In the first method, microarray data has been classified directly with SVM method. In the second method, all ICA components have been employed to train SVM. As can be seen, the proposed algorithm yields the highest value of correctness rate in compare with other methods in two datasets (breast and lung cancer datasets). By way of illustration, our proposed algorithm exhibits relative selleck product improvements of 3.3% over ICA + SVM and SVM algorithms in Lung cancer dataset. Furthermore, it is obvious that if all ICs are used to reconstruct new samples, correctness rate of sub-classifier will

not always be better than employing υ-SVM directly, while, with selecting an appropriate set of ICs, the result improves. Table 4 Comparing proposed algorithm with other existing methods

concerning highest correctness rate CONCLUSION Cancer gene expression profiles are not normally-distributed, either on the complete-experiment or on the individual-gene level.[30] Instead, they exhibit complex, heavy-tailed distributions characterized by statistically-significant skewness and kurtosis. The non-Gaussian distribution of this data affects identification of differentially-expressed genes, functional annotation, and prospective molecular classification. These effects may be reduced in some circumstances, although not completely eliminated, by using nonparametric analytics. In this paper, in order to resolve instability problem of ICs analysis algorithm, selective ICA

algorithm has been used. In this algorithm, samples reconstruction error has been employed to select an independent set of algorithms used in time series analysis. Samples are reconstructed by a set of ICs, and modified SVM sub-classifiers are trained, simultaneously and eventually, best sub-classifier with the highest correctness rate is selected using majority voting method. Suggested algorithm has been applied on three samples of microarray data, and in each sample, correctness rate of 25 sub-classifiers and also general correctness rate are calculated and compared. Simulation results were illustrated that proposed Dacomitinib algorithm leads to reduce the dimension of microarray data and the classification accuracy improves because of using υ-SVM classifier. Also the feasibility and validity of the proposed algorithm has been improved in compare with other existence methods shown in Table 4. Footnotes Source of Support: Nil Conflict of Interest: None declared
It has been shown that the static and dynamic parameters of sperms may determine the chance of pregnancy.[1,2] Therefore, human sperm analysis has great importance for clinical study of the male infertility.[3] In recent years, the ability of analyzing sperm behavior has been provided by using microscopic imaging from human semen.[4] In this method, images which have been captured from semen specimens, are analyzed manually by an expert person.