检索结果-内蒙古大学图书馆

Asynchronous GPU-based DEM solver embedded in commercial CFD software with polyhedral mesh support

POWDER TECHNOLOGY 2024年 444卷

作者： Kianimoqadam, Alireza Lapp, Justin L. Univ Maine Dept Mech Engn 75 Long Rd Orono ME 04469 USA

A novel graphical processing unit-based discrete element method solver is introduced to improve stability, performance, and provide seamless integration into commercial or open-source computational fluid dynamics software. A key innovation is eliminating a need for network communication between solvers, which was previously required for cross-platform coupling. This is accomplished by a direct coupling method that employs dynamic-linked libraries. Furthermore, the solver optimizes memory usage by streamlining the particle-cell search algorithm by eliminating the cells' searching grid. This ensures the solver is compatible with a wide range of mesh types, providing high geometric flexibility. The approach simplifies the simulation process by directly incorporating computational fluid dynamics mesh information into the discrete element method solver. The performance analysis indicates about sixteen times boost in computational speed compared to benchmark central processing unit-based solvers. The solver's compatibility with polyhedral meshes, a vital advantage for complex geometries, is tested against a referenced study regarding the simulation of an immersed-tube fluidized bed.

关键词： Discrete element method graphical processing unit CFD-DEM GPU computation Fluidized bed Meshing

来源：评论

学校读者我要写书评

暂无评论

A novel deep autoencoder based survival analysis approach for microarray dataset

引用

PEERJ COMPUTER SCIENCE 2021年 7卷 e492页

作者： Torkey, Hanaa Atlam, Mostafa El-Fishawy, Nawal Salem, Hanaa Menoufia Univ Fac Elect Engn Comp Sci & Engn Dept Menoufia Egypt Delta Univ Sci & Technol Fac Engn Gamasa Egypt

Background. Breast cancer is one of the major causes of mortality globally. Therefore, different Machine Learning (ML) techniques were deployed for computing survival and diagnosis. Survival analysis methods are used to compute survival probability and the most important factors affecting that probability. Most survival analysis methods are used to deal with clinical features (up to hundreds), hence applying survival analysis methods like cox regression on RNAseq microarray data with many features (up to thousands) is considered a major challenge. Methods. In this paper, a novel approach applying autoencoder to reduce the number of features is proposed. Our approach works on features reconstruction, and removal of noise within the data and features with zero variance across the samples, which facilitates extraction of features with the highest variances (across the samples) that most influence the survival probabilities. Then, it estimates the survival probability for each patient by applying random survival forests and cox regression. Applying the autoencoder on thousands of features takes a long time, thus our model is applied to the graphical processing unit (GPU) in order to speed up the process. Finally, the model is evaluated and compared with the existing models on three different datasets in terms of run time, concordance index, and calibration curve, and the most related genes to survival are discovered. Finally, the biological pathways and GO molecular functions are analyzed for these significant genes. Results. We fine-tuned our autoencoder model on RNA-seq data of three datasets to train the weights in our survival prediction model, then using different samples in each dataset for testing the model. The results show that the proposed AutoCox and AutoRandom algorithms based on our feature selection autoencoder approach have better concordance index results comparing the most recent deep learning approaches when applied to each dataset. Each gene resulting

关键词： Survival analysis Deep learning Autoencoder Breast cancer Cox regression graphical processing unit RNAseq data

来源：评论

学校读者我要写书评

暂无评论

GEDS: GPU execution of spatio-temporal queries over spatio-temporal data streams

引用

Journal of Embedded Computing 2011年第3,4期4卷 117-130页

作者： Cazalas, Jonathan Guha, Ratan School of Electrical Engineering and Computer Science University of Central Florida Orlando FL USA

Much research exists for the efficient processing of spatio-temporal data streams. However, all methods ultimately rely on an ill-equipped processor [22], namely a CPU, to evaluate concurrent, continuous spatio-temporal queries over these data streams. This paper presents GEDS, a scalable, Graphics processing unit (GPU)-based framework for the evaluation of continuous queries over spatio-temporal data streams. Specifically, GEDS employs the computation sharing and parallel processing paradigms to deliver scalability in the evaluation of continuous, spatio-temporal range queries and continuous, spatio-temporal kNN queries. The GEDS framework utilizes the parallel processing capability of the GPU, a stream processor by trade, to handle the computation required in this application. Experimental evaluation shows promising performance and shows the scalability and efficacy of GEDS in spatio-temporal data streaming environments. Additional performance studies demonstrate that, even in light of the costs associated with memory transfers, the parallel processing power provided by GEDS clearly counters and outweighs any associated costs.

关键词： Spatio-temporal data streams computation sharing parallel processing location-based services mobile database systems continuous query range query kNN graphical processing unit GPU

来源：评论

学校读者我要写书评

暂无评论

Weak Signal Enhance Based on the Neural Network Assisted Empirical Mode Decomposition

引用

SENSORS 2020年第12期20卷 3373.-3373.页

作者： Chen, Kai Xie, Kai Wen, Chang Tang, Xin-Gong Yangtze Univ Natl Demonstrat Ctr Expt Elect & Elect Educ Jingzhou 434023 Peoples R China Yangtze Univ Sch Comp Sci Jingzhou 434023 Peoples R China Yangtze Univ Sch Elect & Informat Jingzhou 434023 Peoples R China Yangtze Univ Key Lab Explorat Technol Oil & Gas Resources Minist Educ Wuhan 430100 Peoples R China

In order to enhance weak signals in strong noise background, a weak signal enhancement method based on EMDNN (neural network-assisted empirical mode decomposition) is proposed. This method combines CEEMD (complementary ensemble empirical mode decomposition), GAN (generative adversarial networks) and LSTM (long short-term memory), it enhances the efficiency of selecting effective natural mode components in empirical mode decomposition, thus the SNR (signal-noise ratio) is improved. It can also reconstruct and enhance weak signals. The experimental results show that the SNR of this method is improved from 4.1 to 6.2, and the weak signal is clearly recovered.

关键词： weak signal strong background noises complete ensemble empirical mode graphical processing unit parallel computing cyclic neural network generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Accelerating calculations of RNA secondary structure partition functions using GPUs

引用

ALGORITHMS FOR MOLECULAR BIOLOGY 2013年第1期8卷 29-29页

作者： Stern, Harry A. Mathews, David H. Univ Rochester Ctr Integrated Res Comp Rochester NY 14627 USA Univ Rochester Med Ctr Dept Biochem & Biophys Rochester NY 14642 USA Univ Rochester Med Ctr Ctr RNA Biol Rochester NY 14642 USA

Background: RNA performs many diverse functions in the cell in addition to its role as a messenger of genetic information. These functions depend on its ability to fold to a unique three-dimensional structure determined by the sequence. The conformation of RNA is in part determined by its secondary structure, or the particular set of contacts between pairs of complementary bases. Prediction of the secondary structure of RNA from its sequence is therefore of great interest, but can be computationally expensive. In this work we accelerate computations of base-pair probababilities using parallel graphics processing units (GPUs). Results: Calculation of the probabilities of base pairs in RNA secondary structures using nearest-neighbor standard free energy change parameters has been implemented using CUDA to run on hardware with multiprocessor GPUs. A modified set of recursions was introduced, which reduces memory usage by about 25%. GPUs are fastest in single precision, and for some hardware, restricted to single precision. This may introduce significant roundoff error. However, deviations in base-pair probabilities calculated using single precision were found to be negligible compared to those resulting from shifting the nearest-neighbor parameters by a random amount of magnitude similar to their experimental uncertainties. For large sequences running on our particular hardware, the GPU implementation reduces execution time by a factor of close to 60 compared with an optimized serial implementation, and by a factor of 116 compared with the original code. Conclusions: Using GPUs can greatly accelerate computation of RNA secondary structure partition functions, allowing calculation of base-pair probabilities for large sequences in a reasonable amount of time, with a negligible compromise in accuracy due to working in single precision. The source code is integrated into the RNAstructure software package and available for download at http://***.

关键词： RNA Secondary structure Partition function graphical processing unit CUDA

来源：评论

学校读者我要写书评

暂无评论

NeuroGPU: Accelerating multi-compartment, biophysically detailed neuron simulations on GPUs

引用

JOURNAL OF NEUROSCIENCE METHODS 2022年第0期366卷 109400-109400页

作者： Ben-Shalom, Roy Ladd, Alexander Artherya, Nikhil S. Cross, Christopher Kim, Kyung Geun Sanghevi, Hersh Korngreen, Alon Bouchard, Kristofer E. Bender, Kevin J. Univ Calif San Francisco Kavli Inst Fundamental Neurosci Weill Inst Neurosci San Francisco CA USA Univ Calif San Francisco Dept Neurol San Francisco CA USA Univ Calif Davis MIND Inst Davis CA USA Lawrence Berkeley Natl Lab Computat Res Div Berkeley CA USA Univ Calif Berkeley Hellen Wills Neurosci Inst Berkeley CA USA Univ Calif Berkeley Redwood Ctr Theoret Neurosci Berkeley CA USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA USA Lawrence Berkeley Natl Lab Biol Syst & Engn Div Berkeley CA USA Bar Ilan Univ Leslie & Susan Gonda Multidisciplinary Brain Res Ramat Gan Israel Bar Ilan Univ Mina & Everard Goodman Fac Life Sci Ramat Gan Israel

Background: The membrane potential of individual neurons depends on a large number of interacting biophysical processes operating on spatial-temporal scales spanning several orders of magnitude. The multi-scale nature of these processes dictates that accurate prediction of membrane potentials in specific neurons requires the utilization of detailed simulations. Unfortunately, constraining parameters within biologically detailed neuron models can be difficult, leading to poor model fits. This obstacle can be overcome partially by numerical optimization or detailed exploration of parameter space. However, these processes, which currently rely on central processing unit (CPU) computation, often incur orders of magnitude increases in computing time for marginal improvements in model behavior. As a result, model quality is often compromised to accommodate compute resources. New Method: Here, we present a simulation environment, NeuroGPU, that takes advantage of the inherent parallelized structure of the graphics processing unit (GPU) to accelerate neuronal simulation. Results & comparison with existing methods: NeuroGPU can simulate most biologically detailed models 10-200 times faster than NEURON simulation running on a single core and 5 times faster than GPU simulators (CoreNEURON). NeuroGPU is designed for model parameter tuning and best performs when the GPU is fully utilized by running multiple (> 100) instances of the same model with different parameters. When using multiple GPUs, NeuroGPU can reach to a speed-up of 800 fold compared to single core simulations, especially when simulating the same model morphology with different parameters. We demonstrate the power of NeuoGPU through largescale parameter exploration to reveal the response landscape of a neuron. Finally, we accelerate numerical optimization of biophysically detailed neuron models to achieve highly accurate fitting of models to simulation and experimental data. Conclusions: Thus, NeuroGPU is the faste

关键词： Compartmental models Biophysical simulations Conductance-based models Electrophysiology graphical processing unit

来源：评论

学校读者我要写书评

暂无评论

SpineML and Brian 2.0 interfaces for using GPU enhanced Neuronal Networks (GeNN)

引用

BMC Neuroscience 2014年第1期15卷 1-2页

作者： Thomas Nowotny Esin Yavuz Alexander J Cope James Marshall Marcel Stimberg Dan FM Goodman Kevin Gurney CCNR School of Engineering and Informatics University of Sussex Falmer Brighton BN1 9QJ UK Department of Computer Science University of Sheffield Sheffield S1 4DP UK Institut d’Etudes de la Cognition Ecole Normale Supérieure Paris France Harvard Medical School Harvard University Boston MA 02115 USA Department of Psychology University of Sheffield Sheffield S10 2TP UK

来源：评论

学校读者我要写书评

暂无评论

Fast GPU Algorithm for Analyzing Effective Connectivity in Functional Brain Imaging

引用

IFAC Proceedings Volumes 2013年第20期46卷 349-352页

作者： Lawrence Chan Bin Pang Chi-Ren Shyu Tao Chan Pek-Lan Khong Department of Health Technology and Informatics Hong Kong Polytechnic University Hong Kong (Tel: 852-3400-8561) University of Missouri Informatics Institute University of Missouri Columbia Missouri USA Department of Diagnostic Radiology University of Hong Kong Hong Kong

Functional imaging, such as functional Magnetic Resonance Imaging (fMRI), allows the in-vivo study of the human neuronal circuitry. By applying specific environmental stimuli to human subjects, functional imaging detects signals that could indicate direct or indirect neuronal connectivity when they exhibit certain levels of association between brain regions. However, the directed connections cannot be identified using simple statistical approaches, such as pair-wise correlations. Structural Equation Modeling (SEM) is more appropriate for analyzing the causal relationship, called the effective connectivity. SEM is aimed to fit a path model subject to the anatomical constraints using the data collected from imaging study. Such data-driven path analysis involves the minimization of a maximum likelihood (ML) discrepancy function with respect to some constrained path coefficients. The minimization process is iterative. In each of iterations, a constrained coefficient will be switched to unconstrained and added to the pool of the unconstrained for the minimization. The iterations continue until the model attains an acceptable level of parsimonious fit index. The computing time is a big issue because it increases geometrically with the number of unconstrained path coefficients, in other words, the number of iterations. Using Quad-Core Central processing unit (CPU), it takes a month for the iterations from 0 to 30 path coefficients. High speed computing hardware and software can be applied to the optimization process so as to cope with the above-mentioned issue. graphical processing unit (GPU) is a kind of high speed hardware solution that performs ultra-fast algorithmic computation on huge data matrices. This study demonstrates the utilization of GPU with the parallel Genetic Algorithm (GA) replacing the Powell minimization in the standard analysis software package. It is shown in an example of 30 path coefficients that the time taken for the path analysis can be reduced f

关键词： Genetic algorithms Magnetic Resonance Imaging Structural Equation Modeling graphical processing unit Effective connectivity Path model Neuronal circuitry

来源：评论

学校读者我要写书评

暂无评论

Continuous assessment of cardiac output during exercise using real time flow with fast GPU reconstruction

引用

Journal of Cardiovascular Magnetic Resonance 2012年第SUPPL 1期14卷 P232-P232页

作者： Kowalik, Grzegorz T Steeden, Jennifer A Pandya, Bejal Atkinson, David Taylor, Andrew M Muthurangu, Vivek Centre for Cardiovascular MR UCL Institute of Cardiovascular Science London UK UCL Department of Medical Physics & Bioengineering Centre for Medical Image Computing London UK

来源：评论

学校读者我要写书评

暂无评论

Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling

引用

JOURNAL OF MEDICAL SYSTEMS 2018年第1期42卷 2-2页

作者： Wang, Shui-Hua Lv, Yi-Ding Sui, Yuxiu Liu, Shuai Wang, Su-Jing Zhang, Yu-Dong Univ Leicester Dept Informat Leicester LE1 7RH Leics England Nanjing Univ Sch Elect Sci & Engn Nanjing 210046 Jiangsu Peoples R China Nanjing Med Univ Nanjing Brain Hosp Dept Psychiat Nanjing 210029 Jiangsu Peoples R China Inner Mongolia Univ Coll Comp Sci Hohhot 010012 Peoples R China Chinese Acad Sci Inst Psychol Key Lab Behav Sci Beijing 100101 Peoples R China

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149x acceleration in training and a 166x acceleration in test, compared to CPU.

关键词： Alcohol use disorder Data augmentation Convolutional neural network Max pooling Average pooling Stochastic pooling graphical processing unit

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：