检索结果-内蒙古大学图书馆

Efficient graph-based matrix completion on incomplete animated models

学校读者我要写书评

暂无评论

Efficient graph-based matrix completion on incomplete animat...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Evangelos Vlachos Aris S. Lalos Konstantinos Moustakas Kostas Berberidis Electrical and Computer Engineering Department Computer Engineering and Informatics Department University of Patras Rion-Patras Greece

ISBN: (纸本)9781509060689

Recently, there has been increasing interest for easy and reliable generation of 3D animated models facilitating several real-time applications. In most of these applications, the reconstruction of soft body animations is based on time-varying point clouds which are irregularly sampled and highly incomplete. To overcome these imperfections, we introduce a novel reconstruction technique, using graph-based matrix completion approaches. The presented method exploits spatio-temporal coherences by implicitly forcing the proximity of the adjacent 3D points in time and space. The proposed constraints are modeled by using the weighted Laplacian graphs and are constructed from the available points. Extensive evaluation studies, carried out using a collection of different highly-incomplete dynamic models, verify that the proposed technique achieves plausible reconstruction output despite the constraints posed by arbitrarily complex and motion scenarios.

关键词： Conferences Multimedia communication

Community-based security for the internet of things

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhu, Quanyan Rass, Stefan Schartner, Peter Department of Electrical and Computer Engineering New York University 2 Metrotech Center Brooklyn11201 United States Institute of Applied Informatics System Security Group Universitaet Klagenfurt Universitaetsstrasse 65-67 Klagenfurt9020 Austria

With more and more devices becoming connectable to the internet, the number of services but also a lot of threats increases dramatically. Security is often a secondary matter behind functionality and comfort, but the problem has already been recognized. Still, with many IoT devices being deployed already, security will come step-by-step and through updates, patches and new versions of apps and IoT software. While these updates can be safely retrieved from app stores, the problems kick in via jailbroken devices and with the variety of untrusted sources arising on the internet. Since hacking is typically a community effort these days, security could be a community goal too. The challenges are manifold, and one reason for weak or absent security on IoT devices is their weak computational power. In this chapter, we discuss a community based security mechanism in which devices mutually aid each other in secure software management. We discuss game-theoretic methods of community formation and light-weight cryptographic means to accomplish authentic software deployment inside the IoT device community. Copyright © 2018, The Authors. All rights reserved.

关键词： Internet of things

A Data Mining Approach for Biomarker Discovery Using Transcriptomics in Endometriosis

学校读者我要写书评

暂无评论

A Data Mining Approach for Biomarker Discovery Using Transcr...

IEEE International Conference on Bioinformatics and Biomedicine

作者： Sadia Akter Dong Xu Susan C. Nagel Trupti Joshi Informatics Institute University of Missouri Dept. of Electrical Engineering and Computer Science Informatics Institute Christopher S. Bond Life Sciences Center University of Missouri Dept. of Obstetrics Gynecology and Women's Health School of Medicine Dept. of Health Management and Informatics Informatics Institute Christopher S. Bond Life Sciences Center University of Missouri

ISBN: (纸本)9781538654897

Endometriosis is a complex and common gynecological disorder affecting 5-10% of reproductive age women. Due to the lack of definitive diagnostic symptoms and expensive invasive procedures for diagnosing endometriosis, the average time for the diagnosis can be up to 10 years. This diagnostic latency has a very significant impact on endometriosis patients, and early diagnosis is desired in order to increase quality of life. In this study, we analyzed 38 RNA-seq transcriptomics samples (16 endometriosis and 22 controls) and identified genomic signatures as potential biomarkers. We applied innovative data mining approaches including a combination of a normalization techniques, generalized linear model (GLM) for identifying the differentially expressed genes and a decision tree algorithm for constructing models with higher predictive performance. A total of 5 candidate genes were identified as potential biomarkers of endometriosis, which outperformed the results from the Biosigner tool using a leave-one-out cross-validation technique. Our data mining approach can successfully distinguish the endometriosis patients from the non-endometriosis and can be potentially used as a prediction-based diagnostic tool for other diseases in future.

关键词： Endometriosis Transcriptomic Biomarker discovery Data mining Predictive diagnostic modeling Decision tree Endometriosis data mining Decision Trees transcriptomics Biological Markers

A multi-layer gaussian process for motor symptom estimation in people with parkinson’s disease

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Lang, Muriel Pfister, Franz M.J. Fröhner, Jakob Abedinpour, Kian Pichler, Daniel Fietzek, Urban Um, Terry Taewoong Kulić, Dana Endo, Satoshi Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich Germany Faculty of Mathematics Informatics and Statistics Ludwig-Maximilians-Universität München Munich Germany Department of Neurology and Clinical Neurophysiology Schön Klinik München Schwabing Munich Germany Department of Neurology School of Medicine Technical University of Munich Munich Germany Department of Electrical and Computer Engineering University of Waterloo WaterlooON Canada

The assessment of Parkinson’s disease (PD) poses a significant challenge as it is influenced by various factors which lead to a complex and fluctuating symptom manifestation. Thus, a frequent and objective PD assessment is highly valuable for effective health management of people with Parkinson’s disease (PwP). Here, we propose a method for monitoring PwP by stochastically modeling the relationships between their wrist movements during unscripted daily activities and corresponding annotations about clinical displays of movement abnormalities. We approach the estimation of PD motor signs by independently modeling and hierarchically stacking Gaussian process models for three classes of commonly observed movement abnormalities in PwP including tremor, (non-tremulous) bradykinesia, and (non-tremulous) dyskinesia. We use clinically adopted severity measures as annotations for training the models, thus allowing our multi-layer Gaussian process prediction models to estimate not only their presence but also their severities. The experimental validation of our approach demonstrates strong agreement of the model predictions with these PD annotations. Our results show the proposed method produces promising results in objective monitoring of movement abnormalities of PD in the presence of arbitrary and unknown voluntary motions, and makes an important step towards continuous monitoring of PD in the home environment. Copyright © 2018, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Baheti, Bhakti Chakrabarty, Satrajit Akbari, Hamed Bilello, Michel Wiestler, Benedikt Schwarting, Julian Calabrese, Evan Rudie, Jeffrey Abidi, Syed Mousa, Mina Villanueva-Meyer, Javier Fields, Brandon K.K. Kofler, Florian Shinohara, Russell Takeshi Iglesias, Juan Eugenio Mok, Tony C.W. Chung, Albert C.S. Wodzinski, Marek Jurgas, Artur Marini, Niccolò Atzori, Manfredo Müller, Henning Grosbröhmer, Christoph Siebert, Hanna Hansen, Lasse Heinrich, Mattias P. Canalini, Luca Klein, Jan Gerken, Annika Heldmann, Stefan Hering, Alessa Hahn, Horst K. Meng, Mingyuan Bi, Lei Feng, Dagan Kim, Jinman Zeineldinal, Ramy A. Karar, Mohamed E. Mathis-Ullrich, Franziska Burgert, Oliver Abderezaei, Javid Pionteck, Aymeric Chopra, Agamdeep Kurt, Mehmet Yan, Kewei Yan, Yonghong Tang, Zhe Ma, Jianqiang Nasser, Sahar Almahfouz Kurian, Nikhil Cherian Meena, Mohit Shamsi, Saqib Sethi, Amit Tustison, Nicholas J. Avants, Brian B. Cook, Philip Gee, James C. Tian, Lin Greer, Hastings Niethammer, Marc Hoopesar, Andrew Hoffmannas, Malte Dalcaar, Adrian V. Christodoulidis, Stergios Estiene, Théo Vakalopoulou, Maria Paragios, Nikos Marcus, Daniel S. Davatzikos, Christos Sotiras, Aristeidis Menze, Bjoern Bakas, Spyridon Waldmannstetter, Diana Division of Computational Pathology Department of Pathology and Laboratory Medicine Indiana University School of Medicine IndianapolisIN United States Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO United States GE HealthCare San RamonCA United States University of Pennsylvania PhiladelphiaPA United States Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Mallinckrodt Institute of Radiology Washington University School of Medicine St. LouisMO United States Institute for Informatics Data Science & Biostatistics Washington University School of Medicine St. LouisMO United States Department of Bioengineering Santa Clara University Santa ClaraCA United States Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Computer Science TUM School of Computation Information and Technology Technical University of Munich Munich Germany Department of Diagnostic and Interventional Neuroradiology School of Medicine Klinikum rechts der Isar Technical University of Munich Munich Germany Department of Nuclear Medicine University Hospital Regensburg Regensburg Germany University Hospital Regensburg Regensburg Germany Department of Radiology & Biomedical Imaging University of California San FranciscoCA United States Department of Radiology Duke University Medical Center DurhamNC United States Department of Radiology University of California San DiegoCA United States Helmholtz AI Helmholtz Munich Neuherberg Germany Penn Statistics in Imaging and Visualization Center Department of Biostatistics Epidemiology and Informatics University of Pennsylvania Philadelphia United States Massachusetts General Hospital Harvard Medical School United States Centre for Medical Imaging Computing University College London United Kingdom The Hong Kong University of Science and Technology Hong Kong University of Applied Sciences West

Registration of longitudinal brain Magnetic Resonance Imaging (MRI) scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been considerable progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The challenge was conducted in conjunction with both the IEEE International Symposium on Biomedical Imaging (ISBI) 2022 and the International Conference on Medical Image Computing and computer-Assisted Intervention (MICCAI) 2022. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. The training data with their GT annotations, were publicly released to enable the development of registration algorithms. The validation data, without their GT annotations, were also released to allow for algorithmic evaluation prior to the testing phase, which only allowed submission of containerized algorithms for evaluation on hidden hold-out testing data. Quantitative evaluation and ranking was based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency

关键词： Magnetic resonance imaging

Manifold-adaptive dimension estimation revisited

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Benkő, Zsigmond Stippinger, Marcell Rehus, Roberta Bencze, Attila Fabó, Dániel Hajnal, Boglárka Erőss, Loránd Telcs, András Somogyvári, Zoltán Department of Computational Sciences Wigner Research Centre for Physics H-1121 Hungary János Szentágothai Doctoral School of Neurosciences Semmelweis University H-1085 Hungary Department of Computer Science and Information Theory Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics BudapestH-1111 Hungary Epilepsy Center Department of Neurology National Institute of Clinical Neurosciences BudapestH-1145 Hungary Department of Functional Neurosurgery National Institute of Clinical Neurosciences BudapestH-1145 Hungary Faculty of Information Technology and Bionics Péter Pázmány Catholic University BudapestH-1083 Hungary Department of Quantitative Methods University of Pannonia Faculty of Business and Economics VeszprémH-8200 Hungary Neuromicrosystems ltd. BudapestH-1113 Hungary

Data dimensionality informs us about data complexity and sets limit on the structure of successful signal processing pipelines. In this work we revisit and improve the manifold adaptive Farahmand-Szepesvári-Audibert (FSA) dimension estimator, making it one of the best nearest neighbor-based dimension estimators available. We compute the probability density function of local FSA estimates, if the local manifold density is uniform. Based on the probability density function, we propose to use the median of local estimates as a basic global measure of intrinsic dimensionality, and we demonstrate the advantages of this asymptotically unbiased estimator over the previously proposed statistics: the mode and the mean. Additionally, from the probability density function, we derive the maximum likelihood formula for global intrinsic dimensionality, if i.i.d. holds. We tackle edge and finite-sample effects with an exponential correction formula, calibrated on hypercube datasets. We compare the performance of the corrected-median-FSA estimator with kNN estimators: maximum likelihood (ML, Levina-Bickel) and two implementations of DANCo (R and matlab). We show that corrected-median-FSA estimator beats the ML estimator and it is on equal footing with DANCo for standard synthetic benchmarks according to mean percentage error and error rate metrics. With the median-FSA algorithm, we reveal diverse changes in the neural dynamics while resting state and during epileptic seizures. We identify brain areas with lower-dimensional dynamics that are possible causal sources and candidates for being seizure onset zones. Copyright © 2020, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

NECI: N-Electron Configuration Interaction with an emphasis on state-of-the-art stochastic methods

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guther, Kai Anderson, Robert J. Blunt, Nick S. Bogdanov, Nikolay A. Cleland, Deidre Dattani, Nike Dobrautz, Werner Ghanem, Khaldoon Jeszenski, Peter Liebermann, Niklas Manni, Giovanni Li Lozovoi, Alexander Y. Luo, Hongjun Ma, Dongxia Merz, Florian Overy, Catherine Rampp, Markus Samanta, Pradipta Kumar Schwarz, Lauretta R. Shepherd, James J. Smart, Simon D. Vitale, Eugenio Weser, Oskar Booth, George H. Alavi, Ali Max Planck Institute for Solid State Research Heisenbergstr. 1 Stuttgart70569 Germany Department of Physics King’s College London Strand LondonWC2R 2LS United Kingdom Department of Chemistry University of Cambridge Lensfield Road CambridgeCB2 1EW United Kingdom CSIRO Data61 DocklandsVIC3008 Australia Department of Electrical and Computer Engineering University of Waterloo 200 University Avenue Waterloo Canada Centre for Theoretical Chemistry and Physics NZ Institute for Advanced Study Massey University New Zealand Lenovo HPC&AI Innovation Center Meitnerstr. 9 Stuttgart70563 Germany Gießenbachstr. 2 Garching85748 Germany Department of Chemistry & Informatics Institute University of Iowa

We present NECI, a state-of-the-art implementation of the Full Configuration Interaction Quantum Monte Carlo algorithm, a method based on a stochastic application of the Hamiltonian matrix on a sparse sampling of the wave function. The program utilizes a very powerful parallelization and scales efficiently to more than 24000 CPU cores. In this paper, we describe the core functionalities of NECI and recent developments. This includes the capabilities to calculate ground and excited state energies, properties via the one- and two-body reduced density matrices, as well as spectral and Green’s functions for ab initio and model systems. A number of enhancements of the bare FCIQMC algorithm are available within NECI, allowing to use a partially deterministic formulation of the algorithm, working in a spin-adapted basis or supporting transcorrelated Hamiltonians. NECI supports the FCIDUMP file format for integrals, supplying a convenient interface to numerous quantum chemistry programs and it is licensed under GPL-3.0. This article has been accepted by the Jouranl of Chemical Physics, after it is published, it will be found at https://***/journal/jcp. Copyright © 2020, The Authors. All rights reserved.

关键词： Quantum chemistry

Balance the nodule shape and surroundings: A new multichannel image based convolutional neural network scheme on lung nodule diagnosis

学校读者我要写书评

暂无评论

Balance the nodule shape and surroundings: A new multichanne...

Medical Imaging 2017: computer-Aided Diagnosis

作者： Sun, Wenqing Zheng, Bin Huang, Xia Qian, Wei Medical Imaging and Informatics Laboratory Department of Electrical and Computer Engineering University of Texas El PasoTX United States College of Engineering University of Oklahoma NormanOK United States Sino-Dutch Biomedical and Information Engineering School Northeastern University Shenyang China

ISBN: (纸本)9781510607132

Deep learning is a trending promising method in medical image analysis area, but how to efficiently prepare the input image for the deep learning algorithms remains a challenge. In this paper, we introduced a novel artificial multichannel region of interest (ROI) generation procedure for convolutional neural networks (CNN). From LIDC database, we collected 54880 benign nodule samples and 59848 malignant nodule samples based on the radiologists' annotations. The proposed CNN consists of three pairs of convolutional layers and two fully connected layers. For each original ROI, two new ROIs were generated: one contains the segmented nodule which highlighted the nodule shape, and the other one contains the gradient of the original ROI which highlighted the textures. By combining the three channel images into a pseudo color ROI, the CNN was trained and tested on the new multichannel ROIs (multichannel ROI II). For the comparison, we generated another type of multichannel image by replacing the gradient image channel with a ROI contains whitened background region (multichannel ROI I). With the 5-fold cross validation evaluation method, the CNN using multichannel ROI II achieved the ROI based area under the curve (AUC) of 0.8823±0.0177, compared to the AUC of 0.8484±0.0204 generated by the original ROI. By calculating the average of ROI scores from one nodule, the lesion based AUC using multichannel ROI was 0.8793±0.0210. By comparing the convolved features maps from CNN using different types of ROIs, it can be noted that multichannel ROI II contains more accurate nodule shapes and surrounding textures. © 2017 SPIE.

关键词： Biological organs

Multi-tenant cross-slice resource orchestration: A deep reinforcement learning approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Chen, Xianfu Zhao, Zhifeng Wu, Celimuge Bennis, Mehdi Liu, Hang Ji, Yusheng Zhang, Honggang VTT Technical Research Centre of Finland Oulu Finland Zhejiang Lab College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Graduate School of Informatics and Engineering University of Electro-Communications Tokyo Japan Centre for Wireless Communications University of Oulu Finland Department of Electrical Engineering and Computer Science Catholic University of America United States Information Systems Architecture Research Division National Institute of Informatics Tokyo Japan College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

With the cellular networks becoming increasingly agile, a major challenge lies in how to support diverse services for mobile users (MUs) over a common physical network infrastructure. Network slicing is a promising solution to tailor the network to match such service requests. This paper considers a system with radio access network (RAN)-only slicing, where the physical infrastructure is split into slices providing computation and communication functionalities. A limited number of channels are auctioned across scheduling slots to MUs of multiple service providers (SPs) (i.e., the tenants). Each SP behaves selfishly to maximize the expected long-term payoff from the competition with other SPs for the orchestration of channels, which provides its MUs with the opportunities to access the computation and communication slices. This problem is modelled as a stochastic game, in which the decision makings of a SP depend on the global network dynamics as well as the joint control policy of all SPs. To approximate the Nash equilibrium solutions, we first construct an abstract stochastic game with the local conjectures of channel auction among the SPs. We then linearly decompose the per-SP Markov decision process to simplify the decision makings at a SP and derive an online scheme based on deep reinforcement learning to approach the optimal abstract control policies. Numerical experiments show significant performance gains from our scheme. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning