Abstract: Instance selection (IS) technique is used to reduce
the data size to improve the performance of data mining methods.
Recently, to process very large data set, several proposed methods
divide the training set into some disjoint subsets and apply IS
algorithms independently to each subset. In this paper, we analyze
the limitation of these methods and give our viewpoint about how to
divide and conquer in IS procedure. Then, based on fast condensed
nearest neighbor (FCNN) rule, we propose a large data sets instance
selection method with MapReduce framework. Besides ensuring the
prediction accuracy and reduction rate, it has two desirable properties:
First, it reduces the work load in the aggregation node; Second
and most important, it produces the same result with the sequential
version, which other parallel methods cannot achieve. We evaluate the
performance of FCNN-MR on one small data set and two large data
sets. The experimental results show that it is effective and practical.
Abstract: The aim of this paper is to investigate the
performance of the developed two point block method designed for
two processors for solving directly non stiff large systems of higher
order ordinary differential equations (ODEs). The method calculates
the numerical solution at two points simultaneously and produces
two new equally spaced solution values within a block and it is
possible to assign the computational tasks at each time step to a
single processor. The algorithm of the method was developed in C
language and the parallel computation was done on a parallel shared
memory environment. Numerical results are given to compare the
efficiency of the developed method to the sequential timing. For
large problems, the parallel implementation produced 1.95 speed-up
and 98% efficiency for the two processors.
Abstract: With the rapid development in the field of life
sciences and the flooding of genomic information, the need for faster
and scalable searching methods has become urgent. One of the
approaches that were investigated is indexing. The indexing methods
have been categorized into three categories which are the lengthbased
index algorithms, transformation-based algorithms and mixed
techniques-based algorithms. In this research, we focused on the
transformation based methods. We embedded the N-gram method
into the transformation-based method to build an inverted index
table. We then applied the parallel methods to speed up the index
building time and to reduce the overall retrieval time when querying
the genomic database. Our experiments show that the use of N-Gram
transformation algorithm is an economical solution; it saves time and
space too. The result shows that the size of the index is smaller than
the size of the dataset when the size of N-Gram is 5 and 6. The
parallel N-Gram transformation algorithm-s results indicate that the
uses of parallel programming with large dataset are promising which
can be improved further.