Search

• A parallel algorithm for Association rule mining. • Association rule mining of genomics data. • A dynamic workload balancing algorithm for FP-Growth. Association rule mining (ARM) is largely employed in several scientific areas and application domains, and many different algorithms for learning association rules from databases have been introduced. Despite the presence of many existing algorithms, there is still room for the introduction of novel approaches tailored for novel kinds of datasets. Because often the efficiency of such algorithms depends on the type of analyzed dataset. For instance, classical ARM algorithms present some drawbacks for biological datasets produced by microarray technologies in particular containing Single Nucleotide Polymorphisms (SNPs). In particular classical algorithms require large execution times also with small datasets. Therefore the possibility to improve the performance of such algorithms by leveraging parallel computing is a growing research area. The main contributions of this paper are: a comparison among different sequential, parallels and distributed ARM techniques, and the presentation of a novel ARM algorithm, named Balanced Parallel Association Rule Extractor from SNPs (BPARES), that employs parallel computing and a novel balancing strategy to improve response time. BPARES improves performance without loosing in accuracy as well as it handles more efficiently the available computational power and reduces the memory consumption. [ABSTRACT FROM AUTHOR]

We present a new computation method for simulating reflection high-energy electron diffraction and the total-reflection high-energy positron diffraction experiments. The two experiments are used commonly for the structural analysis of material surface. The present paper improves the conventional numerical method, the multi-slice method , for faster computation, since the present method avoids the matrix-eigenvalue solver for the computation of matrix exponentials and can adopt higher-order ordinary differential equation solvers. Moreover, we propose a high-performance implementation based on multi-thread parallelization and cache-reusable subroutines. In our tests, this new method performs up to 2,000 times faster than the conventional method without compromising accuracy. [ABSTRACT FROM AUTHOR]

In fake news detection, intelligent optimization seems to be a more effective and explainable solution methodology than the black-box methods that have been extensively used in the literature. This study takes the optimization-based method one step further and proposes a novel, multi-thread hybrid metaheuristic approach for fake news detection in social media. The most innovative feature of the proposed method is that it uses a supervisor thread mechanism, which simultaneously monitors and improves the performance and search patterns of metaheuristic algorithms running parallel. With the supervisor thread mechanism, it is possible to analyse different key attribute combinations in the search space. In addition, this study develops a software framework that allows this model to be implemented easily. It tests the performance of the proposed model on three different data sets, respectively containing news about Covid-19, the Syrian War, and daily politics. The proposed method is evaluated in comparison to the results of fifteen different well-known deep models and classification algorithms. Experimental results prove the success of the proposed model and that it can produce competitive results., (© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.)

We describe the new version (v2.49t) of the code hfodd which solves the nuclear Skyrme–Hartree–Fock (HF) or Skyrme–Hartree–Fock–Bogolyubov (HFB) problem by using the Cartesian deformed harmonic-oscillator basis. In the new version, we have implemented the following physics features: (i) the isospin mixing and projection, (ii) the finite-temperature formalism for the HFB and HF+BCS methods, (iii) the Lipkin translational energy correction method, (iv) the calculation of the shell correction. A number of specific numerical methods have also been implemented in order to deal with large-scale multi-constraint calculations and hardware limitations: (i) the two-basis method for the HFB method, (ii) the Augmented Lagrangian Method (ALM) for multi-constraint calculations, (iii) the linear constraint method based on the approximation of the RPA matrix for multi-constraint calculations, (iv) an interface with the axial and parity-conserving Skyrme–HFB code hfbtho, (v) the mixing of the HF or HFB matrix elements instead of the HF fields. Special care has been paid to using the code on massively parallel leadership class computers. For this purpose, the following features are now available with this version: (i) the Message Passing Interface (MPI) framework, (ii) scalable input data routines, (iii) multi-threading via OpenMP pragmas, (iv) parallel diagonalization of the HFB matrix in the simplex-breaking case using the ScaLAPACK library. Finally, several little significant errors of the previous published version were corrected. New version program summary: Program title: hfodd (v2.49t) Catalogue identifier: ADFL_v3_0 Program summary URL: http://cpc.cs.qub.ac.uk/summaries/ADFL_v3_0.html Program obtainable from: CPC Program Library, Queenʼs University, Belfast, N. Ireland Licensing provisions: GNU General Public Licence v3 No. of lines in distributed program, including test data, etc.: 190 614 No. of bytes in distributed program, including test data, etc.: 985 898 Distribution format: tar.gz Programming language: FORTRAN-90 Computer: Intel Pentium-III, Intel Xeon, AMD-Athlon, AMD-Opteron, Cray XT4, Cray XT5 Operating system: UNIX, LINUX, Windows XP Has the code been vectorized or parallelized?: Yes, parallelized using MPI RAM: 10 Mwords Word size: The code is written in single-precision for the use on a 64-bit processor. The compiler option -r8 or +autodblpad (or equivalent) has to be used to promote all real and complex single-precision floating-point items to double precision when the code is used on a 32-bit machine. Classification: 17.22 Catalogue identifier of previous version: ADFL_v2_2 Journal reference of previous version: Comput. Phys. Comm. 180 (2009) 2361 External routines: The user must have access to [1.] the NAGLIB subroutine f02axe, or LAPACK subroutines zhpev, zhpevx, zheevr, or zheevd, which diagonalize complex hermitian matrices, [2.] the LAPACK subroutines dgetri and dgetrf which invert arbitrary real matrices, [3.] the LAPACK subroutines dsyevd, dsytrf and dsytri which compute eigenvalues and eigenfunctions of real symmetric matrices, [4.] the LINPACK subroutines zgedi and zgeco, which invert arbitrary complex matrices and calculate determinants, [5.] the BLAS routines dcopy, dscal, dgeem and dgemv for double-precision linear algebra and zcopy, zdscal, zgeem and zgemv for complex linear algebra, or provide another set of subroutines that can perform such tasks. The BLAS and LAPACK subroutines can be obtained from the Netlib Repository at the University of Tennessee, Knoxville: http://netlib2.cs.utk.edu/. Does the new version supersede the previous version?: Yes Nature of problem: The nuclear mean field and an analysis of its symmetries in realistic cases are the main ingredients of a description of nuclear states. Within the Local Density Approximation, or for a zero-range velocity-dependent Skyrme interaction, the nuclear mean field is local and velocity dependent. The locality allows for an effective and fast solution of the self-consistent Hartree–Fock equations, even for heavy nuclei, and for various nucleonic (n-particle–n-hole) configurations, deformations, excitation energies, or angular momenta. Similarly, Local Density Approximation in the particle–particle channel, which is equivalent to using a zero-range interaction, allows for a simple implementation of pairing effects within the Hartree–Fock–Bogolyubov method. Solution method: The program uses the Cartesian harmonic oscillator basis to expand single-particle or single-quasiparticle wave functions of neutrons and protons interacting by means of the Skyrme effective interaction and zero-range pairing interaction. The expansion coefficients are determined by the iterative diagonalization of the mean-field Hamiltonians or Routhians which depend non-linearly on the local neutron and proton densities. Suitable constraints are used to obtain states corresponding to a given configuration, deformation or angular momentum. The method of solution has been presented in: [J. Dobaczewski, J. Dudek, Comput. Phys. Commun. 102 (1997) 166]. Reasons for new version: Version 2.49s of HFODD provides a number of new options such as the isospin mixing and projection of the Skyrme functional, the finite-temperature HF and HFB formalism and optimized methods to perform multi-constrained calculations. It is also the first version of HFODD to contain threading and parallel capabilities. Summary of revisions: [1.] Isospin mixing and projection of the HF states has been implemented. [2.] The finite-temperature formalism for the HFB equations has been implemented. [3.] The Lipkin translational energy correction method has been implemented. [4.] Calculation of the shell correction has been implemented. [5.] The two-basis method for the solution to the HFB equations has been implemented. [6.] The Augmented Lagrangian Method (ALM) for calculations with multiple constraints has been implemented. [7.] The linear constraint method based on the cranking approximation of the RPA matrix has been implemented. [8.] An interface between HFODD and the axially-symmetric and parity-conserving code HFBTHO has been implemented. [9.] The mixing of the matrix elements of the HF or HFB matrix has been implemented. [10.] A parallel interface using the MPI library has been implemented. [11.] A scalable model for reading input data has been implemented. [12.] OpenMP pragmas have been implemented in three subroutines. [13.] The diagonalization of the HFB matrix in the simplex-breaking case has been parallelized using the ScaLAPACK library. [14.] Several little significant errors of the previous published version were corrected. Running time: In serial mode, running 6 HFB iterations for 152Dy for conserved parity and signature symmetries in a full spherical basis of shells takes approximately 8 min on an AMD Opteron processor at 2.6 GHz, assuming standard BLAS and LAPACK libraries. As a rule of thumb, runtime for HFB calculations for parity and signature conserved symmetries roughly increases as , where N is the number of full HO shells. Using custom-built optimized BLAS and LAPACK libraries (such as in the ATLAS implementation) can bring down the execution time by 60%. Using the threaded version of the code with 12 threads and threaded BLAS libraries can bring an additional factor 2 speed-up, so that the same 6 HFB iterations now take of the order of 2 min 30 s. [ABSTRACT FROM AUTHOR]