Mining association rules between sets of items in large databases
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Study of positive and negative association rules based on multi-confidence and chi-squared test
ADMA'06 Proceedings of the Second international conference on Advanced Data Mining and Applications
| Hi-index | 0.98 |
Tracing of heavy metal pollution sources is a current hot issue of agricultural soil quality management. Land utilization is one of the important factors which affect the heavy metal contents of regional soil. In order to model the relationship between soil heavy metal contamination and land utilization, this paper adopts a novel positive and negative association rule method in order to effectively find the probabilities of different dual events which occur simultaneously and frequently. Given the item set @Dd, which are the differences between the values of As, Cd, Cr, Cu, and Hg contents and the corresponding background values, and the set of land use types T, consisting of grain farm, vegetable farm, orchard and forest land, we find the dual association rule T@?@Dd. With soil heavy metal data collected in 2006-2008 from Beijing, the experimental results demonstrate that land utilization has made a greater contribution to the accumulation of the concentrations of Hg and Cd than to that of the concentrations of As, Cr and Cu.