http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Multi-label feature selection using density-based graph clustering and ant colony optimization
Kakarash Zana Azeez,Mardukhia Farhad,Moradi Parham 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.1
Multi-label learning is a machine learning subclass that aims to assign more than one label simultaneously for each instance. Many real-world tasks include high-dimensional data which reduces the performance of machine learning methods. To solve this issue, a filter and multi-label feature selection is proposed in this paper. The main idea of the proposed method is to choose highly relevant and non-redundant features with the lowest information loss. The proposed method first uses a novel graph-based density peaks clustering to group similar features to reach this goal. It then uses the ant colony optimization search process to rank features based on their relevancy to a set of labels and also their redundancy with the other features. A graph first represents the feature space, and then a novel density peaks clustering is used to group similar features. Then, the ants are searched through the graph to select a set of non-similar features by remaining in the clusters with a low probability and jumping among the clusters with a high probability. Moreover, in this paper, to evaluate the solutions found by the ants, a novel criterion based on mutual information was used to assign a high pheromone value to highly relevant and non-redundant features. Finally, the final features are chosen based on their pheromone values. The results of experiments on a set of real-world datasets show the superiority of the proposed method over a set of baseline and state-of-the-art methods.
Differential regulation of hepcidin in cancer and noncancer tissues and its clinical implications
Driton Vela,Zana Vela-Gaxha 생화학분자생물학회 2018 Experimental and molecular medicine Vol.50 No.-
Hepcidin is a crucial peptide for regulating cellular iron efflux. Because iron is essential for cell survival, especially for highly active cells, such as tumor cells, it is imperative to understand how tumor cells manipulate hepcidin expression for their own metabolic needs. Studies suggest that hepcidin expression and regulation in tumor cells show important differences in comparison with those in non-tumorous cells. These differences should be investigated to develop new strategies to fight cancer cells. Manipulating hepcidin expression to starve cancer cells for iron may prove to be a new therapy in the anticancer arsenal.
Evidence for the onset of color transparency in ρ<sup>0</sup> electroproduction off nuclei
CLAS Collaboration,El Fassi, L.,Zana, L.,Hafidi, K.,Holtrop, M.,Mustapha, B.,Brooks, W.K.,Hakobyan, H.,Zheng, X.,Adhikari, K.P.,Adikaram, D.,Aghasyan, M.,Amaryan, M.J.,Anghinolfi, M.,Arrington, J.,Ava North-Holland Pub. Co 2012 Physics letters: B Vol.712 No.4
We have measured the nuclear transparency of the incoherent diffractive A(e,e<SUP>'</SUP>ρ<SUP>0</SUP>) process in <SUP>12</SUP>C and <SUP>56</SUP>Fe targets relative to <SUP>2</SUP>H using a 5 GeV electron beam. The nuclear transparency, the ratio of the produced ρ<SUP>0</SUP>@?s on a nucleus relative to deuterium, which is sensitive to ρA interaction, was studied as function of the coherence length (l<SUB>c</SUB>), a lifetime of the hadronic fluctuation of the virtual photon, and the four-momentum transfer squared (Q<SUP>2</SUP>). While the transparency for both <SUP>12</SUP>C and <SUP>56</SUP>Fe showed no l<SUB>c</SUB> dependence, a significant Q<SUP>2</SUP> dependence was measured, which is consistent with calculations that included the color transparency effects.