Search

The wrapper algorithm adopts the performance of the learning algorithm as the evaluation criteria to obtain excellent classification performance. However, the wrapper algorithm is prone to converge prematurely. A global chaotic bat algorithm (GCBA) is put up forward to improve this shortage. First, GCBA applies chaotic map to population initialization to cover the entire solution space. In addition, adaptive learning factors are presented to balance exploration and exploration. The learning factor of local optimal position gradually decreases in the early stage while the learning factor of global optimal position gradually increases in the later stage. Finally, to improve the exploitation, an improved transfer function is proposed, which transfers the continuous space to discrete binary space. GCBA is tested on 14 UCI data sets and 5 gene expression data sets compared with other 6 comparison algorithms. Compared with other algorithms, the results show that GCBA is able to achieve better classification performance. [ABSTRACT FROM AUTHOR]

The Relief algorithm is a feature selection algorithm that uses the nearest neighbor to weight attributes. However, Relief only considers the correlation between features, which leads to a low classification accuracy on noisy datasets whose interaction effect is weak. To overcome the weaknesses of Relief, a novel feature selection algorithm, named Multidirectional Relief (MRelief), is proposed. The MRelief algorithm includes four improvements. First, the multidirectional neighbor search method, which finds all neighbors within a distance threshold from different orientations, is included to obtain regularly distributed neighbors. Therefore, the weights provided by MRelief are more accurate than those provided by Relief. Second, a novel objective function that incorporates the instances' force coefficients is introduced to reduce the influence of noise. Thus, the new objective function improves the classification accuracy of MRelief. Third, subset generation is introduced to the MRelief algorithm and combined with the maximum Pearson maximum distance (MPMD) to generate a promising candidate subset for feature selection. Finally, a novel multiclass margin definition is proposed and introduced to the MRelief algorithm to handle multiclass data. As demonstrated by extensive experiments on eleven UCI datasets and eleven real-world gene expression benchmarking datasets, MRelief is significantly better than other algorithms including LPLIR, ReliefF, LLH-Relief, MultiSURF, MSLIR-NN, MRMR, MPMD and STIR in our study. [ABSTRACT FROM AUTHOR]

The clinical features of EBV-positive diffuse large B cell lymphoma (DLBCL) indicate a poorer prognosis than EBV-negative DLBCL. Currently, there is no efficacious drug for EBV-positive DLBCL. The cytokine interleukin-21 (IL-21) has been reported to be pro-apoptotic in DLBCL cell lines and is being explored as a new therapeutic strategy for this type of lymphomas. However, our previous studies showed that IL-21 stimulation of EBV-positive DLBCL cell lines leads to increased proliferation. Here, analysis of a rare clinical sample of EBV-positive DLBCL, in combination with a NOD/SCID mouse xenograft model, confirmed the effect of IL-21 on the proliferation of EBV-positive DLBCL cells. Using RNA-sequencing, we identified the pattern of differentially-expressed genes following IL-21 treatment and verified the expression of key genes at the protein level using western blotting. We found that IL-21 upregulates expression of the host MYC and AP-1 (composed of related Jun and Fos family proteins) and STAT3 phosphorylation, as well as expression of the viral LMP-1 protein. These proteins are known to promote the G1/S phase transition to accelerate cell cycle progression. Furthermore, in NOD/SCID mouse xenograft model experiments, we found that IL-21 treatment increases glucose uptake and angiogenesis in EBV-positive DLBCL tumours. Although more samples are needed to validate these observations, our study reconfirms the adverse effects of IL-21 on EBV-positive DLBCL, which has implications for the drug development of DLBCL. [ABSTRACT FROM AUTHOR]

For each microarray data set, only a small number of genes are beneficial. Due to the high-dimensional problem, gene selection research work remains a challenge. In order to solve the high-dimensional problem, we propose a dimensionality reduction algorithm named K value maximum relevance minimum redundancy improved grey wolf optimizer (KMR2IGWO). First, in the processing of KMR2, the K genes are selected. Second, the K genes are initialized by two ways according to random selection feature and different proportions of selection feature. Finally, the IGWO algorithm selects the optimal classification accuracy and the optimal combination of gene by adjusting the parameters of fitness function. The algorithm has a significant dimensionality reduction effect and is suitable for high-dimensional data sets. Experimental results show that the proposing KMR2IGWO strategy significantly reduces the dimension of microarray data and removes the redundant features. On the 14 microarray data sets, compared with the four algorithms mRMR + PSO, mRMR + GA, mRMR + BA, mRMR + CS, the proposed algorithm has higher performance in classification accuracy and feature subset length. In five data sets, the proposed algorithm average classification accuracy is 100%. On the 14 data sets, the proposed algorithm has a very significant dimensionality reduction effect, and the dimensionality reduction range is between 0.4% and 0.04%. [ABSTRACT FROM AUTHOR]

Feature selection is an important filtering method for data analysis, pattern classification, data mining, and so on. Feature selection reduces the number of features by removing irrelevant and redundant data. In this paper, we propose a hybrid filter-wrapper feature subset selection algorithm called the maximum Spearman minimum covariance cuckoo search (MSMCCS). First, based on Spearman and covariance, a filter algorithm is proposed called maximum Spearman minimum covariance (MSMC). Second, three parameters are proposed in MSMC to adjust the weights of the correlation and redundancy, improve the relevance of feature subsets, and reduce the redundancy. Third, in the improved cuckoo search algorithm, a weighted combination strategy is used to select candidate feature subsets, a crossover mutation concept is used to adjust the candidate feature subsets, and finally, the filtered features are selected into optimal feature subsets. Therefore, the MSMCCS combines the efficiency of filters with the greater accuracy of wrappers. Experimental results on eight common data sets from the University of California at Irvine Machine Learning Repository showed that the MSMCCS algorithm had better classification accuracy than the seven wrapper methods, the one filter method, and the two hybrid methods. Furthermore, the proposed algorithm achieved preferable performance on the Wilcoxon signed-rank test and the sensitivity-specificity test. [ABSTRACT FROM AUTHOR]

We investigate in this paper nonconvex binary quadratically constrained quadratic programming (QCQP) which arises in various real-life fields. We propose a novel approach of getting quadratic convex reformulation (QCR) for this class of optimization problem. Our approach employs quadratic surrogate functions and convexifies all the quadratic inequality constraints to construct QCR. The price of this approach is the introduction of an extra quadratic inequality. The “best” QCR among the proposed family, in terms that the bound of the corresponding continuous relaxation is best, can be found via solving a semidefinite programming problem. Furthermore, we prove that the bound obtained by continuous relaxation of our best QCR is as tight as Lagrangian bound of binary QCQP. Computational experiment is also conducted to illustrate the solution efficiency improvement of our best QCR when applied in off-the-shell software. [ABSTRACT FROM AUTHOR]