Assessing Parallel Heterogeneous Computer Architectures for Multiobjective Feature Selection on EEG Classification

  • Juan José Escobar
  • Julio OrtegaEmail author
  • Jesús González
  • Miguel Damas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9656)


High-dimensional multi-objective optimization will open promising approaches to many applications on bioinformatics once efficient parallel procedures are available. These procedures have to take advantage of the present heterogeneous architectures comprising multicore CPUs and GPUs. In this paper, we describe and analyze several OpenCL implementations for an application comprising multiobjective feature selection for clustering in an EEG classification task on high-dimensional patterns. These implementation alternatives correspond to different uses of multicore CPU and GPU platforms to process irregular data codes. Depending on the dataset used, we have reached speedups of up to 14.9 and 17.2 with up to 24 threads for the implemented OpenCL CPU kernels and of up to 7.1 and 9.1 with up to 13 SMX processors and 256 local work-items for our OpenCL GPU kernels. Nevertheless, to provide this level of performance, careful considerations about the use of the memory hierarchy of the heterogeneous architecture and different strategies to cope with the irregularity of our target application have to be taken into account.


Brain-Computer Interfaces (BCI) EEG classification Feature selection GPU Heterogeneous parallel architectures Multiobjective optimization 



This work has been funded by projects TIN2012-32039 and TIN2015-67020-P (Spanish “Ministerio de Econ. y Compet.” and FEDER funds).


  1. 1.
    Mukhopadhyay, A., et al.: A survey of multiobjective evolutionary algorithms for data mining: part I. IEEE Trans. Evol. Comput. 18(1), 4–19 (2014)CrossRefGoogle Scholar
  2. 2.
    Mukhopadhyay, A., et al.: A survey of multiobjective evolutionary algorithms for data mining: part II. IEEE Trans. Evol. Comput. 8(1), 20–35 (2014)CrossRefGoogle Scholar
  3. 3.
    Rupp, R., Kleih, S.C., Leeb, R., Millán, J.R., Kübler, A., Müller-Putz, G.R.: Brain-computer interfaces and assistive technology. In: Grübler, G., Hildt, E. (eds.) Brain-Computer Interfaces in Their Ethical, Social and Cultural Contexts. The International Library of Ethics, Law and Technology, vol. 12, pp. 7–38. Springer Science-Business Media, Dordrecht (2014). doi: 10.1007/978-94-017-8996-7_2 Google Scholar
  4. 4.
    Collet, P.: Why GPGPUs for evolutionary computation? In: Tsutsui, S., Collet, P. (eds.) Massively Parallel Evolutionary Computation on GPGPUs. Natural Computing Series, pp. 3–14. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  5. 5.
    Teodoro, G., Kurc, T., Andrade, G., Kong, J., Ferreira, R., Saltz, J.: Application performance analysis and efficient execution on systems with multi-core CPUs, GPUs, and MICs: a case study with microscopy image analysis. Intl. J. of High Perform. Comput. Appl. 1–20 (2015). doi: 10.1177/1094342015594519
  6. 6.
    Greg, C.: Hazelwood K. Where is the data? Why you cannot debate CPU vs. GPU performances without the answer. In: IEEE International Symposium on Performance Analysis of Systems and Softwareernational(ISPASS), pp.134–144 (2011)Google Scholar
  7. 7.
    Bellman, G.A.: Adaptive Control Processes: A Guided Tour. Princeton University Press, Princeton (1961)CrossRefzbMATHGoogle Scholar
  8. 8.
    Marinaki, M., Marinakis, Y.: An Island memetic differential evolution algorithm for the feature selection problem. In: Terrazas, G., Otero, F.E., Masegosa, A.D. (eds.) NICSO 2013. SCI, vol. 512, pp. 33–47. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  9. 9.
    Emmanouilidis, C., Hunter, A., MacIntyre, J.: A multiobjective evolutionary setting for feature selection and a commonality-based crossover operator. In: Proceedings of the 2000 Congress on Evolutionary Computation, pp. 309–316. IEEE Press, New York (2000). doi: 10.1109/CEC.2000.870311
  10. 10.
    Handl, J., Knowles, J.: Feature subset selection in unsupervised learning via multiobjective optimization. Int. J. Comput. Intell. Res. 2(3), 217–238 (2006). doi: 10.5019/j.ijcir.2006.64 MathSciNetCrossRefGoogle Scholar
  11. 11.
    Oliveira, L.S., Sabourin, R., Bortolozzi, F., Suen, C.Y.: A methodology for feature selection using multiobjective genetic algorithms for handwritten digit string recognition. Int. J. Pattern Recognit. Artif. Intell. 17(6), 903–929 (2003). doi: 10.1142/S021800140300271X CrossRefGoogle Scholar
  12. 12.
    Kim, Y., Street, W.N., Menczer, F.: Evolutionary model selection in unsupervised learning. Intell. Data Anal. 6(6), 531–556 (2002). doi: 10.1145/347090.347169 zbMATHGoogle Scholar
  13. 13.
    Morita, M., Sabourin, R., Bortolozzi, F., Suen, C.Y.: Unsupervised feature selection using multi-objective genetic algorithms for handwritten word recognition. In: Proceedings of the 7th International Conference on Document Analysis and Recognition, 666–670. IEEE Press, New York (2003). doi: 10.1109/ICDAR.2003.1227746
  14. 14.
    Mierswa, I., Wurst, M.: Information preserving multi-objective feature selection for unsupervised learning. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO 2006, pp. 1545–1552. ACM, New York (2006). doi: 10.1145/1143997.1144248
  15. 15.
    de Souza, T., Matwin, J., Japkowitz, N.: Parallelizing feature selection. Algorithmica 45(3), 433–456 (2006). doi: 10.1007/s00453-006-1220-3 MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Zao, Z., Zhang, R., Cox, J., Duling, D., Sarle, W.: Massively parallel feature selection: an approach based on variance preservation. Mach. Learn. 92(1), 195–220 (2013). doi: 10.1007/s10994-013-5373-4 MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Kimovski, D., Ortega, J., Ortiz, A., Baños, R.: Parallel alternatives for evolutionary multi-objective optimization in unsupervised feature selection. Expert Syst. Appl. 42(9), 4239–4252 (2015). doi: 10.1016/j.eswa.2015.01.061 CrossRefGoogle Scholar
  18. 18.
    Kimovski, D., Ortega, J., Ortiz, A., Baños, R.: Leveraging cooperation for parallel multi-objective feature selection in high-dimensional EEG data. Concurrency: Pract. Experience 27, 5476–5499 (2015)CrossRefGoogle Scholar
  19. 19.
    Arbelaitz, O., Gurrutxaga, I., Muguerza, J., Pérez, J.M., Perona, I.: An externsive comparative study of cluster validity indices. Pattern Recogn. 46(1), 243–256 (2013)CrossRefGoogle Scholar
  20. 20.
    Deb, K., Agrawal, S., Pratab, A., Meyarivan, T.: A fast elitist Non-dominated sorting genetic algorithms for multi-objective optimisation: NSGA-II. In: Deb, K., Rudolph, G., Lutton, E., Merelo, J.J., Schoenauer, M., Schwefel, H.-P., Yao, X. (eds.) PPSN 2000. LNCS, vol. 1917, pp. 849–858. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  21. 21.
  22. 22.
    Forgy, E.: Cluster analysis of multivariate data: efficiency vs interpretability of classification. Biometrics 21, 768 (1965)Google Scholar
  23. 23.
    Fonseca, C.M., López-Ibáñez, M., Paquete, L., Guerreiro, A.P.: Computation of the Hypervolume indicator (2014).
  24. 24.
    Luong, T.V., Melab, N., Talbi, E.-G.: GPU-based island model for evolutionary algorithms. In: GECCO 2010 Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 1089–1096 (2010)Google Scholar
  25. 25.
    Alba, E., Luque, G., Nesmachnow, S.: Parrallel Metaheuristics: recent advances and new trends. Intl. Trans. Op. Res. 20, 1–48 (2013)CrossRefzbMATHGoogle Scholar
  26. 26.
    Pospichal, P., Jaros, J., Schwarz, J.: Parallel genetic algorithm on the CUDA architecture. In: Di Chio, C., Cagnoni, S., Cotta, C., Ebner, M., Ekárt, A., Esparcia-Alcazar, A.I., Goh, C.-K., Merelo, J.J., Neri, F., Preuß, M., Togelius, J., Yannakakis, G.N. (eds.) EvoApplicatons 2010, Part I. LNCS, vol. 6024, pp. 442–451. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  27. 27.
    Sharma, D., Collet, P.: Implementation techniques for massively parallel Multi-objective optimization. In: Tsutsui, S., Collet, P. (eds.) Massively Parallel Evolutionary Computation on GPGPUs, pp. 267–286. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  28. 28.
    Wong, M.L., Cui, G.: Data mining using parallel multi-objective evolutionary algorithms on graphics processing units. In: Tsutsui, S., Collet, P. (eds.) Massively Parallel Evolutionary Computation on GPGPUs, pp. 287–307. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  29. 29.
    Baramkar, P.P., Kulkarni, D.B.: Review for K-means on graphics processing units (GPU). Intl. J. Research & Technology (IJERT) 3(6), 1911–1914 (2014)Google Scholar
  30. 30.
    Kijsipongse, E., U-ruekolan, S.: Dynamic load balancing on GPU clusters for large-scale K-means clustering. In: Proceedings of Ninth International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 346–350 (2012)Google Scholar
  31. 31.
    Farivar, R., Rebolledo, D., Chan, E., Campbell, R.: A Parallel implementation of K-means clustering on GPUs. In: Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), 14–17 July 2008Google Scholar
  32. 32.
    Wu, R., Zhang, B., Hsu, M.: Clustering billions of data points using GPUs. In: Proceedings of UCHPC-MAW 2009 (2009). doi: 10.1145/1531666.1531668
  33. 33.
    Zechner, M., Granitzer, M.: Accelerating K-Means on the Graphics Processor via CUDA. In: Proceedings of First International Conference on Intensive Applications and Services, pp. 7–15 (2009)Google Scholar
  34. 34.
    Fazendeiro, P., Padole, C., Sequeira, P., Prata, P.: OpenCL implementations of a genetic algorithm for feature selection in periocular biometric recognition. In: Panigrahi, B.K., Das, S., Suganthan, P.N., Nanda, P.K. (eds.) SEMCCO 2012. LNCS, vol. 7677, pp. 729–737. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  35. 35.
    Asensio-Cubero, J., Gan, J.Q., Palaniappan, R.: Multiresolution analysis over simple graphs for brain computer interfaces. J. Neural Eng. 10(4), 046014 (2013). doi: 10.1088/1741-2560/10/4/046014 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Juan José Escobar
    • 1
  • Julio Ortega
    • 1
    Email author
  • Jesús González
    • 1
  • Miguel Damas
    • 1
  1. 1.Department of Computer Architecture and TechnologyCITIC, University of GranadaGranadaSpain

Personalised recommendations