针对时间序列聚类问题的特征学习与集成学习研究

Although conventional static data clustering has been studied for many years, time series clustering recently has been becoming quite popular in various fields due to that such underpinning techniques can discover the intrinsic structures and condense or summarize information contained in growing time series datasets. Unlike static data, time series have many distinct characteristics, including high dimensionality, complex time dependency, and large volume, all of which make the clustering of time series more challenging than static data clustering. In this proposal, we intensively study the time series data mining from the perspective of clustering analysis, and proposed an representation learning-based ensemble learning approach via multiple weighting scheme for time series clustering problems. Three key issues are explored in this proposal: (1) the representation learning/deep learning technique is used to optimally capture important features of time series such as dynamic behaviors and temporal coherence. (2) A novel multiple weighting scheme is proposed to optimally reconcile the input partitions into a single consolidated solution that significantly improve the robustness and accuracy of clustering analysis on time series via ensemble learning approach (3) The proposed approaches have out-standing ability in automatic detection of cluster number. Sum of all, we will carry out the forefront research of time series clustering in association of clustering ensemble techniques, the research results will not only contribute to the theoretical analysis, but also applications of time series data mining and pattern recognition.

传统静态数据的聚类方法已经得到了较为深入的研究，然而现实生活中越来越多的应用领域涉及到时间序列数据的聚类分析。但时间序列数据具有复杂的动态特性、高维度和海量性等特点，使得传统的聚类算法无法获得较为理想的结果。本课题将深入研究时间序列数据挖掘技术中的聚类问题，拟提出了一种基于特征学习的复合式加权聚类集成学习模型，以解决以下主要问题：（1）通过提出基于深度学习的特征提取方法，有效地捕捉时间序列的动态特性与时间片段的关联性，并使其根据不同目标时间序列数据集自适应提取特征信息（2）通过引入新的复合式加权机制，优化集成学习模型的融合方式，使得时间序列聚类分析的鲁棒性与精确度得到进一步的提高。（3）在时间序列聚类分析中能够有效地捕捉类簇的本征结构，自动识别类数。综上所述本课题将在特征学习及集成学习的基础上，对时间序列数据聚类分析提出较为前沿的理论研究，其研究成果将具有较高的理论和实用应用价值。

传统静态数据的聚类方法已经得到了较为深入的研究，然而现实生活中越来越多的应用领域涉及到时间序列数据的聚类分析。但时间序列数据具有复杂的动态特性、高维度和海量性等特点，使得传统的聚类算法无法获得较为理想的结果。.本课题深入研究时间序列数据挖掘技术中的聚类问题，提出了基于特征学习的复合式加权聚类集成学习模型，并取得了以下成果：（1）通过提出基于深度学习的特征提取方法，有效地捕捉时间序列的动态特性与时间片段的关联性，并使其根据不同目标时间序列数据集自适应提取特征信息；（2）通过引入新的复合式加权机制，优化集成学习模型的融合方式，使得时间序列聚类分析的鲁棒性与精确度得到进一步的提高；（3）在时间序列聚类分析中能够有效地捕捉类簇的本征结构，自动识别类数。.综上所述本课题将在特征学习及集成学习的基础上，对时间序列数据聚类分析提出较为前沿的理论研究，其研究成果将具有较高的理论和实用应用价值。

内容获取失败，请点击重试