Anping Song

Multi-objective association rule mining with binary bat algorithm

Association rule mining meeting a variety of measures is regarded as a multi-objective optimization problem rather than a single objective optimization problem. The convergent speed of traditional multi-objective algorithms such as genetic algorithm is slow and the efficiency of these algorithms is low. Furthermore, the rules generated by traditional multi-objective algorithms are too large to be efficiently analyzed and explored in any further process. Bat algorithm is a new efficient global optimal algorithm whose convergence is superior to binary particle swarm optimization (BPSO) and genetic algorithm. This paper discusses the application of multi-objective bat algorithm to association rule mining. We propose multi-objective binary bat algorithm (MBBA) based on Pareto for association rule mining. This algorithm is independent of minimum support and minimum confidence. To evaluate the association rules mined by MBBA algorithm, we propose a new method to discover interesting association rules without favoring or excluding any measure. Compared with the single-objective BPSO, binary bat algorithm (BBA) and Apriori algorithm, the experimental results on six datasets show that the new algorithm is feasible and highly effective. It can make up the shortage of single objective algorithms and traditional association rule mining algorithms.

Parallel Numerical Simulations of Three-Dimensional Electromagnetic Radiation with MPI-CUDA Paradigms

Using parallel computation can enhance the performance of numerical simulation of electromagnetic radiation and get great runtime reduction. We simulate the electromagnetic radiation calculation based on the multicore CPU and GPU Parallel Architecture Clusters by using MPI-OpenMP and MPI-CUDA hybrid parallel algorithm. This is an effective solution comparing to the traditional finite-difference time-domain method which has a shortage in the calculation of the electromagnetic radiation on the problem of inadequate large data space and time. What is more, we use regional segmentation, subregional data communications, consolidation, and other methods to improve procedures nested parallelism and finally verify the correctness of the calculation results. Studying these two hybrid models of parallel algorithms run on the high-performance cluster computer, we draw the conclusion that both models are suitable for large-scale numerical calculations, and MPI-CUDA hybrid model can achieve higher speedup.

Clustering Gene Expression Data Based on Harmony Search and K-harmonic Means

Clustering is one of the most commonly data explorer techniques in Data Mining. K-harmonic means clustering (KHM) is an extension of K-means (KM) and solves the problem of KM initialization using a built-in boosting function. However, it is also suffering from running into local optima. As a stochastic global optimization technique, harmony search (HS) can solve this problem. HS-based KHM, HSKHM not only helps KHM clustering escaping from local optima but also overcomes the shortcoming of slow convergence speed of HS. In this paper, we proposed a hybrid data-clustering algorithm, HSKHM. The experimental results on four real gene expression datasets indicate that HSKHM is superior KHM and HS in most cases. The HSKHM algorithm not only improves the convergence speed of HS but also helps KHM escaping from local optima.

A multi-domain decomposition strategy for the lattice Boltzmann method for steady-state flows

ABSTRACT The lattice Boltzmann method (LBM) is a potent numerical technique based on kinetic theory. It can effectively simulate the steady-state and unsteady-state flow problems. A multi-domain decomposition strategy is developed for the LBM in order to accelerate the rate of convergence in different domains by the relative error in the different regions of the steady-state flow. In addition, the proposed method can effectively reduce the amount of calculations required and improve numerical stability. Numerical experiments involving both two- and three-dimensional steady-state flows demonstrate drastically improved computational efficiency and superior numerical stability over the popular lattice Bathnagar-Gross-Krook (BGK) model. Moreover, for unsteady-state flow problems, the presented method can also be used to obtain the flow phenomenon of some unsteady-state flows by choosing the suitable parameter.

Scalable Parallel Algorithm of Multiple-Relaxation-Time Lattice Boltzmann Method with Large Eddy Simulation on Multi-GPUs

The lattice Boltzmann method (LBM) has become an attractive and promising approach in computational fluid dynamics (CFD). In this paper, parallel algorithm of D3Q19 multi-relaxation-time LBM with large eddy simulation (LES) is presented to simulate 3D flow past a sphere using multi-GPUs (graphic processing units). In order to deal with complex boundary, the judgement method of boundary lattice for complex boundary is devised. The 3D domain decomposition method is applied to improve the scalability for cluster, and the overlapping mode is introduced to hide the communication time by dividing the subdomain into two parts: inner part and outer part. Numerical results show good agreement with literature and the 12 Kepler K20M GPUs perform about 5100 million lattice updates per second, which indicates considerable scalability.

Utilizing Bat Algorithm to Optimize Membership Functions for Fuzzy Association Rules Mining

In numerous studies on fuzzy association rules mining, membership functions are usually provided by experts. It is unrealistic to predefine appropriate membership functions for every different dataset in real-world applications. In order to solve the problem, metaheuristic algorithms are applied to the membership functions optimization. As a popular metaheuristic method, bat algorithm has been successfully applied to many optimization problems. Thus a novel fuzzy decimal bat algorithm for association rules mining is proposed to automatically extract membership functions from quantitative data. This algorithm has enhanced local and global search capacity. In addition, a new fitness function is proposed to evaluate membership functions. The function takes more factors into account, thus can assess the number of obtained association rules more accurately. Proposed algorithm is compared with several commonly used metaheuristic methods. Experimental results show that the proposed algorithm has better performance, and the new fitness function can evaluate the quality of membership functions more reasonably.