The rapid processing of remote sensing (RS) images is essential in many large-scale real-time monitoring, such as meteorological monitoring and natural disaster warning. However, the computation cost of RS is often ex...
详细信息
The rapid processing of remote sensing (RS) images is essential in many large-scale real-time monitoring, such as meteorological monitoring and natural disaster warning. However, the computation cost of RS is often expensive, traditional RS processingmethods cannot satisfy the time requirement of dynamic monitoring. Fortunately, cloud computing not only provides an effective service for data management, but also offers a convenient way to execute RS computing, It is necessary to integrate the rapid RS processing services in a unified cloud computing architecture. The architecture can provide users with integrated rapid RS imageprocessing service through effective huge data management and distributedparallelprocessing. This paper explores rapid processingmethods and strategies for RS images based on cloud computing. In order to compare with other computing paradigms, we choose the maximum likelihood classification (MLC) as our experimental algorithm and Mahalanobis distance clustering (MDC) as our verifying algorithm to execute comparing. In these experiments, we compare the computation cost of RS processing in three computing paradigms (stand-alone, MPI, and MapReduce). From the intensive experimental results, we find that the RS processing based on cloud computing performs best from the aspects of programming convenience, data management and computational efficiency simultaneously, especially when processing huge amount of data. (C) 2013 Elsevier B.V. All rights reserved.
Non-negative matrix factorization (NMF) is an efficient dimension reduction method and plays an important role in many pattern recognition and computer vision tasks. However, conventional NMF methods are not robust si...
详细信息
Non-negative matrix factorization (NMF) is an efficient dimension reduction method and plays an important role in many pattern recognition and computer vision tasks. However, conventional NMF methods are not robust since the objective functions are sensitive to outliers and do not consider the geometric structure in datasets. In this paper, we proposed a correntropy graph regularized NMF (CGNMF) to overcome the aforementioned problems. CGNMF maximizes the correntropy between data matrix and its reconstruction to filter out the noises of large magnitudes, and expects the coefficients to preserve the intrinsic geometric structure of data. We also proposed a modified version of our CGNMF which construct the adjacent graph by using sparse representation to enhance its reliability. Experimental results on popular image datasets confirm the effectiveness of CGNMF.
In this article we report on our experience in computing resultants of bivariate polynomials on Graphics processing Units (GPU). Following the outline of Collins' modular approach [6], our algorithm starts by mapp...
详细信息
In this article we report on our experience in computing resultants of bivariate polynomials on Graphics processing Units (GPU). Following the outline of Collins' modular approach [6], our algorithm starts by mapping the input polynomials to a finite field for sufficiently many primes m. Next, the GPU algorithm evaluates the polynomials at a number of fixed points x is an element of Z(m), and computes a set of univariate resultants for each modular image. Afterwards, the resultant is reconstructed using polynomial interpolation and Chinese remaindering. The GPU returns resultant coefficients in the form of Mixed Radix (MR) digits. Finally, large integer coefficients are recovered from the MR representation on the CPU. All computations performed by the algorithm (except for, partly, Chinese remaindering) are outsourced to the graphics processor thereby minimizing the amount of work to be done on the host machine. The main theoretical contribution of this work is the modification of Collins' modular algorithm using the methods of matrix algebra to make an efficient realization on the GPU feasible. According to the benchmarks, our algorithm outperforms a CPU-based resultant algorithm from 64-bit Maple 14 by a factor of 100. (C) 2012 Elsevier Inc. All rights reserved.
There are many imageprocessing techniques based on partial differential equations that perform well, but they consume much computational time. It's vital that rapid and efficient ways of solving these equations a...
详细信息
ISBN:
(纸本)9780769550602
There are many imageprocessing techniques based on partial differential equations that perform well, but they consume much computational time. It's vital that rapid and efficient ways of solving these equations are developed. Use of the Laplace transforms permits solution to the time dependent problems in a parallel environment. The solution procedure requires numerical computation of an inverse Laplace transform of which the Stehfest method was examined in the tests. We investigated the performance and efficiency of using the Laplace transform technique for the solution of a mathematical model related to image in-painting and compared the results with temporal integration.
Synchronization is a central issue in concurrency and plays an important role in the behavior and performance of modern programmes. Programming languages and hardware designers are trying to provide synchronization co...
详细信息
ISBN:
(纸本)9780769549712
Synchronization is a central issue in concurrency and plays an important role in the behavior and performance of modern programmes. Programming languages and hardware designers are trying to provide synchronization constructs and primitives that can handle concurrency and synchronization issues efficiently. Programmers have to find a way to select the most appropriate constructs and primitives in order to gain the desired behavior and performance under concurrency. Several parameters and factors affect the choice, through complex interactions among (i) the language and the language constructs that it supports, (ii) the system architecture, (iii) possible run-time environments, virtual machine options and memory management support and (iv) applications. We present a systematic study of synchronization strategies, focusing on concurrent data structures. We have chosen concurrent data structures with different number of contention spots. We consider both coarse-grain and fine-grain locking strategies, as well as lock-free methods. We have investigated synchronization-aware implementations in C++, C# (. NET and Mono) and Java. Considering the machine architectures, we have studied the behavior of the implementations on both Intel's Nehalem and AMD's Bulldozer. The properties that we study are throughput and fairness under different workloads and multiprogramming execution environments. For NUMA architectures fairness is becoming as important as the typically considered throughput property. To the best of our knowledge this is the first systematic and comprehensive study of synchronization-aware implementations. This paper takes steps towards capturing a number of guiding principles and concerns for the selection of the programming environment and synchronization methods in connection to the application and the system characteristics.
Link partition clusters edges of a complex network to discover its overlapping communities. Due to Its effectiveness, link partition has attracted much attentions from the network science community. However, since lin...
详细信息
Link partition clusters edges of a complex network to discover its overlapping communities. Due to Its effectiveness, link partition has attracted much attentions from the network science community. However, since link partition assigns each edge of a network to unique community, it cannot detect the disjoint communities. To overcome this deficiency, this paper proposes a link partition on asymmetric weighted graph (LPAWG) method for detecting overlapping communities. Particularly, LPAWG divides each edge into two parts to distinguish the roles of connected nodes. This strategy biases edges to a specific node and helps assigning each node to its affiliated community. Since LPAWG introduces more edges than those in the original network, it cannot efficiently detect communities from some networks with relative large amount of edges. We therefore aggregate the line graph of LPAWG to shrink its scale. Experimental results of community detection on both synthetic datasets and the realworld networks show the effectiveness of LPAWG comparing with the representative methods.
Multi-objective optimization problems consist of numerous, often conflicting, criteria for which any solution existing on the Pareto front of criterion trade-offs is considered optimal. In this paper we present a gene...
详细信息
ISBN:
(纸本)9783642450082;9783642450075
Multi-objective optimization problems consist of numerous, often conflicting, criteria for which any solution existing on the Pareto front of criterion trade-offs is considered optimal. In this paper we present a general-purpose algorithm designed for solving multi-objective problems (MOPS) on graphics processing units (GPUs). Specifically, a purely asynchronous multi-populous genetic algorithm is introduced. While this algorithm is designed to maximally utilize consumer grade nVidia GPUs, it is feasible to implement on any parallel hardware. The GPU's massively parallel architecture and low latency memory result in + 125 times speed-up for proposed parametrization relative to single threaded CPU implementations. The algorithm, NSGA-AD, consistently solves for solution sets of better or equivalent quality to state-of-the-art methods.
The mathematical basis of mathematical morphology is set theory, which is widely used in the field of imageprocessing, and distributed computing methods will require significant computing resources case that is broke...
详细信息
Understanding of the human brain functioning currently represents a challenging problem. In contrast to usual serial computers and complicated hierarchically organized artificial man-made systems, decentralized, paral...
Understanding of the human brain functioning currently represents a challenging problem. In contrast to usual serial computers and complicated hierarchically organized artificial man-made systems, decentralized, parallel and distributed information processing principles are inherent to the brain. Besides adaptation and learning, which play a crucial role in brain functioning, oscillatory neural activity, synchronization and resonance accompany the brain work. Neural-like oscillatory network models, designed by the authors for imageprocessing, allow to elucidate the capabilities of dynamical, synchronization-based types of imageprocessing, presumably exploited by the brain. The oscillatory network models, studied by means of computer modeling and qualitative analysis, are presented and discussed in the book. Some other problems of paralleldistributed information processing are also considered, such as a recall process from network memory for large-scale recurrent associative memory neural networks, performance of oscillatory networks of associative memory, dynamical oscillatory network methods of imageprocessing with synchronization-based performance, optical parallel information processing based on the nonlinear optical phenomenon of photon echo, and modeling random electric fields of quasi-monochromatic polarized light beams using systems of superposed stochastic oscillators. This makes the book highly interesting to researchers dealing with various aspects of parallel information processing.
Semi-supervised clustering aims at boosting the clustering performance on unlabeled samples by using labels from a few labeled samples. Constrained NMF (CNMF) is one of the most significant semi-supervised clustering ...
详细信息
ISBN:
(纸本)9781479914821
Semi-supervised clustering aims at boosting the clustering performance on unlabeled samples by using labels from a few labeled samples. Constrained NMF (CNMF) is one of the most significant semi-supervised clustering methods, and it factorizes the whole dataset by NMF and constrains those labeled samples from the same class to have identical encodings. In this paper, we propose a novel soft-constrained NMF (SCNMF) method by softening the hard constraint in CNMF. Particularly, SCNMF factorizes the whole dataset into two lower-dimensional factor matrices by using multiplicative update rule (MUR). To utilize the labels of labeled samples, SCNMF iteratively normalizes both factor matrices after updating them with MURs to make encodings of labeled samples close to their label vectors. It is therefore reasonable to believe that encodings of unlabeled samples are also close to their corresponding label vectors. Such strategy significantly boosts the clustering performance even when the labeled samples are rather limited, e.g., each class owns only a single labeled sample. Since the normalization procedure never increases the computational complexity of MUR, SCNMF is quite efficient and effective in practices. Experimental results on face image datasets illustrate both efficiency and effectiveness of SCNMF compared with both NMF and CNMF.
暂无评论