• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Innovative Computing Information and Control >CLUSTER IDENTIFICATION FOR MICROARRAY GENE EXPRESSION DATA UNDER CONFLICT OF INTEREST
【24h】

CLUSTER IDENTIFICATION FOR MICROARRAY GENE EXPRESSION DATA UNDER CONFLICT OF INTEREST

机译：利益冲突下微阵列基因表达数据的聚类识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In our former deal with conflict analysis, the conflicting information is evaluated by exploiting enhanced variant of FLEXFIS using overlapping clustering methodology. The execution of grouping methodology is assessed by employing two microarray gene expression datasets. Nevertheless, this method has achieved low grouping exactness in arranging the gene expression information. Subsequently, to enhance the gene quality order exactness and fortitude the conflicts, another conflict research method is proposed with modified fuzzy c-means clustering strategy. Our proposed strategy involves four phases viz., MFCM based grouping, fuzzy guidelines framing, conflict analysis and semi supervised learning. The MFCM clustering with our strategy ensures improvement in convergence speed with reduction in plasticity - stability dilemma. The fuzzy principles are created for the grouped information and accordingly the conflict methodology is performed to look at the information which is available in more than one cluster. The choice of MFCM strategy guarantees variation in convergence speed with diminishment in plasticity - constancy predicament. The usage result demonstrates the viability of proposed conflict analysis procedure in clustering the information in a characterized group. The execution of the proposed conflict procedure is assessed by leading different probes distinctive microarray gene expression datasets. In addition, the execution of the proposed strategy is contrasted with the current FLEXFIS and FLEXFIS with overlapping clustering methodologies. The analytic consequence demonstrates that our proposed strategy more precisely groups the gene data into their appropriate cluster or tenet than any of the other prevailing methodologies with high order precision.
机译：在我们以前的冲突分析处理中，通过使用重叠聚类方法利用FLEXFIS的增强型变体来评估冲突信息。通过采用两个微阵列基因表达数据集来评估分组方法的执行。但是，该方法在安排基因表达信息时分组准确性较低。随后，为提高基因质量顺序的准确性和冲突性，提出了另一种采用改进的模糊c均值聚类策略的冲突研究方法。我们提出的策略涉及四个阶段，即基于MFCM的分组，模糊指导框架，冲突分析和半监督学习。采用我们策略的MFCM群集可确保收敛速度的提高，同时减少可塑性-稳定性难题。为分组的信息创建了模糊原理，因此执行了冲突方法以查看多个集群中可用的信息。 MFCM策略的选择可确保收敛速度的变化，同时可塑性-恒定性困境也会减少。使用结果证明了所提出的冲突分析程序在将信息聚类到特征组中的可行性。通过领导不同的探针独特的微阵列基因表达数据集来评估提出的冲突程序的执行情况。此外，所提出策略的执行与当前的FLEXFIS和具有重叠聚类方法的FLEXFIS形成对比。分析结果表明，我们提出的策略比其他任何流行的方法都更精确地将基因数据精确地分为适当的簇或原则。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号