检索结果-内蒙古大学图书馆

VisGraphNet: A complex network interpretation of convolutional neural features

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Florindo, Joao B. Lee, Young-Sup Jun, Kyungkoo Jeon, Gwanggil Albertini, Marcelo K. Institute of Mathematics Statistics and Scientific Computing University of Campinas Rua Sérgio Buarque de Holanda 651 Cidade Universitária"Zeferino Vaz" - Distr. Barão Geraldo SP CampinasCEP 13083-859 Brazil Department of Embedded Systems Engineering Incheon National University 119 Academy-ro Yeonsu-gu Incheon22012 Korea Republic of Department of Computer Science Federal University of Uberlandia Av. Joao Naves de Avila 2121 room Minas Gerais Uberlandia1B150 Brazil

Here we propose and investigate the use of visibility graphs to model the feature map of a neural network. The model, initially devised for studies on complex networks, is employed here for the classification of texture images. The work is motivated by an alternative viewpoint provided by these graphs over the original data. The performance of the proposed method is verified in the classification of four benchmark databases, namely, KTHTIPS-2b, FMD, UIUC, and UMD and in a practical problem, which is the identification of plant species using scanned images of their leaves. Our method was competitive with other state-of-the-art approaches, confirming the potential of techniques used for data analysis in different contexts to give more meaningful interpretation to the use of neural networks in texture classification. © 2021, CC BY.

关键词： Complex networks

Experiences of young people and their caregivers of using technology to manage type 1 diabetes mellitus: Systematic literature review and narrative synthesis

学校读者我要写书评

暂无评论

JMIR Diabetes 2021年第1期6卷 e20973页

作者： Brew-Sam, Nicola Chhabra, Madhur Parkinson, Anne Hannan, Kristal Brown, Ellen Pedley, Lachlan Brown, Karen Wright, Kristine Pedley, Elizabeth Nolan, Christopher J. Phillips, Christine Suominen, Hanna Tricoli, Antonio Desborough, Jane Department of Health Services Research and Policy Research School of Population Health College of Health and Medicine Australian National University Building 62 Mills Rd Acton Canberra 2601 ACT Australia Canberra Health Services Canberra Australia ANU Medical School College of Health and Medicine Australian National University Canberra Australia John Curtin School of Medical Research College of Health and Medicine Australian National University Canberra Australia School of Computing College of Engineering and Computer Science Australian National University Canberra Australia Department of Computing University of Turku Turku Finland Data61 Commonwealth Scientific and Industrial Research Organisation Canberra Australia Nanotechnology Research Lab Research School of Chemistry College of Science Australian National University Canberra Australia

Background: In the last decade, diabetes management has begun to transition to technology-based care, with young people being the focus of many technological advances. Yet, detailed insights into the experiences of young people and their caregivers of using technology to manage type 1 diabetes mellitus are lacking. Objective: The objective of our study was to describe the breadth of experiences and perspectives on diabetes technology use among children and adolescents with type 1 diabetes mellitus and their caregivers. Methods: This systematic literature review used integrated thematic analysis to guide a narrative synthesis of the included studies. We analyzed the perspectives and experiences of young people with type 1 diabetes mellitus and their caregivers reported in qualitative studies, quantitative descriptive studies, and studies with a mixed methods design. Results: Seventeen articles met the inclusion criteria, and they included studies on insulin pump, glucose sensors, and remote monitoring systems. The following eight themes were derived from the analysis: (1) expectations of the technology prior to use, (2) perceived impact on sleep and overnight experiences, (3) experiences with alarms, (4) impact on independence and relationships, (5) perceived usage impact on blood glucose control, (6) device design and features, (7) financial cost, and (8) user satisfaction. While many advantages of using diabetes technology were reported, several challenges for its use were also reported, such as cost, the size and visibility of devices, and the intrusiveness of alarms, which drew attention to the fact that the user had type 1 diabetes mellitus. Continued use of diabetes technology was underpinned by its benefits outweighing its challenges, especially among younger people. Conclusions: Diabetes technologies have improved the quality of life of many young people with type 1 diabetes mellitus and their caregivers. Future design needs to consider the impact of these te

关键词： Adolescents Children Diabetes Experiences Perspectives Self-management Systematic review Technology Type 1 diabetes mellitus

A practical guide to machine learning interatomic potentials – Status and future

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jacobs, Ryan Morgan, Dane Attarian, Siamak Meng, Jun Shen, Chen Wu, Zhenghao Xie, Clare Yijia Yang, Julia H. Artrith, Nongnuch Blaiszik, Ben Ceder, Gerbrand Choudhary, Kamal Csanyi, Gabor Cubuk, Ekin Dogus Deng, Bowen Drautz, Ralf Fu, Xiang Godwin, Jonathan Honavar, Vasant Isayev, Olexandr Johansson, Anders Kozinsky, Boris Martiniani, Stefano Ong, Shyue Ping Poltavsky, Igor Schmidt, K.J. Takamoto, So Thompson, Aidan Westermayr, Julia Wood, Brandon M. Department of Materials Science and Engineering University of Wisconsin-Madison MadisonWI55705 United States Harvard University Center for the Environment Harvard University CambridgeMA02138 United States John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Materials Chemistry and Catalysis Debye Institute for Nanomaterials Science Utrecht University Utrecht3584 CG Netherlands Globus University of Chicago ChicagoIL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States Department of Materials Science and Engineering University of California BerkeleyCA94720 United States Materials Sciences Division Lawrence Berkeley National Laboratory CA94720 United States Material Measurement Laboratory National Institute of Standards and Technology GaithersburgMD20899 United States Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Google DeepMind Mountain ViewCA United States Ruhr-Universität Bochum Bochum44780 Germany Meta United States Orbital Materials London United Kingdom Department of Computer Science and Engineering The Pennsylvania State University University ParkPA United States College of Information Sciences and Technology The Pennsylvania State University University ParkPA United States Artificial Intelligence Research Laboratory The Pennsylvania State University University ParkPA United States Center for Artificial Intelligence Foundations and Scientific Applications The Pennsylvania State University University ParkPA United States Department of Chemistry Mellon College of Science Carnegie Mellon University PittsburghPA15213 United States Computational Biology Department School of Computer Science Carnegie Mellon University PittsburghPA15213 United States Courant Institute of Mathematical Sciences New York University New YorkNY10003 United States Center for Soft Matter Research Department of P

The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spirit of this review is to help such researchers by serving as a practical, accessible guide to the state-of-the-art in MLIPs. This review paper covers a broad range of topics related to MLIPs, including (i) central aspects of how and why MLIPs are enablers of many exciting advancements in molecular modeling, (ii) the main underpinnings of different types of MLIPs, including their basic structure and formalism, (iii) the potentially transformative impact of universal MLIPs for both organic and inorganic systems, including an overview of the most recent advances, capabilities, downsides, and potential applications of this nascent class of MLIPs, (iv) a practical guide for estimating and understanding the execution speed of MLIPs, including guidance for users based on hardware availability, type of MLIP used, and prospective simulation size and time, (v) a manual for what MLIP a user should choose for a given application by considering hardware resources, speed requirements, energy and force accuracy requirements, as well as guidance for choosing pre-trained potentials or fitting a new potential from scratch, (vi) discussion around MLIP infrastructure, including sources of training data, pre-trained potentials, and hardware resources for training, (vii) summary of some key limitations of present MLIPs and current approaches to mitigate such limitations, including methods of including long-range interactions, handling magnetic systems, and treatment of excited states, and finally (viii) we finish with some more speculative thoughts on what the future holds for the development and application of MLIPs over the next 3-10+ years. © 2025, CC BY.

关键词： Digital storage

Deep localization of subcellular protein structures from fluorescence microscopy images

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tahir, Muhammad Anwar, Saeed Mian, Ajmal Muzaffar, Abdul Wahab College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Data61 The Commonwealth Scientific and Industrial Research Organisation Australia Department of Computer Science and Engineering The Australian National University Australia School of Computer Science University of Technology Sydney Australia Computer Science and Software Engineering The University of Western Australia

Accurate localization of proteins from fluorescence microscopy images is challenging due to the inter-class similarities and intra-class disparities introducing grave concerns in addressing multi-class classification problems. Conventional machine learning-based image prediction pipelines rely heavily on pre-processing such as normalization and segmentation followed by hand-crafted feature extraction to identify useful, informative, and application-specific features. Here, we demonstrate that deep learning-based pipelines can effectively classify protein images from different datasets. We propose an end-to-end Protein Localization Convolutional Neural Network (PLCNN) that classifies protein images more accurately and reliably. PLCNN processes raw imagery without involving any pre-processing steps and produces outputs without any customization or parameter adjustment for a particular dataset. Experimental analysis is performed on five benchmark datasets. PLCNN consistently outperformed the existing state-of-the-art approaches from traditional machine learning and deep architectures. This study highlights the importance of deep learning for the analysis of fluorescence microscopy protein imagery. The proposed deep pipeline can better guide drug designing procedures in the pharmaceutical industry and open new avenues for researchers in computational biology and bioinformatics. © 2019, CC BY.

关键词： Fluorescence microscopy

Correction: Current Studies and Applications of Shuffled Frog Leaping Algorithm: A Review

学校读者我要写书评

暂无评论

Archives of Computational Methods in Engineering 2022年第5期30卷 3469-3469页

作者： Maaroof, Bestan B. Rashid, Tarik A. Abdulla, Jaza M. Hassan, Bryar A. Alsadoon, Abeer Mohammadi, Mokhtar Khishe, Mohammad Mirjalili, Seyedali Information Technology Department College of Commerce University of Sulaimani Sulaymaniyah Iraq Computer Science and Engineering University of Kurdistan Hewler Erbil Iraq Computer Science Department College of Science Komar University of Science and Technology Sulaymaniyah Iraq Information Technology College of Commerce University of Sulaimani Sulaymaniyah Iraq Kurdistan Institution for Strategic Studies and Scientific Research Sulaimani Iraq School of Computing and Mathematics Charles Sturt University Sydney Australia Information Technology Department Asia Pacific International College (APIC) Sydney Australia Department of Information Technology College of Engineering and Computer Science Lebanese French University Kurdistan Region Iraq Department of Marine Electronics and Communication Engineering Imam Khomeini Marine Science University Nowshahr Iran Centre for Artificial Intelligence Research and Optimization Torrens University Adelaide Australia Yonsei Frontier Lab Yonsei University Seoul Korea

Jamming and force distribution in growing epithelial tissue

学校读者我要写书评

暂无评论

Physical Review Research 2021年第2期3卷 023129-023129页

作者： Pranav Madhikar Jan Åström Björn Baumeier Mikko Karttunen Department of Mathematics and Computer Science & Institute for Complex Molecular Systems Eindhoven University of Technology 5600 MB Eindhoven The Netherlands CSC Scientific Computing Ltd Kägelstranden 14 02150 Esbo Finland Department of Chemistry The University of Western Ontario 1151 Richmond Street London Ontario Canada N6A 5B7 Department of Applied Mathematics The University of Western Ontario 1151 Richmond Street London Ontario Canada N6A 5B7 The Centre for Advanced Materials and Biomaterials Research The University of Western Ontario 1151 Richmond Street London Ontario Canada N6A 3K7

We investigate morphologies of proliferating cellular tissues using a numerical simulation model for mechanical cell division and migration in two dimensions. The model is applied to a bimodal mixture consisting of stiff cells with a low growth potential and soft cells with a high growth potential; cancer cells are typically considered to be softer than healthy cells. In an even mixture, the soft cells develop into a tissue matrix and the stiff cells into a dendritelike network structure. When soft cells are placed inside a tissue consisting of stiff cells (to model cancer growth), the soft cells develop into a fast-growing tumorlike structure that gradually evacuates the stiff cell matrix. The model also demonstrates (1) how soft cells orient themselves in the direction of the largest effective stiffness as predicted by the theory of Bischofs and Schwarz [Proc. Natl. Acad. Sci. USA 100, 9274 (2003)] and (2) that the orientation and force generation continue a few cell rows behind the soft-stiff interface. With increasing intercell friction, tumor growth slows down, and cell death occurs. The contact force distribution between cells is demonstrated to be highly sensitive to cell type mixtures and cell-cell interactions, which indicates that local mechanical forces can be useful as a regulator of tissue formation. The results shed light on established experimental data.

关键词： Biological movement Cell aggregation Cell division Cell mechanics Jamming

Enhanced hyperspectral tomography for bioimaging by spatiospectral reconstruction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Warr, Ryan Ametova, Evelina Cernik, Robert J. Fardell, Gemma Handschuh, Stephan Jørgensen, Jakob S. Papoutsellis, Evangelos Pasca, Edoardo Withers, Philip J. Henry Royce Institute Department of Materials The University of Manchester ManchesterM13 9PL United Kingdom Laboratory for Applications of Synchrotron Radiation Karlsruhe Institute of Technology Kaiserstr. 12 KarlsruheD-76131 Germany Scientific Computing Department Science Technology Facilities Council UK Research and Innovation Rutherford Appleton Laboratory Chilton DidcotOX11 0QX United Kingdom VetCore Facility for Research University of Veterinary Medicine Vienna Vienna Austria Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Mathematics The University of Manchester ManchesterM13 9PL United Kingdom

Here we apply hyperspectral bright field imaging to collect computed tomographic images with excellent energy resolution (800 eV), applying it for the first time to map the distribution of stain in a fixed biological sample through its characteristic K-edge. Conventionally, because the photons detected at each pixel are distributed across as many as 200 energy channels, energy-selective images are characterised by low count-rates and poor signal-to-noise ratio. This means high X-ray exposures, long scan times and high doses are required to image unique spectral markers. Here, we achieve high quality energy-dispersive tomograms from low dose, noisy datasets using a dedicated iterative reconstruction algorithm. This exploits the spatial smoothness and inter-channel structural correlation in the spectral domain using two carefully chosen regularisation terms. For a multi-phase phantom, a reduction in scan time of 36 times is demonstrated. Spectral analysis methods including K-edge subtraction and absorption step-size fitting are evaluated for an ex vivo, single (iodine)-stained biological sample, where low chemical concentration and inhomogeneous distribution can affect soft tissue segmentation and visualisation. The reconstruction algorithms are available through the open-source Core Imaging Library. Taken together, these tools offer new capabilities for visualisation and elemental mapping, with promising applications for multiply-stained biological specimens. © 2021, CC BY.

关键词： Tomography

Twofold saddle-point formulation of biot poroelasticity with stress-dependent diffusion

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gómez-Vargas, Bryan Mardal, Kent-André Ruiz-Baier, Ricardo Vinje, Vegard Sección de Matemática Sede de Occidente Universidad de Costa Rica San Ramón Ala juela Costa Rica Department of Mathematics Division of Mechanics University of Oslo Norway Simula Research Laboratory Lysaker1325 Norway School of Mathematics Monash University 9 Rainforest Walk MelbourneVIC3800 Australia Institute of Computer Science and Mathematical Modelling Sechenov University Moscow Russia Universidad Adventista de Chile Casilla 7-D Chillán Chile Department for Numerical Analysis and Scientific Computing Simula Research Laboratory Lysaker Norway

We introduce a stress/total-pressure formulation for poroelasticity that includes the coupling with steady nonlinear diffusion modified by stress. The nonlinear problem is written in mixed-primal form, coupling a perturbed twofold saddle-point system with an elliptic problem. The continuous formulation is analysed in the framework of abstract fixed-point theory and Fredholm alternative for compact operators. A mixed finite element method is proposed and its stability and convergence analysis are carried out. We also include a few illustrative numerical tests. The resulting model can be used to study waste removal in the brain parenchyma, where diffusion of a tracer alone or a combination of advection and diffusion are not sufficient to explain the alterations in rates of filtration observed in porous media *** Codes 65N60, 92C50 © 2021, CC BY.

关键词： Diffusion

A generalized lattice boltzmann model for fluid flow system and its application in two-phase flows

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yuan, Xiaolei Chai, Zhenhua Wang, Huili Shi, Baochang School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 School of Mathematics and Computer Science Wuhan Textile University Wuhan430073

In this paper, a generalized lattice Boltzmann (LB) model with a mass source is proposed to solve both incompressible and nearly incompressible Navier-Stokes (N-S) equations. This model can be used to deal with single-phase and twophase ows problems with a mass source term. From this generalized model, we can not only get some existing models, but also derive new models. Moreover, for the incompressible model derived, a modified pressure scheme is introduced to calculate the pressure, and then to ensure the accuracy of the model. In this work, we will focus on a two-phase ow system, and in the frame work of our generalized LB model, a new phase-field-based LB model is developed for incompressible and quasi-incompressible two-phase ows. A series of numerical simulations of some classic physical problems, including a spinodal decomposition, a static droplet, a layered Poiseuille ow, and a bubble rising ow under buoyancy, are performed to validate the developed model. Besides, some comparisons with previous quasi-incompressible and incompressible LB models are also carried out, and the results show that the present model is accurate in the study of two-phase ows. Finally, we also conduct a comparison between quasiincompressible and incompressible LB models for two-phase ow problems, and find that in some cases, the proposed quasi-incompressible LB model performs better than incompressible LB models. Copyright © 2019, The Authors. All rights reserved.

关键词： Two phase flow