Circular object arrangement using spherical embeddings

作     者：Evangelopoulos, Xenophon Brockmeier, Austin J. Mu, Tingting Goulermas, John Y. 

作者机构：Univ Liverpool Dept Comp Sci Liverpool Merseyside England Univ Delaware Dept Elect & Comp Engn Delaware OH USA Univ Manchester Sch Comp Sci Manchester Lancs England 

出 版 物：《PATTERN RECOGNITION》 (图形识别)

年 卷 期：2020年第103卷

页      面：107192-107192页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：School of Electrical Engineering  Electronics and Computer Science  at the University of Liverpool  U.K 

主　　题：Combinatorial data analysis Data sequencing Circular seriation Quadratic assignment problem Spherical embeddings 

摘      要：We consider the problem of recovering a circular arrangement of data instances with respect to some proximity measure, such that nearby instances are more similar. Applications of this problem, also referred to as circular seriation, can be found in various disciplines such as genome sequencing, data visualization and exploratory data analysis. Circular seriation can be expressed as a quadratic assignment problem, which is in general an intractable problem. Spectral-based approaches can be used to find approximate solutions, but are shown to perform well only for a specific class of data matrices. We propose a bilevel optimization framework where we employ a spherical embedding approach together with a spectral method for circular ordering in order to recover circular arrangements of the embedded data. Experiments on real and synthetic datasets demonstrate the competitive performance of the proposed method. (C) 2019 Elsevier Ltd. All rights reserved.