Cancer subtype stratification, which may help to make a better decision in treating cancerous patients, is one of the most crucial and challenging problems in cancer studies. To this end, various computational methods...
详细信息
Cancer subtype stratification, which may help to make a better decision in treating cancerous patients, is one of the most crucial and challenging problems in cancer studies. To this end, various computational methods such as Feature selection, which enhances the accuracy of the classification and is an NP-Hard problem, have been proposed. However, the performance of the applied methods is still low and can be increased by the state-of-the-art and efficient methods. We used 11 efficient and popular meta-heuristic algorithms including WCC, LCA, GA, PSO, ACO, ICA, LA, HTS, FOA, DSOS and CUK along with SVM classifier to stratify human breast cancer molecular subtypes using mRNA and micro-RNA expression data. The applied algorithms select 186 mRNAs and 116 miRNAs out of 9692 mRNAs and 489 miRNAs, respectively. Although some of the selected mRNAs and miRNAs are common in different algorithms results, six miRNAs including miR-190b, miR-18a, miR-301a, miR-34c-5p, miR-18b, and miR-129-5p were selected by equal or more than three different algorithms. Further, six mRNAs, including HAUS6, LAMA2, TSPAN33, PLEKHM3, GFRA3, and DCBLD2, were chosen through two different algorithms. We have reported these miRNAs and mRNAs as important diagnostic biomarkers to the stratification of breast cancer subtypes. By investigating the literature, it is also observed that most of our reported mRNAs and miRNAs have been proposed and introduced as biomarkers in cancer subtypes stratification.
This paper aims to apply the bio-inspired intelligent techniques to optimize the maintenance scheduling of transformers. The study is enhanced with the aid of forest optimization algorithm to reach a schedule of reduc...
详细信息
ISBN:
(纸本)9781509040452
This paper aims to apply the bio-inspired intelligent techniques to optimize the maintenance scheduling of transformers. The study is enhanced with the aid of forest optimization algorithm to reach a schedule of reduced failure rate and decreased insulation life loss of transformers. To verify the effectivity of this approach, the method is tested on a real distribution system consisting of 48 distribution transformers. Test results confirm that the proposed scheduling method is feasible and effective.
The k-Nearest Neighbor (k-NN) algorithm is one of the well-known and most common used algorithms for the classification problems. In this study, we have focused on feature weighted k-NN problems. Two different problem...
详细信息
The k-Nearest Neighbor (k-NN) algorithm is one of the well-known and most common used algorithms for the classification problems. In this study, we have focused on feature weighted k-NN problems. Two different problems are studied. In the first problem, k value and the weights of each feature are optimized to maximize the classification accuracy. Objective function of the problem is nonconvex and nonsmooth. As a solution approach, forest optimization algorithm (FOA), which is a newly introduced evolutionary algorithm, has been considered. Two different algorithms based on FOA are proposed. In the latter problem, class dependency on the feature weights is considered and class dependent feature weighted k-NN problem is studied where the feature weights are different for each class for maximizing the classification accuracy. A solution algorithm again based on FOA is proposed. All proposed algorithms are tested on different benchmark data sets and the numerical results are reported. Performances of the algorithms are also compared with the other algorithms from the other studies in the literature.
暂无评论