The algorithm based on Maximal Information Coefficient is a frontier algorithm in Big Data field
Since this algorithm has a very high complexity of time
it is very slow to process the big data. To solve this problem
the adaptive and fast algorithm based on Maximal Information Coefficient is proposed. This new algorithm which is realized through multithreading improves the speed of the data processing. For the different variables of quantity
a different parallel strategy was put forward. And the number of thread is based on the core of CPU through a tactic. As a result
this algorithm improve the efficiency of the original algorithm based on Maximal Information Coefficient dramatically.
关键词
Keywords
references
Mokhtar B A. On a robust correlation coefficient[J]. The Statistician, 1990, 39(4): 455-460. DOI: 455
战泉茹. 基于最大信息系数的人脸特征选择[D]. 长春: 东北师范大学, 2013: 7-13.
Reshef D N, Reshef Y A, Finucane H K, et al. Detecting novel associations in large data sets[J]. Science, 2011, 334(6062): 1518-1524. DOI: 1518
David N R, Yakir A R, Hilary K F. Detecting novel associations in large datasets[J]. Science, 2011, 334(6062): 1518-1524. DOI: 1518
Ernesto P, Rodrigo Q Q, Joydeep B. Nonlinear multivariate analysis of neurophysiological signals[J]. Progress in Neurobiology, 2005, 77(1): 1-37. DOI: 1