检索结果-内蒙古大学图书馆

Learning With MOOCS (LWMOOCS)

作者： Magesh Chandramouli Ge Jin Daniel Cubillos Department of Computer Information Technology and Graphics Purdue University Northwest Hammond USA

ISBN: (纸本)9781728125503

Project MANEUVER (Manufacturing Education Using Virtual Environment Resources) is developing an affordable virtual reality (VR) framework to address the imminent demand for well-trained digital manufacturing (DM) technicians. MANEUVER project has a set of MOOC (Massive Open Online Course) video contents that provides a process of setting up local VR server, navigating inside 3D environment, interacting with 3D objects, simulating CNC machines and different 3D printer models. The previously stated topics are the list of successfully created MOOC videos that have been deployed on the project MANEUVER website. MANEUVER is developing an innovative multi-modal VR framework for DM instruction. Using a "train-the-trainers" approach, a replicable faculty development model is being developed for secondary and post-secondary institutions. By addressing regional and national entry-level needs of the workforce, the project benefits society and contributes to national economic progress and prosperity.

关键词： Electronic learning computer aided instruction Videos Three-dimensional displays Tools

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Detector Training with Prototypes for Vehicle Detection

Semi-supervised Detector Training with Prototypes for Vehicl...

引用

International Conference on Intelligent Transportation

作者： Georg Waltner Michael Opitz Georg Krispel Horst Possegger Horst Bischof Institute of Computer Graphics and Vision (ICG) Faculty of Computer Science Graz University of Technology Graz Austria

Adapting detectors to new datasets is needed in scenarios where a user has a specific dataset that contains novel classes or is recorded in a setting where a pretrained detector fails. While detectors based on Convolutional Neural Networks (CNNs) are state-of-the-art and nowadays publicly available, they suffer from bad generalization capabilities when applied on datasets that notably differ from the one they were trained on. Finetuning the detector is only possible if the dataset is large enough to not destroy the underlying feature representation. We propose a method where only a few prototypes are labeled for training in a semi-supervised manner. In particular, we separate the detection from the classification step to avoid impairing the bounding box proposal generation. Our trained prototype classification network provides labels to automatically source a large dataset containing 20 to 30 times more samples without further supervision, which we then use to train a more powerful network. We evaluate our method on a private vehicle dataset with six classes and show that evaluating on a previously unseen recording site we can gain an accuracy increase of 9% at same precision and recall levels. We further show that finetuning with as few as 25 labeled samples per class doubles accuracy compared to directly using pretrained features for nearest neighbor classification.

关键词： Detectors Proposals Prototypes Training Object detection Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

Classification supporting Covid-19 diagnostics based on patient survey data

arXiv

引用

arXiv 2020年

作者： Henzela, Joanna Tobiasz, Joanna Kozielskia, Michal Bach, Malgorzata Foszner, Pawel Gruca, Aleksandra Kania, Mateusz Mika, Justyna Papiez, Anna Werner, Aleksandra Zyla, Joanna Jaroszewicz, Jerzy Polanska, Joanna Sikoraa, Marek Department of Computer Networks and Systems Silesian University of Technology Gliwice Poland Department of Data Science and Engineering Silesian University of Technology Gliwice Poland Department of Applied Informatics Silesian University of Technology Gliwice Poland Department of Graphics Computer Vision and Digital Systems Silesian University of Technology Gliwice Poland Department of Infectious Diseases and Hepatology Medical University of Silesia Katowice Poland

Distinguishing COVID-19 from other flu-like illnesses can be difficult due to ambiguous symptoms and still an initial experience of doctors. Whereas, it is crucial to filter out those sick patients who do not need to be tested for SARSCoV-2 infection, especially in the event of the overwhelming increase in disease. As a part of the presented research, logistic regression and XGBoost classifiers, that allow for effective screening of patients for COVID-19, were generated. Each of the methods was tuned to achieve an assumed acceptable threshold of negative predictive values during classification. Additionally, an explanation of the obtained classification models was presented. The explanation enables the users to understand what was the basis of the decision made by the model. The obtained classification models provided the basis for the DECODE service (***), which can serve as support in screening patients with COVID-19 disease. Moreover, the data set constituting the basis for the analyses performed is made available to the research community. This data set consisting of more than 3,000 examples is based on questionnaires collected at a hospital in Poland. Copyright © 2020, The Authors. 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

Advanced Fuzzy C-Means Algorithm Based on Local Density and Distance

引用

Journal of Shanghai Jiaotong university(Science) 2018年第5期23卷 636-642页

作者： Shaochun PANG Yijie SHAO Sen JIANG Keyuan School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Department of Computer Information Technology ＆ Graphics Purdue University NorthwestHammond 46323USA

This paper presents an advanced fuzzy C-means(FCM) clustering algorithm to overcome the weakness of the traditional FCM algorithm, including the instability of random selecting of initial center and the limitation of the data separation or the size of clusters. The advanced FCM algorithm combines the distance with density and improves the objective function so that the performance of the algorithm can be improved. The experimental results show that the proposed FCM algorithm requires fewer iterations yet provides higher accuracy than the traditional FCM algorithm. The advanced algorithm is applied to the influence of stars' box-office data, and the classification accuracy of the first class stars achieves 92.625%.

关键词： objective function clustering center fuzzy C-means （FCM） clustering algorithm degree of member-ship

来源：评论

学校读者我要写书评

暂无评论

Depth-Awareness in a System for Mixed-Reality Aided Surgical Procedures 15th

Depth-Awareness in a System for Mixed-Reality Aided Surgical...

引用

15th International Conference on Intelligent Computing, ICIC 2019

作者： Sylos Labini, Mauro Gsaxner, Christina Pepe, Antonio Wallner, Juergen Egger, Jan Bevilacqua, Vitoantonio Institute for 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 Electrical and Information Engineering Polytechnic University of Bari Bari Italy Department of Oral and Maxillofacial Surgery Medical University of Graz Graz Austria

ISBN: (纸本)9783030267650

computer-assisted surgery is a trending topic in research, with many different approaches which aim at supporting surgeons in the operating room. Existing surgical planning and navigation solutions are often considered to be distracting, unintuitive or hard to interpret. In this work, we address this issue with an approach based on mixed reality devices like Microsoft HoloLens. We assess the depth sensing capabilities of Microsoft HoloLens, and the potential benefit they could bring to computer-assisted surgery applications. © 2019, Springer Nature Switzerland AG.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

IRIS: Interactive real-time feedback image segmentation with deep learning

IRIS: Interactive real-time feedback image segmentation with...

引用

Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Pepe, Antonio Schussnig, Richard Li, Jianning Gsaxner, Christina Chen, Xiaojun Fries, Thomas-Peter Egger, Jan Stanford University School of Medicine Department of Radiology 300 Pasteur Dr StanfordCA United States Graz University of Technology Institute of Computer Graphics and Vision Inffeldgasse 16c/II GrazA-8010 Austria Computer Algorithms for Medicine Laboratory GrazA-8010 Austria Graz University of Technology Institute of Structural Analysis Lessingstraße 25/II GrazA-8010 Austria Medical University of Graz Department of Oral and Maxillofacial Surgery Auenbruggerplatz 5/1 GrazA-8036 Austria Shanghai Jiao Tong University School of Mechanical Engineering 800 Dong Chuan Road Shanghai200240 China

ISBN: (纸本)9781510634015

Volumetric examinations of the aorta are nowadays of crucial importance for the management of critical pathologies such as aortic dissection, aortic aneurism, and other pathologies, which affect the morphology of the artery. These examinations usually begin with the acquisition of a Computed Tomography Angiography (CTA) scan from the patient, which is later on postprocessed to reconstruct the 3D geometry of the aorta. The first postprocessing step is referred to as segmentation. Different algorithms have been suggested for the segmentation of the aorta;including interactive methods, as well as fully automatic methods. Interactive methods need to be fine-tuned on each single CTA scan and result in longer duration of the process, whereas fully automatic methods require the possession of a large amount of labeled training data. In this work, we introduce a hybrid approach by combining a deep learning method with a consolidated interaction technique. In particular, we trained a 2D and a 3D U-Net on a limited number of patches extracted from 25 labeled CTA scans. Afterwards, we use an interactive approach, which consists in defining a region of interest (ROI) by just placing a seed point. This seed point is later used as the center of a 2D or 3D patch to be fed to the 2D or 3D U-Net, respectively. Due to the low content variation of these patches, this method allows to correctly segment the ROIs without the need for parameter tuning for each dataset and with a smaller training dataset, requiring the same minimal interaction as state-of-the-art interactive methods. Later on, the new segmented CTA scans can be further used to train a convolutional network for a fully automatic approach. © 2020 SPIE

关键词： Angiography

来源：评论

学校读者我要写书评

暂无评论

Bundle adjustment revisited

arXiv

引用

arXiv 2019年

作者： Chen, Yu Chen, Yisong Wang, Guoping Peking University Department of Computer Science and Technology Graphics and Interactive Lab Beijing China

3D reconstruction has been developing all these two decades, from moderate to medium size and to large scale. It’s well known that bundle adjustment plays an important role in 3D reconstruction, mainly in Structure from Motion(SfM) and Simultaneously Localization and Mapping(SLAM). While bundle adjustment optimizes camera parameters and 3D points as a non-negligible final step, it suffers from memory and efficiency requirements in very large scale reconstruction. In this paper, we study the development of bundle adjustment elaborately in both conventional and distributed approaches. The detailed derivation and pseudo codes are also given in this paper. Copyright © 2019, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fast decomposable submodular function minimization using constrained total variation 33

Fast decomposable submodular function minimization using con...

引用

33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019

作者： Sesh Kumar, K.S. Bach, Francis Pock, Thomas Data Science Institute Imperial College London United Kingdom INRIA Ecole Normale Superieure PSL Research University Paris France Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

We consider the problem of minimizing the sum of submodular set functions assuming minimization oracles of each summand function. Most existing approaches reformulate the problem as the convex minimization of the sum of the corresponding Lovász extensions and the squared Euclidean norm, leading to algorithms requiring total variation oracles of the summand functions;without further assumptions, these more complex oracles require many calls to the simpler minimization oracles often available in practice. In this paper, we consider a modified convex problem requiring a constrained version of the total variation oracles that can be solved with significantly fewer calls to the simple minimization oracles. We support our claims by showing results on graph cuts for 2D and 3D graphs. © 2019 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Identifying Consumer Health Terms of Side Effects in Twitter Posts

引用

Studies in Health technology and Informatics 2018年 251卷 273-276页

作者： Jiang, Keyuan Chen, Tingyu Calix, Ricardo A. Bernard, Gordon R. Computer Information Technology and Graphics Purdue University Northwest United States Department of Medicine Vanderbilt University United States

ISBN: (纸本)9781614998792

Prevalence of social media has driven a growing number of health related applications with the information shared by online users. It is well known that a gap exists between healthcare professionals and laypeople in expressing the same health concepts. Filling this gap is particularly important for health related applications using social media data. A data-driven, attributional similarity-based method was developed to identify Twitter terms related to side effect concepts. For the 10 most common side effect (symptom) concepts, our method was able to identify a total of 333 Twitter terms, among which only 90 are mapped to those in the consumer health vocabulary (CHV). The identified Twitter terms are specific to Twitter data, indicating a need to expand the existing CHV, and many of them seem to have less ambiguity in word senses than those in CHV. © 2018 The authors and IOS Press. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Decomposition strategy aimed at minimizing power consumption

引用

AIP Conference Proceedings 2022年第1期2611卷 070003页

作者： Marcin Kubica Adam Opara Dariusz Kania Department of Digital Systems Silesian University of Technology ul. Akademicka 2A 44-100 Gliwice Poland Department of Graphics Computer Vision and Digital Systems Silesian University of Technology ul. Akademicka 2A 44-100 Gliwice Poland

The article presents a new strategy of function decomposition, which is aimed at reducing the dynamic power consumption of the obtained logic structures. The essence of this strategy consists in finding decompositions that minimize the number of LUT blocks, and additionally lead to the limitation of the Switching Activity. A key element in the process of searching for such a decomposition is the appropriate selection of the cost function of a given partition of variables. The decomposition of the function is based on the BDD cut, which, with a properly selected cut line and appropriate ordering of variables, leads to effective solutions in terms of power consumption. The article contains a series of experiments showing the effectiveness of the proposed algorithm.

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：