检索结果-内蒙古大学图书馆

A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

Computers, Materials & Continua 2022年第2期70卷 2971-2989页

作者： Jose Escorcia-Gutierrez Jordina Torrents-Barrena Margarita Gamarra Natasha Madera Pedro Romero-Aroca Aida Valls Domenec Puig Electronic and Telecommunications Engineering Program Universidad Autónoma del CaribeBarranquilla080001Colombia Department of Computational Science and Electronic Universidad de la CostaCUCBarranquilla080001Colombia Ophthalmology Service Universitari Hospital Sant JoanInstitut de Investigacio Sanitaria Pere VirgiliReus43201Spain Departament d’Enginyeria Informàtica i Matemàtiques Escola Tècnica Superior d’EnginyeriaUniversitat Rovira i VirgiliTarragona43007Spain

Diabetic retinopathy (DR) is a complication of diabetesmellitus thatappears in the retina. Clinitians use retina images to detect DR pathologicalsigns related to the occlusion of tiny blood vessels. Such occlusion brings adegenerative cycle between the breaking off and the new generation of thinnerand weaker blood vessels. This research aims to develop a suitable retinalvasculature segmentation method for improving retinal screening proceduresby means of computer-aided diagnosis systems. The blood vessel segmentationmethodology relies on an effective feature selection based on SequentialForward Selection, using the error rate of a decision tree classifier in theevaluation function. Subsequently, the classification process is performed bythree alternative approaches: artificial neural networks, decision trees andsupport vector machines. The proposed methodology is validated on threepublicly accessible datasets and a private one provided by Hospital Sant Joanof Reus. In all cases we obtain an average accuracy above 96% with a sensitivityof 72% in the blood vessel segmentation process. Compared with the state-ofthe-art, our approach achieves the same performance as other methods thatneed more computational *** method significantly reduces the numberof features used in the segmentation process from 20 to 5 dimensions. Theimplementation of the three classifiers confirmed that the five selected featureshave a good effectiveness, independently of the classification algorithm.

关键词： Diabetic retinopathy artificial neural networks decision trees support vector machines feature selection retinal vasculature segmentation

来源：评论

学校读者我要写书评

暂无评论

Distinct mechanisms of FAK mechanoactivation by different extracellular matrix proteins

引用

医用生物力学 2013年第S1期28卷 69-71页

作者： Jihye Seong Arash Tajik Jie Sun Jun-Lin Guan Martin J.Humphries Susan E.Craig Asha Shekaran Andrs J.García Ning Wang Yingxiao Wang Neuroscience Program University of Illinois Department of Mechanical Science and Engineering University of Illinois Department of Bioengineering & Beckman Institute for Advanced Science and Technology University of Illinois Division of Molecular Medicine and Genetics Departments of Internal Medicine and Cell & DevelopmentalBiologyUniversity of Michigan Medical School Wellcome Trust Centre for Cell-Matrix Research Faculty of Life SciencesUniversity of Manchester Woodruff School of Mechanical Engineering and Petit Institute for Bioengineering and Bioscience Georgia Institute of Technology Department of Biomedical Engineering School of Life Science and TechnologyHuazhong University of Science and Technology Department of Integrative and Molecular Physiology Center for Biophysics and Computational BiologyInstitute for Genomic BiologyUniversity of Illinois Department of Bioengineering University of California

Introduction Cells can sense and respond to the mechanical microenvironment by converting forces into biochemical signals inside the cells,***[1-3].Focal adhesions are the major sites of interaction between a cell and... 详细信息

Introduction Cells can sense and respond to the mechanical microenvironment by converting forces into biochemical signals inside the cells,***^[1-3].Focal adhesions are the major sites of interaction between a cell and its extracellular matrix（ECM）microenvironment,thus outside mechanical signals can be sensed at focal adhesions through transmembrane receptor *** particular,it has been shown that matrix elasticity can control the cell fate^[4]by modulating the interactions between ECM proteins and their receptor integrins^[5,6].For example,different rigidity of polyacrylamide（PA）gels can lead to different density of ECM ancho-

关键词： integrin converting transmembrane biochemical modulating elasticity rigidity polyacrylamide outside purchased

来源：评论

学校读者我要写书评

暂无评论

Machine learning based non-Newtonian fluid model with molecular fidelity

arXiv

引用

arXiv 2020年

作者： Lei, Huan Wu, Lei Weinan, E. Department of Computational Mathematics Science & Engineering Department of Statistics & Probability Michigan State University MI48824 United States Department of Mathematics and Program in Applied and Computational Mathematics Princeton University NJ08544 United States

We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model directly from a micro-scale description. Polymer solution is used as an example to demonstrate the essential ideas. To faithfully retain molecular fidelity, we establish a micro-macro correspondence via a set of encoders for the micro-scale polymer configurations and their macro-scale counterparts, a set of nonlinear conformation tensors. The dynamics of these conformation tensors can be derived from the micro-scale model and the relevant terms can be parametrized using machine learning. The final model, named the deep non-Newtonian model (DeePN2), takes the form of conventional non-Newtonian fluid dynamics models, with a new form of the objective tensor derivative. Numerical results demonstrate the accuracy of DeePN2. Copyright © 2020, The Authors. All rights reserved.

关键词： Viscous flow

来源：评论

学校读者我要写书评

暂无评论

Pretreatment Chemometrics in Holistic Biogas Life Cycle Assessment: Framing Case Study with Carica papaya

引用

Waste and Biomass Valorization 2018年 1-14页

作者： Jensen, Cory D. Olugbemide, A.D. Akpa, F.A.O. Oladipo, Ajayi College of Engineering and Computational Sciences Colorado School of Mines GoldenCO United States Division of Liberal Arts and International Studies Joint Policy Program with the University of Colorado Colorado School of Mines GoldenCO United States Auchi Polytechnic AuchiEdo State Nigeria Department of Basic Sciences Auchi Polytechnic AuchiEdo State Nigeria Department of Science Laboratory Technology Auchi Polytechnic AuchiEdo State Nigeria Department of Agricultural and Bio-Environmental Engineering Auchi Polytechnic AuchiEdo State Nigeria

This research explores synergistic pre-treatment parameters and chemometrics as applicable to systems level biogas related research frameworks (such as the sustainable development goals) for anaerobic digestion biomass processes-policy. Specifically, the hypothesis that simple feedstock pretreatment-digestion methods can be applied to rapidly evaluate biochemical-biogas potential of anaerobically digested Carica papaya petioles was tested. Pretreatment parameters explored include hydration, i.e. 1:4, 1:6, 1:8 and 1:10 substrate mass to water weight ratios and hydrochloric acid pretreatment chemistry, i.e. 1%—0.3 M, 3%—0.7 M, 5%—1.0 M, in batch digestions experiments with non-inoculated C. papaya petioles. Biomass feedstock was obtained from Edo State, Nigeria. Digestions were performed at ambient temperature, i.e. 27 °C, for 3 weeks. Pretreated C. papaya petiole samples were analyzed with Fourier transform infrared spectroscopy to characterize spectra with characteristic absorbance ratios indicative of physicochemical changes in biomass that include;cross-linked lignin ratio, the lateral order index, and hydrogen bond intensity. Cumulative gaseous yields from C. papaya petiole digestions were fit to the modified Gompertz form and optimized with non-linear regression in Matlab® to derive mathematical parameters, i.e. daily maximum production rate of biogas, a lag phase prior to biogas production, and biogas potential. An optimum C. papaya petiole pretreatment digestion scenario, i.e. 1:4 substrate-to-water ratio and 3%, i.e. 0.7 M, HCl pretreatment resulted in a 150% increase in yield, (10.9 mL gas/g VS) compared to non-pretreated C. papaya petiole digestion. Analysis with the modified Gompertz form also suggests rapid biogas potential assessment can be performed in a few days-time, i.e. approximately 10 days with distinct visual characterization of individual digestion performance. It was concluded that the applied digestion procedures with the use of C. papaya peti

关键词： Anaerobic digestion

来源：评论

学校读者我要写书评

暂无评论

Early surveillance of rice bakanae disease using deep learning and hyperspectral imaging

引用

aBIOTECH 2024年第3期5卷 281-297页

作者： Sishi Chen Xuqi Lu Hongda Fang Anand Babu Perumal Ruyue Li Lei Feng Mengcen Wang Yufei Liu College of Biosystems Engineering and Food Science Zhejiang UniversityHangzhou 310058China State Key Laboratory of Rice Biology and Breeding Zhejiang UniversityHangzhou 310058China Computational Modeling and Nanoscale Processing Unit National Institute of Food TechnologyEntrepreneurship and Management-ThanjavurMinistry of Food Processing IndustriesThanjavur 613005India College of Environmental and Resource Sciences Zhejiang UniversityHangzhou 310058China Global Education Program for AgriScience Frontiers Graduate School of AgricultureHokkaido UniversitySapporo 060-8589Japan

Bakanae disease,caused by Fusarium fujikuroi,poses a significant threat to rice production and has been observed in most rice-growing *** disease symptoms caused by different pathogens may vary,including elongated and weak stems,slender and yellow leaves,and dwarfism,as *** disease is likely to cause necrosis of diseased seedlings,and it may cause a large area of infection in the field through the transmission of ***,early disease surveillance plays a crucial role in securing rice *** monitoring methods are both time-consuming and labor-intensive and cannot be broadly *** this study,a combination of hyperspectral imaging technology and deep learning algorithms were used to achieve in situ detection of rice seedlings infected with bakanae *** data were obtained on the 9th,15th,and 21st day after rice infection to explore the physiological and biochemical performance,which helps to deepen the research on the disease *** data were obtained over these same periods of infection,and a deep learning model,named Rice Bakanae Disease-Visual Geometry Group(RBD-VGG),was established by leveraging hyperspectral imaging technology and deep learning *** on this model,an average accuracy of 92.2%was achieved on the 21st day of *** also achieved an accuracy of 79.4%as early as the 9th *** characteristic wavelengths were extracted to increase the feasibility of using portable spectral equipment for field ***,the model offers an efficient and non-destructive surveillance methodology for monitoring bakanae disease,thereby providing an efficient avenue for disease prevention and control.

关键词： Bakanae disease Hyperspectral imaging Deep learning Early surveillance Disease monitoring

来源：评论

学校读者我要写书评

暂无评论

Midwest Structural sciences Center A University‐Government Partnership

引用

AIP Conference Proceedings 2008年第1期973卷 377-382页

作者： William A. Dick Executive Director Midwest Structural Sciences Center Computational Science and Engineering Program University of Illinois at Urbana‐Champaign 2270 Digital Computer Laboratory 1304 West Springfield Avenue Urbana Illinois 61801 USA

Strategic partnerships among universities, industry and government have been a trademark of the research environment in the United States for more than two decades. Each member of this research triad brings a set of unique perspectives and strengths to the table, as well as being hampered with an often equally daunting set of weaknesses. It is clear that given appropriate opportunities in specific technologies, university‐industry‐government collaboration is a “big winner.” Our observation, however, is that some federally‐funded research programs have failed to achieve the synergistic result envisioned by the funding agency, the host university, or collaborating industries. This paper introduces the relationships and highlights a new research program at the University of Illinois focused on the structural sciences necessary for next‐generation air vehicles. Keys to successful programs are realistic expectations on all sides, a clear focus on appropriate science and engineering technologies, flexibility on the part of the federal funding agency, and a strong university management team.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

Physical Review E 2001年第5期64卷 051503-051503页

作者： Y. Gebremichael T. B. Schrøder F. W. Starr S. C. Glotzer Center for Theoretical and Computational Materials Science and Polymers Division National Institute of Standards and Technology Gaithersburg Maryland 20899 Chemical Physics Program Institute for Physical Sciences and Technology University of Maryland College Park Maryland 20742 Departments of Chemical Engineering and Materials Science and Engineering University of Michigan Ann Arbor Michigan 48109

In recent years, experimental and computational studies have demonstrated that the dynamics of glass-forming liquids are spatially heterogeneous, exhibiting regions of temporarily enhanced or diminished mobility. Here we present a detailed analysis of dynamical heterogeneity in a simulated “bead-spring” model of a low-molecular-weight polymer melt. We investigate the transient nature and size distribution of clusters of “mobile” chain segments (monomers) as the polymer melt is cooled toward its glass transition. We also explore the dependence of this clustering on the way in which the mobile subset is defined. We show that the mean cluster size is time dependent with a peak at intermediate time, and that the mean cluster size at the peak time grows with decreasing temperature T. We show that for each T a particular fraction of particles maximizes the mean cluster size at some characteristic time, and this fraction depends on T. The growing size of the clusters demonstrates the growing range of correlated motion, previously reported for this same system [C. Beneman et al. Nature (London) 399, 246 (1999)]. The distribution of cluster sizes approaches a power law near the mode-coupling temperature, similar to behavior reported for a simulated binary mixture and a dense colloidal suspension, but with a different exponent. We calculate the correlation length of the clusters, and show that it exhibits similar temperature- and time-dependent behavior as the mean cluster size, with a maximum at intermediate time. We show that the characteristic time of the maximum cluster size follows the scaling predicted by mode-coupling theory (MCT) for the β time scale, revealing a possible connection between spatially heterogeneous dynamics and MCT.

关键词： .size distribution clustering intermediate segments glass transition investigate toward glass-forming monomers Polymer Melt Dynamical Heterogeneity spatially heterogeneous mean cluster correlated dynamics mobile subset peak time

来源：评论

学校读者我要写书评

暂无评论

End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems 18

End-to-end symmetry preserving inter-atomic potential energy...

引用

Proceedings of the 32nd International Conference on Neural Information Processing Systems

作者： Linfeng Zhang Jiequn Han Han Wang Wissam A. Saidi Roberto Car E. Weinan Program in Applied and Computational Mathematics Princeton University Institute of Applied Physics and Computational Mathematics China and CAEP Software Center for High Performance Numerical Simulation China Department of Mechanical Engineering and Materials Science University of Pittsburgh Program in Applied and Computational Mathematics Princeton University and Department of Chemistry and Department of Physics Princeton University and Princeton Institute for the Science and Technology of Materials Princeton University Program in Applied and Computational Mathematics Princeton University and Department of Mathematics Princeton University and Beijing Institute of Big Data Research China

Machine learning models are changing the paradigm of molecular modeling, which is a fundamental tool for material science, chemistry, and computational biology. Of particular interest is the inter-atomic potential energy surface (PES). Here we develop Deep Potential - Smooth Edition (DeepPot-SE), an end-to-end machine learning-based PES model, which is able to efficiently represent the PES of a wide variety of systems with the accuracy of ab initio quantum mechanics models. By construction, DeepPot-SE is extensive and continuously differentiable, scales linearly with system size, and preserves all the natural symmetries of the system. Further, we show that DeepPot-SE describes finite and extended systems including organic molecules, metals, semiconductors, and insulators with high fidelity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal fusion of audio, scene, and face features for first impression estimation

Multimodal fusion of audio, scene, and face features for fir...

引用

International Conference on Pattern Recognition

作者： Furkan Gürpinar Heysem Kaya Albert Ali Salah Program of Computational Science and Engineering Boğaziçi University Istanbul Turkey Namik Kemal Universitesi Tekirdag TR Department of Computer Engineering Boğaziçi University Istanbul Turkey

ISBN: (纸本)9781509048489

Affective computing, particularly emotion and personality trait recognition, is of increasing interest in many research disciplines. The interplay of emotion and personality shows itself in the first impression left on other people. Moreover, the ambient information, e.g. the environment and objects surrounding the subject, also affect these impressions. In this work, we employ pre-trained Deep Convolutional Neural Networks to extract facial emotion and ambient information from images for predicting apparent personality. We also investigate Local Gabor Binary Patterns from Three Orthogonal Planes video descriptor and acoustic features extracted via the popularly used openSMILE tool. We subsequently propose classifying features using a Kernel Extreme Learning Machine and fusing their predictions. The proposed system is applied to the ChaLearn Challenge on First Impression Recognition, achieving the winning test set accuracy of 0.913, averaged over the “Big Five” personality traits.

关键词： Feature extraction Face Acoustics Emotion recognition Visualization Training Kernel

来源：评论

学校读者我要写书评

暂无评论

Implementation of contact line motion based on the phase-field lattice Boltzmann method

引用

Physical Review E 2024年第4期109卷 045307-045307页

作者： Long Ju Zhaoli Guo Bicheng Yan Shuyu Sun Computational Transport Phenomena Laboratory (CTPL) King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Kingdom of Saudi Arabia Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology Wuhan 430074 China Energy Resource and Petroleum Engineering Program Physical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Kingdom of Saudi Arabia

This paper proposes a strategy to implement the free-energy-based wetting boundary condition within the phase-field lattice Boltzmann method. The greatest advantage of the proposed method is that the implementation of contact line motion can be significantly simplified while still maintaining good accuracy. For this purpose, the liquid-solid free energy is treated as a part of the chemical potential instead of the boundary condition, thus avoiding complicated interpolations with irregular geometries. Several numerical testing cases, including droplet spreading processes on the idea flat, inclined, and curved boundaries, are conducted, and the results demonstrate that the proposed method has good ability and satisfactory accuracy to simulate contact line motions.

关键词： Contact line dynamics Wetting Lattice-Boltzmann methods

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：