摘要：This paper introduces a technique that can efficiently identify symptoms
and risk factors for early childhood diseases by using feature reduction, which was
developed based on Principal Component Analysis (PCA) method. Previous research
using Apriori algorithm for association rule mining only managed to get the frequent
item sets, so it could only find the frequent association rules. Other studies used
ARIMA algorithm and succeeded in obtaining the rare item sets and the rare
association rules. The approach proposed in this study was to obtain all the complete
sets including the frequent item sets and rare item sets with feature reduction. A series
of experiments with several parameter values were extrapolated to analyze and
compare the computing performance and rules produced by Apriori algorithm,
ARIMA, and the proposed approach. The experimental results show that the
proposed approach could yield more complete rules and better computing
performance.
关键词：Early childhood diseases; PCA; Medical record; Apriori Algorithm
