Results Visually, differences between submissions were small. Pixel-wise differences originated from image orientation, assumed field-of-view or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics. Discussion and Conclusion While the description level of the published algorithm enabled participants to reproduce CG-SENSE in general, details of the implementation varied, e.g., density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient meta-data accompanying open data sets. Defining reproducibility quantitatively turned out to be non-trivial for this image reconstruction challenge, in the absence of ground-truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG-SENSE presented here, as a benchmark for methods comparison. Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Towards the generation of digital twins for facility management based on 3D point clouds 34

学校读者我要写书评

暂无评论

Towards the generation of digital twins for facility managem...

34th Annual Association of Researchers in Construction Management Conference, ARCOM 2018

作者： Stojanovic, Vladeta Trapp, Matthias Richter, Rico Hagedorn, Benjamin Döllner, Jürgen Computer Graphics Systems Group Hasso Plattner Institute Faculty of Digital Engineering University of Potsdam Prof.-Dr.-Helmert-Straße 2-3 Potsdam14482 Germany

Advances versus adaptation of Industry 4.0 practices in Facility Management (FM) have created usage demand for up-to-date digitized building assets. The use of Building Information Modelling (BIM) for FM in the Operation and Maintenance (O&M) stages of the building lifecycle is intended to bridge the gap between operations and digital data, but lacks the functionality of assessing and forecasting the state of the built environment in real-time. To accommodate this, BIM data needs to be constantly updated with the current state of the built environment. However, generation of as-is BIM data for a digital representation of a building is a labor intensive process. While some software applications offer a degree of automation for the generation of as-is BIM data, they can be impractical to use for routinely updating digital FM documentation. Current approaches for capturing the built environment using remote sensing and photometry-based methods allow for the creation of 3D point clouds that can be used as basis data for a Digital Twin (DT), along with existing BIM and FM documentation. 3D point clouds themselves do not contain any semantics or specific information about the building components they represent physically, but using machine learning methods they can be enhanced with semantics that would allow for reconstruction of as-is BIM and basis DT data. This paper presents current research and development progress of a service-oriented platform for generation of semantically rich 3D point cloud representations of indoor environments. A specific focus is placed on the reconstruction and visualization of the captured state of the built environment for increasing FM stakeholder engagement and facilitating collaboration. The preliminary results of a prototypical web-based application demonstrate the feasibility of such a platform for FM using a service-oriented paradigm. © Proceeding of the 34th Annual ARCOM Conference, ARCOM 2018.

关键词： Visualization

Graph-based parallel large scale structure from motion

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Yu Shen, Shuhan Chen, Yisong Wang, Guoping Graphics and Interactive Lab Department of Computer Science and Technology School of Electronic Engineering and Computer Science Peking University National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

While Structure from Motion (SfM) achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. In this work, large scale SfM is deemed as a graph problem, and we tackle it in a divide-and-conquer manner. Firstly, the images clustering algorithm divides images into clusters with strong connectivity, leading to robust local reconstructions. Then followed with an image expansion step, the connection and completeness of scenes are enhanced by expanding along with a maximum spanning tree. After local reconstructions, we construct a minimum spanning tree (MST) to find accurate similarity transformations. Then the MST is transformed into a Minimum Height Tree (MHT) to find a proper anchor node and is further utilized to prevent error accumulation. When evaluated on different kinds of datasets, our approach shows superiority over the state-of-the-art in accuracy and efficiency. Our algorithm is open-sourced in https://***/AIBluefisher/GraphSfM. Copyright © 2019, The Authors. All rights reserved.

关键词： Clustering algorithms

Dualism for CAD-system creation based on natural- intellectual representation

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and engineering 2020年第4期709卷

作者： A I Razumowsky M A Loktev Laboratory of Computer Graphics V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences 65 Profsoyuznaya street Moscow 117997 Russia Department of Engineering Graphics Moscow State Technological University 'STANKIN' Vadkovsky Pereulok 3a. 127055 Moscow Russia

When developing difficultly deterministic software solutions of automated systems, control over the algorithmization and structurization of the task should lie outside the control of the formal interconnection of operators and data. The design of software systems should be controlled from the external control area both over the algorithmization and structuring, and over the autonomous independent consideration of the element. The fact of the possibility of arbitrary coordination of the structural elements of the software system is called the dual representation. The integrative role between independent design elements is assigned to the natural – intellectual interface, which is able to provide a dualism of perception of the elements of the information space both as structurally related and as independent.

关键词：

Memorizing all for implicit discourse relation recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bai, Hongxiao Zhao, Hai Zhao, Junhan Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University Computer Graphics Technology Purdue University West LafayetteIN United States

Implicit discourse relation recognition is a challenging task due to the absence of the nec-essary informative clue from explicit connec-tives. The prediction of relations requires a deep understanding of the semantic meanings of sentence pairs. As implicit discourse relation recognizer has to carefully tackle the se-mantic similarity of the given sentence pairs and the severe data sparsity issue exists in the meantime, it is supposed to be beneficial from mastering the entire training data. Thus in this paper, we propose a novel memory mecha-nism to tackle the challenges for further performance improvement. The memory mecha-nism is adequately memorizing information by pairing representations and discourse relations of all training instances, which right fills the slot of the data-hungry issue in the current im-plicit discourse relation recognizer. Our experiments show that our full model with memo-rizing the entire training set reaches new state-of-the-art against strong baselines, which es-pecially for the first time exceeds the milestone of 60% accuracy in the 4-way task. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Deep learning methods for parallel magnetic resonance image reconstruction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Knoll, Florian Hammernik, Kerstin Zhang, Chi Moeller, Steen Pock, Thomas Sodickson, Daniel K. Akçakaya, Mehmet Center for Biomedical Imaging Department of Radiology New York University Institute of Computer Vision and Graphics Graz University of Technology Department of Electrical and Computer Engineering Center for Magnetic Resonance Research University of Minnesota MinneapolisMN United States Center for Magnetic Resonance Research University of Minnesota MinneapolisMN United States

Following the success of deep learning in a wide range of applications, neural network-based machine learning techniques have received interest as a means of accelerating magnetic resonance imaging (MRI). A number of ideas inspired by deep learning techniques from computer vision and image processing have been successfully applied to non-linear image reconstruction in the spirit of compressed sensing for both low dose computed tomography and accelerated MRI. The additional integration of multi-coil information to recover missing k-space lines in the MRI reconstruction process, is still studied less frequently, even though it is the de-facto standard for currently used accelerated MR acquisitions. This manuscript provides an overview of the recent machine learning approaches that have been proposed specifically for improving parallel imaging. A general background introduction to parallel MRI is given that is structured around the classical view of image space and k-space based methods. Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks. Image-domain based techniques that introduce improved regularizers are covered as well as k-space based methods, where the focus is on better interpolation strategies using neural networks. Issues and open problems are discussed as well as recent efforts for producing open datasets and benchmarks for the community. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging