Accelerating data gravitation-based classification using GPU

Data gravitation-based classification model, a new physic law inspired classification model, has been demonstrated to be an effective classification model for both standard and imbalanced tasks. However, due to its large scale of gravitational computation during the feature weighting process, DGC suffers from high computational complexity, especially for large data sets. In this paper, we address the problem of speeding up gravitational computation using graphics processing unit (GPU). We design a GPU parallel algorithm namely GPU–DGC to accelerate the feature weighting process of the DGC model. Our GPU–DGC model distributes the gravitational computing process to parallel GPU threads, in order to compute gravitation simultaneously. We use 25 open classification data sets to evaluate the parallel performance of our algorithm. The relationship between the speedup ratio and the number of GPU threads is discovered and discussed based on the empirical studies. The experimental results show the effectiveness of GPU–DGC, with the maximum speedup ratio of 87 to the serial DGC. Its sensitivity to the number of GPU threads is also discovered in the empirical studies.

[1]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[2]  Jack J. Purdum,et al.  C programming guide , 1983 .

[3]  Casimir A. Kulikowski,et al.  Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[4]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[5]  Russell C. Eberhart,et al.  Comparison between Genetic Algorithms and Particle Swarm Optimization , 1998, Evolutionary Programming.

[6]  James Kennedy,et al.  Small worlds and mega-minds: effects of neighborhood topology on particle swarm performance , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[7]  H. Yoshida,et al.  A particle swarm optimization for reactive power and voltage control considering voltage security assessment , 1999, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[8]  T. Krink,et al.  Particle swarm optimisation with spatial particle extension , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[9]  O. Weck,et al.  A COMPARISON OF PARTICLE SWARM OPTIMIZATION AND THE GENETIC ALGORITHM , 2005 .

[10]  Andrew Chi-Sing Leung,et al.  An RBF-based compression method for image-based relighting , 2006, IEEE Transactions on Image Processing.

[11]  Andrew Chi-Sing Leung,et al.  Discrete Wavelet Transform on Consumer-Level Graphics Hardware , 2007, IEEE Transactions on Multimedia.

[12]  Andrew Chi-Sing Leung,et al.  Parallelization of cellular neural networks on GPU , 2008, Pattern Recognit..

[13]  Raghavendra D. Prabhu,et al.  SOMGPU: An unsupervised pattern classifier on Graphical Processing Unit , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[14]  Narayana Prasad Padhy,et al.  Comparison of Particle Swarm Optimization and Genetic Algorithm for TCSC-based Controller Design , 2007 .

[15]  Dragan Simic,et al.  Financial Forecasting of Invoicing and Cash Inflow Processes for Fair Exhibitions , 2009, HAIS.

[16]  Bo Yang,et al.  Data gravitation based classification , 2009, Inf. Sci..

[17]  Nathan Srebro,et al.  A GPU-tailored approach for training kernelized SVMs , 2011, KDD.

[18]  Sebastián Ventura,et al.  Weighted Data Gravitation Classification for Standard and Imbalanced Data , 2013, IEEE Transactions on Cybernetics.

[19]  Erich Schikuta,et al.  Multicore and GPU Parallelization of Neural Networks for Face Recognition , 2013, ICCS.

[20]  Qi Li,et al.  Parallel multitask cross validation for Support Vector Machine using GPU , 2013, J. Parallel Distributed Comput..

[21]  Sadoghi Yazdi Hadi,et al.  Gravitation based classification , 2013 .

[22]  L. Chen,et al.  Cognitive gravitation model for classification on small noisy data , 2013, Neurocomputing.

[23]  Sebastián Ventura,et al.  Parallel multi-objective Ant Programming for classification using GPUs , 2013, J. Parallel Distributed Comput..

[24]  Sebastián Ventura,et al.  Parallel evaluation of Pittsburgh rule-based classifiers on GPUs , 2014, Neurocomputing.

[25]  Yuehui Chen,et al.  A new approach for imbalanced data classification based on data gravitation , 2014, Inf. Sci..

[26]  Qian Du,et al.  GPU Parallel Implementation of Support Vector Machines for Hyperspectral Image Classification , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  Nikil D. Dutt,et al.  A GPU-accelerated cortical neural network model for visually guided robot navigation , 2015, Neural Networks.

[28]  Jaume Bacardit,et al.  Large-scale experimental evaluation of GPU strategies for evolutionary machine learning , 2016, Inf. Sci..

[29]  Sebastián Ventura,et al.  Effective lazy learning algorithm based on a data gravitation model for multi-label learning , 2016, Inf. Sci..

[30]  Zeyu Chen,et al.  Particle swarm optimization-based optimal power management of plug-in hybrid electric vehicles considering uncertain driving conditions , 2016 .

[31]  Binod Kumar,et al.  Design and simulation of equilateral triangular microstrip antenna using particle swarm optimization (PSO) and advanced particle swarm optimization (APSO) , 2016 .

[32]  F. Fang,et al.  Estimation of kinetic parameters of an anaerobic digestion model using particle swarm optimization , 2017 .