Method for parallel construction of a committee of decision tree for processing the electroencephalography signals.

*(English. Russian original)*Zbl 1175.92008
Mosc. Univ. Comput. Math. Cybern. 33, No. 1, 45-50 (2009); translation from Vestn. Mosk. Univ., Ser. XV 2009, No. 1, 43-49 (2009).

Summary: A method for parallel construction of a classifier ensemble for solving the problem of localization of neuron sources within the brain on the basis of the analysis of electroencephalography signals is described. The idea of the proposed parallel numerical method consists in the consideration of the source parameters as attributes of decision tress constructed in parallel. The method is based on formation of a training data set from an experimental signal and construction of a classifier on the basis of the value of error of the potential, that is, the difference between the measured and model values of the potential.

The efficiency of parallelization of the localization problem, namely, the data distribution between processors, and the distributed training of the ensembles of decision trees are considered. Analysis of the scalability of the problem of construction of a classifier ensemble with increase in the number of processors in the course of solution of the problem of localization of a neuron source on multiprocessor computational complexes is presented. The parallel source localization algorithm is developed for architectures with either common or distributed memory. The algorithm is realized using the MPI technology; a hybrid model of parallel calculations using MPI and OpenMPI is also discussed.

The efficiency of parallelization of the localization problem, namely, the data distribution between processors, and the distributed training of the ensembles of decision trees are considered. Analysis of the scalability of the problem of construction of a classifier ensemble with increase in the number of processors in the course of solution of the problem of localization of a neuron source on multiprocessor computational complexes is presented. The parallel source localization algorithm is developed for architectures with either common or distributed memory. The algorithm is realized using the MPI technology; a hybrid model of parallel calculations using MPI and OpenMPI is also discussed.

##### MSC:

92C20 | Neural biology |

92C55 | Biomedical imaging and signal processing |

65Y05 | Parallel numerical computation |

PDF
BibTeX
Cite

\textit{E. A. Popova}, Mosc. Univ. Comput. Math. Cybern. 33, No. 1, 45--50 (2009; Zbl 1175.92008); translation from Vestn. Mosk. Univ., Ser. XV 2009, No. 1, 43--49 (2009)

Full Text:
DOI

##### References:

[1] | J. Mosher, M. Leahy, and P. Lewis, ”EEG and MEG: Forward Solutions for Inverse Methods,” IEEE Trans. Biomed. Eng. 46, 245–259 (1999). |

[2] | E. A. Popova, ”Ensemble of Decision Trees for Localization of Neural Sources of Brain,” Vestn. Mosk. Univ., Ser. 15: Vychisl. Mat. Kibern., No. 3, 46–55 (2008) [Mosk. Univ. Comp. Math. Cybern. 32, 167–176 (2008)]. |

[3] | M. Mehta, R. Agrawal, and J. Rissanen, ”SLIQ: a Fast Scalable Classifier for Data Mining,” in Proc. of the Fifth Int. Conf. on Ext. Database Technology, Avignon, France, March 25–29, 1996 (Springer-Verlag, 1996), pp. 18–32. |

[4] | J. Shafer, R. Agrawal, and M. Mehta, ”SPRINT: a Scalable Parallel Classifier for Data Mining,” in Proc. 22 Int. Conf. on Very Large Databases, Bombay, India, Sept. 3–6, 1996 (Morgan Kaufmann, Bombay, 1996), pp. 544–555. |

[5] | R. Jin and J. Agrawal, ”Communication and Memory Efficient Parallel Decision Tree Construction” in Proc. of the Third SIAM Int. Conf. on DM, San Francisco, CA, May 1–3, 2003 (SIAM, San Francisco, 2003), pp. 571–576. |

[6] | L. Breiman, ”Random Forests,” Machine Learning 45(3), 5–32 (2001). · Zbl 1007.68152 |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.