RESEARCH AND APPLICATION OF RULE UPDATING MINING ALGORITHM FOR MARINE WATER QUALITY MONITORING DATA

Abstract

This paper studies the characteristics of marine water quality monitoring data monitored by photoelectric sensor network, mines the potential information from the massive data. on account of the continuous accumulation of monitoring data, this paper focuses on the study of database with numerical attribute and proposes a rule updating algorithm for solving the rule maintenance issues caused by changes in the database. according to the rule, the algorithm forms a new database from part of the original data and the new data, and searches the new database by random search, thus can avoid creating a large number of redundant rules and can quickly mine effective rules at the same time. experimental results show that this method not only can avoid mining in the whole original massive data, but also can improve work efficiency, and can quickly and effectively find new data and find useful rules in the data with high practicability.