作者: Emma Peeling , Allan Tucker
DOI: 10.1007/978-3-540-74825-0_17
关键词:
摘要: The progression of many biological and medical processes such as disease development are inherently temporal in nature. However datasets associated with from cross-section studies, meaning they provide a snapshot particular process across population, but do not actually contain any information. In this paper we address by constructing orderings crosssection data samples using minimum spanning tree methods for weighted graphs. We call these reconstructed pseudo time-series incorporate them into models dynamic Bayesian networks. Results our preliminary study show that including information improves classification performance. conclude outlining future directions research, considering different construction other modelling approaches.