基于核聚类算法的高校定位研究

Orientation research of universities based on kernel clustering algorithm

提出一个基于核聚类算法的高校定位模型.引入核函数,将原始数据由数据空间映射到特征空间中进行聚类.核聚类算法经过了核函数的非线性映射,使原始数据的特征更完整地显现出来,从而使聚类结果更客观、有效,可以解决传统方法主观性强、偏差大的缺陷.将核聚类算法应用于我国16所高校定位的研究,结果表明该方法可行且有效.通过聚类结果的分析,提出高校可分为教学科研生态位协调型、低教学生态位高科研生态位型、高教学生态位低科研生态位型3类,并对不同类型高校提出发展建议.

An orientation model of universities based on kernel clustering algorithm is presented. By using kernel functions, the data in original space can be mapped into a high-dimensional feature space, such that more features of the data are exposed so that clustering can be performed efficiently. This procedure makes its clustering result more objective and valid. This method is applied to the orientation of 16 universities, and results show feasibility and effectiveness. According to the clustering result, universities are classified into three types by the fitness of teaching and research, which are coordination, high teaching-low research niche and low teaching-high research niche.