Multidimensional analysis model for highly pathogenic avian influenza using data cube and data mining techniques

The highly pathogenic avian influenza (HPAI) viral disease can spread rapidly, resulting in high mortality rates and severe economic damage. To minimize the damage incurred from such diseases, it is necessary to develop technology for collecting and analysing livestock disease data. In this paper, we propose a data cube model with data mining techniques for the analysis of HPAI using livestock disease data accumulated over an extended period. Based on the construction of the data cube model, a multidimensional HPAI analysis is performed using online analytical processing (OLAP) operations to assess the temporal and spatial perspectives of the spread of the disease with varying levels of abstraction. Furthermore, the proposed analysis model provides useful information that generates site connectedness and potential sequential dissemination routes of HPAI outbreaks by applying association rule mining and sequential pattern mining, respectively. We confirm the feasibility and applicability of the proposed HPAI analysis model by implementing and applying an analysis system to HPAI outbreaks in South Korea.