As both clinical and cognitive neuroscience matures, the need for sophisticated neuroimaging analyses becomes more important. The use of imaging markers to predict clinical outcomes, or even imaging outcomes, can have...
详细信息
As both clinical and cognitive neuroscience matures, the need for sophisticated neuroimaging analyses becomes more important. The use of imaging markers to predict clinical outcomes, or even imaging outcomes, can have great impact on public health. However, such analyses are still under development since it is challenging for several reasons: 1) the images are of high dimension, and 2) the images may exhibit complex spatial correlation structure. Bayesian methods play an important role in solving these problems by dealing with spatial data flexibly and applying efficient sampling algorithms. This dissertation aims to develop spatial Bayesian models to predict either scalar or imaging outcomes by using imaging predictors and seeks computationally efficient approaches.
In Chapter I, we propose a Bayesian scalar-on-image regression model with application to Multiple Sclerosis (MS) Magnetic Resonance Imaging (MRI) data. Specifically, we build up a multinomial logistic regression model to predict the clinical subtypes of MS patients by using their 3D MRI lesion data. Parameters corresponding to MRI predictors are spatially varying in the image space and are assumed to have a Gaussian Process (GP) prior distribution. Since the covariates are highly correlated, we use the Hamiltonian Monte Carlo algorithm, which is more statistically efficient than other Markov Chain Monte Carlo methods when the parameters are highly correlated. Finally, to reduce computational burden, we code the problem to run in parallel on a graphical processing unit. Results from simulation studies and a real MS data set show that our method has high prediction accuracy as evaluated by leave-one-out cross validation using an importance-sampling scheme.
In Chapter ii, we propose a novel image-on-image regression model, by extending a spatial Bayesian latent factor model to neuroimaging data, where low dimensional latent factors are adopted to make connections between high-dimensional image outcomes a
3D image registration is one of the most fundamental and computationally expensive operations in medical image analysis. Here, we present a mixed-precision, Gauss–Newton–Krylov solver for diffeomorphic registration ...
详细信息
We describe and demonstrate an optimization-based x-ray image reconstruction framework called Adorym. Our framework provides a generic forward model, allowing one code framework to be used for a wide range of imaging ...
详细信息
With the development of intelligent traffic system, high-definition cameras are spread along the urban roads. These devices transmit real-time captured images to data center for multi-purpose usability, but these brin...
详细信息
Predicting the performance of an application running on parallel computing platforms is increasingly becoming important because of its influence on development time and resource management. However, predicting the per...
详细信息
Predicting the performance of an application running on parallel computing platforms is increasingly becoming important because of its influence on development time and resource management. However, predicting the performance with respect to parallel processes is complex for iterative and multi-stage applications. This research proposes a performance approximation approach FiM to predict the calculation time with FiM-Cal and communication time with FiM-Com of an application running on a distributed framework. FiM-Cal consists of two key components that are coupled with each other: (1) a Stochastic. Markov Model to capture non-deterministic runtime that often depends on parallel resources, e.g., number of processes, and (2) a machine-learning model that extrapolates the parameters for calibrating our Markov model when we have changes in application parameters such as dataset. Along with the parallel calculation time, parallel computing platforms consume some data transfer time to communicate among different nodes. FiM-Com consists of a simulation queuing model to quickly estimate communication time. Our new modeling approach considers different design choices along multiple dimensions, namely (i) process-level parallelism, (ii) distribution of cores on multi-processor platform, (iii) application related parameters, and (iv) characteristics of datasets. The major contribution of our prediction approach is that FiM can provide an accurate prediction of parallelprocessing time for the datasets that have a much larger size than that of the training datasets. We evaluate our approach with NAS parallel Benchmarks and real iterative data processing applications. We compare the predicted results (e.g., end-to-end execution time) with actual experimental measurements on a real distributed platform. We also compare our work with an existing prediction technique based on machine learning. We rank the number of processes according to the actual and predicted results from FLM an
Detection of strongly connected component (SCC) on the GPU has become a fundamental operation to accelerate graph computing. Existing SCC detection methods on multiple GPUs introduce massive unnecessary data transform...
详细信息
ISBN:
(数字)9781728133201
ISBN:
(纸本)9781728133218
Detection of strongly connected component (SCC) on the GPU has become a fundamental operation to accelerate graph computing. Existing SCC detection methods on multiple GPUs introduce massive unnecessary data transformation between multiple GPUs. In this paper, we propose a novel distributed SCC detection approach using multiple GPUs plus CPU. Our approach includes three key ideas: (1) segmentation and labeling over large-scale datasets; (2) collecting and merging the segmented SCCs; and (3) running tasks assignment over multiples GPUs and CPU. We implement our approach under a hybrid distributed architecture with multiple GPUs plus CPU. Our approach can achieve device-level optimization and can be compatible with the state-of-the-art algorithms. We conduct extensive theoretical and experimental analysis to demonstrate efficiency and accuracy of our approach. The experimental results expose that our approach can achieves 11.2×, 1.2×, 1.2× speedup for SCC detection using NVIDIA K80 compared with Tarjan's, FB-Trim, and FB-Hybrid algorithms respectively.
The aim of this paper is to establish the homogenization approach that eliminates the difficulties encountered by the conventional numerical methods in analyzing thermal behavior of the multi-material component system...
详细信息
The aim of this paper is to establish the homogenization approach that eliminates the difficulties encountered by the conventional numerical methods in analyzing thermal behavior of the multi-material component systems with minimum computational resources. Analysis of problems with intricacies or larger domains can be made simpler through finite element assisted homogenization approach. In this paper, applicability of homogenization approach is verified by considering two cases (i) composite with voids and (ii) composite with fibers distributed randomly. Fiber randomness case is investigated by Digital image-Based (DIB) modeling technique in association with MATLAB'S imageprocessing module. Also effect of transverse fiber crack on the effective thermal conductivity of the composite is studied. Results of homogenization approach compared with micro-mechanics approach yielded maximum percentage deviation of 1.72% for voids case and 1.49% for fiber randomness case.
Background: Bioinformatics research comes into an era of big data. Mining potential value in biological big data for scientific research and health care field has the vital significance. Deep learning as new machine l...
详细信息
Background: Bioinformatics research comes into an era of big data. Mining potential value in biological big data for scientific research and health care field has the vital significance. Deep learning as new machine learning algorithms, on the basis of big data and high performance distributedparallel computing, show the excellent performance in biological big data processing. Objective: Provides a valuable reference for researchers to use deep learning in their studies of processing large biological data. methods: This paper introduces the new model of data storage and computational facilities for big data analyzing. Then, the application of deep learning in three aspects including biological omics data processing, biological imageprocessing and biomedical diagnosis was summarized. Aiming at the problem of large biological data processing, the accelerated methods of deep learning model have been described. Conclusion: The paper summarized the new storage mode, the existing methods and platforms for biological big data processing, and the progress and challenge of deep learning applies in biological big data processing.
Relationships in online social networks often imply social connections in real life. An accurate understanding of relationship types benefits many applications, e.g. social advertising and recommendation. Some recent ...
详细信息
ISBN:
(数字)9781728129037
ISBN:
(纸本)9781728129044
Relationships in online social networks often imply social connections in real life. An accurate understanding of relationship types benefits many applications, e.g. social advertising and recommendation. Some recent attempts have been proposed to classify user relationships into predefined types with the help of pre-labeled relationships or abundant interaction features on relationships. Unfortunately, both relationship feature data and label data are very sparse in real social platforms like WeChat, rendering existing methods inapplicable. In this paper, we present an in-depth analysis of WeChat relationships to identify the major challenges for the relationship classification task. To tackle the challenges, we propose a Local Community-based Edge Classification (LoCEC) framework that classifies user relationships in a social network into real-world social connection types. LoCEC enforces a three-phase processing, namely local community detection, community classification and relationship classification, to address the sparsity issue of relationship features and relationship labels. Moreover, LoCEC is designed to handle large-scale networks by allowing parallel and distributedprocessing. We conduct extensive experiments on the real-world WeChat network with hundreds of billions of edges to validate the effectiveness and efficiency of LoCEC.
Uncertainty quantification is a critical missing component in radio interferometric imaging that will only become increasingly important as the big-data era of radio interferometry emerges. Statistical sampling approa...
详细信息
Uncertainty quantification is a critical missing component in radio interferometric imaging that will only become increasingly important as the big-data era of radio interferometry emerges. Statistical sampling approaches to perform Bayesian inference, like Markov Chain Monte Carlo (MCMC) sampling, can in principle recover the full posterior distribution of the image, from which uncertainties can then be quantified. However, for massive data sizes, like those anticipated from the Square Kilometre Array, it will be difficult if not impossible to apply any MCMC technique due to its inherent computational cost. We formulate Bayesian inference problems with sparsity-promoting priors (motivated by compressive sensing), for which we recover maximum a posteriori (MAP) point estimators of radio interferometric images by convex optimization. Exploiting recent developments in the theory of probability concentration, we quantify uncertainties by post-processing the recovered MAP estimate. Three strategies to quantify uncertainties are developed: (i) highest posterior density credible regions, (ii) local credible intervals (cf. error bars) for individual pixels and superpixels, and (iii) hypothesis testing of image structure. These forms of uncertainty quantification provide rich information for analysing radio interferometric observations in a statistically robust manner. Our MAP-based methods are approximately 10(5) times faster computationally than state-of-theart MCMC methods and, in addition, support highly distributed and parallelized algorithmic structures. For the first time, our MAP-based techniques provide a means of quantifying uncertainties for radio interferometric imaging for realistic data volumes and practical use, and scale to the emerging big data era of radio astronomy.
暂无评论