唐山师范学院学报
唐山師範學院學報
당산사범학원학보
JOURNAL OF TANGSHAN TEACHERS COLLEGE
2015年
2期
42-44
,共3页
数据挖掘%关联规则%BDIF
數據挖掘%關聯規則%BDIF
수거알굴%관련규칙%BDIF
data mining%association rules%based transactional databases including frequent item set
阐述了关联规则挖掘的研究情况，关联规则的分类方法等，对经典Apriori算法进行了分析和评价，在此基础上提出了一种高效产生频繁集的BDIF（Based Transactional Databases Including Frequent ItemSet）算法；它通过划分数据块，快速的搜寻频繁项目集，从而减少对数据块的扫描次数，提高了算法的效率。并用BorlandC++Builder6.0开发环境来调试、验证该算法。
闡述瞭關聯規則挖掘的研究情況，關聯規則的分類方法等，對經典Apriori算法進行瞭分析和評價，在此基礎上提齣瞭一種高效產生頻繁集的BDIF（Based Transactional Databases Including Frequent ItemSet）算法；它通過劃分數據塊，快速的搜尋頻繁項目集，從而減少對數據塊的掃描次數，提高瞭算法的效率。併用BorlandC++Builder6.0開髮環境來調試、驗證該算法。
천술료관련규칙알굴적연구정황，관련규칙적분류방법등，대경전Apriori산법진행료분석화평개，재차기출상제출료일충고효산생빈번집적BDIF（Based Transactional Databases Including Frequent ItemSet）산법；타통과화분수거괴，쾌속적수심빈번항목집，종이감소대수거괴적소묘차수，제고료산법적효솔。병용BorlandC++Builder6.0개발배경래조시、험증해산법。
This article describes research on association rule mining and classification methods of association rules, analyzes and evaluates the classic Apriori algorithm, which gives rise to an efficient frequent BDIF (Based Transactional Databases Including Frequent Item Set) algorithm. It thereby reduces scanning data block and improves algorithm efficiency by dividing data block and quickly searching for frequent item set.
