Paradigms for Effective Parallelization of Inherently Sequential Graph Algorithms on Multi-Core Architectures

The chapter describes two algorithmic paradigms, dubbed speculation and iteration and approximate update, for parallelizing greedy graph algorithms and vertex ordering algorithms, respectively, on multicore architectures. The common challenge in these two classes of algorithms is that the computations involved are inherently sequential. The efficacy of the paradigms in overcoming this challenge is demonstrated via extensive experimental study on two representative algorithms from each class and two Intel multi-core systems. The algorithms studied are (1) greedy algorithms for distance-k coloring (for k = 1 and k = 2) and (2) algorithms for two degree-based vertex orderings. The experimental results show that the paradigms enable the design of scalable methods that to a large extent preserve the quality of solution obtained by the underlying serial algorithms.

Noise Removal from Remote Sensed Images by NonLocal Means with OpenCL Algorithm

We introduce a multi-platform portable implementation of the NonLocal Means methodology aimed at noise removal from remotely sensed images. It is particularly suited for hyperspectral sensors for which real-time applications are not possible with only CPU based algorithms. In the last decades computational devices have usually been a compound of cross-vendor sets of specifications (heterogeneous system architecture) that bring together integrated central processing (CPUs) and graphics processor (GPUs) units. However, the lack of standardization resulted in most implementations being too specific to a given architecture, eliminating (or making extremely difficult) code re-usability across different platforms. In order to address this issue, we implement a multi option NonLocal Means algorithm developed using the Open Computing Language (OpenCL) applied to Hyperion hyperspectral images. Experimental results demonstrate the dramatic speed-up reached by the algorithm on GPU with respect to conventional serial algorithms on CPU and portability across different platforms. This makes accurate real time denoising of hyperspectral images feasible.

An Exact Parallel Algorithm for the Radio k-coloring Problem

For a positive integer k, a radio k-coloring of a simple connected graph G = (V (G), E(G)) is a mapping | f(u) - f(v)| ≥ k +1-d (u , v ) such that f :V (G)→{0,1, 2,...} for each pair of distinct vertices u and v of G, where d(u, v) is the distance between u and v in G. The span of a radio k-coloring f, rck(f), is the maximum integer it assigns to some vertex of G. The radio k-chromatic number, rck(G) of G is min{rck(f)}, where the minimum is taken over all radio k-colorings f of G. If k is the diameter of G, then rck(G) is known as the radio number of G. In this work, we propose four algorithms (two serial algorithms and their parallel versions) which related to the radio k-coloring problem. One of them is an approximate algorithm that determines an upper bound of the radio number of a given graph. The other is an exact algorithm which finds the radio number of a graph G. The approximate algorithm is a polynomial time algorithm while the exact algorithm is an exponential time algorithm. The parallel algorithms are parallelized using the Message Passing Interface (MPI) standard. The experimental results prove the ability of the proposed algorithms to achieve a speedup 7 for 8 processors.

Evaluation of nine HIV rapid test kits to develop a national HIV testing algorithm in Nigeria

Background: Non-cold chain-dependent HIV rapid testing has been adopted in many resource-constrained nations as a strategy for reaching out to populations. HIV rapid test kits (RTKs) have the advantage of ease of use, low operational cost and short turnaround times. Before 2005, different RTKs had been used in Nigeria without formal evaluation. Between 2005 and 2007, a study was conducted to formally evaluate a number of RTKs and construct HIV testing algorithms. Objectives: The objectives of this study were to assess and select HIV RTKs and develop national testing algorithms. Method: Nine RTKs were evaluated using 528 well-characterised plasma samples. These comprised 198 HIV-positive specimens (37.5%) and 330 HIV-negative specimens (62.5%), collected nationally. Sensitivity and specificity were calculated with 95% confidence intervals for all nine RTKs singly and for serial and parallel combinations of six RTKs; and relative costs were estimated. Results: Six of the nine RTKs met the selection criteria, including minimum sensitivity and specificity (both ≥ 99.0%) requirements. There were no significant differences in sensitivities or specificities of RTKs in the serial and parallel algorithms, but the cost of RTKs in parallel algorithms was twice that in serial algorithms. Consequently, three serial algorithms, comprising four test kits (BundiTM, DetermineTM, Stat-Pak® and Uni-GoldTM) with 100.0% sensitivity and 99.1% – 100.0% specificity, were recommended and adopted as national interim testing algorithms in 2007. Conclusion: This evaluation provides the first evidence for reliable combinations of RTKs for HIV testing in Nigeria. However, these RTKs need further evaluation in the field (Phase II) to re-validate their performance.

Parallel Algorithms for Spatial Rainfall Distribution

This paper proposes parallel algorithms for precipitation of flood modelling, especially applied in spatial rainfall distribution. As an important input in flood modelling, spatial distribution of rainfall is always needed as a pre-conditioned model. In this paper two interpolation methods, Inverse distance weighting (IDW) and Ordinary kriging (OK) are discussed. Both are developed in parallel algorithms in order to reduce the computational time. To measure the computation efficiency, the performance of the parallel algorithms are compared to the serial algorithms for both methods. Findings indicate that: (1) the computation time of OK algorithm is up to 23% longer than IDW; (2) the computation time of OK and IDW algorithms is linearly increasing with the number of cells/ points; (3) the computation time of the parallel algorithms for both methods is exponentially decaying with the number of processors. The parallel algorithm of IDW gives a decay factor of 0.52, while OK gives 0.53; (4) The parallel algorithms perform near ideal speed-up.

Analysis and Simulation of the Dynamic Spectrum Allocation Based on Parallel Immune Optimization in Cognitive Wireless Networks

Spectrum allocation is one of the key issues to improve spectrum efficiency and has become the hot topic in the research of cognitive wireless network. This paper discusses the real-time feature and efficiency of dynamic spectrum allocation and presents a new spectrum allocation algorithm based on the master-slave parallel immune optimization model. The algorithm designs a new encoding scheme for the antibody based on the demand for convergence rate and population diversity. For improving the calculating efficiency, the antibody affinity in the population is calculated in multiple computing nodes at the same time. Simulation results show that the algorithm reduces the total spectrum allocation time and can achieve higher network profits. Compared with traditional serial algorithms, the algorithm proposed in this paper has better speedup ratio and parallel efficiency.

An Empirical Study on the Performance of Cost-Sensitive Boosting Algorithms with Different Levels of Class Imbalance

Cost-sensitive boosting algorithms have proven successful for solving the difficult class imbalance problems. However, the influence of misclassification costs and imbalance level on the algorithm performance is still not clear. The present paper aims to conduct an empirical comparison of six representative cost-sensitive boosting algorithms, including AdaCost, CSB1, CSB2, AdaC1, AdaC2, and AdaC3. These algorithms are thoroughly evaluated by a comprehensive suite of experiments, in which nearly fifty thousands classification models are trained on 17 real-world imbalanced data sets. Experimental results show that AdaC serial algorithms generally outperform AdaCost and CSB when dealing with different imbalance level data sets. Furthermore, the optimality of AdaC2 algorithm stands out around the misclassification costs setting:CN=0.7,CP=1, especially for dealing with strongly imbalanced data sets. In the case of data sets with a low-level imbalance, there is no significant difference between the AdaC serial algorithms. In addition, the results indicate that AdaC1 is comparatively insensitive to the misclassification costs, which is consistent with the finding of the preceding research work.