本文講述了什么是數(shù)據(jù)挖掘，以及數(shù)據(jù)挖掘的兩種策略：有指導(dǎo)和無指導(dǎo)學(xué)習(xí)。作
者用心臟病數(shù)據(jù)集范例來解釋有指導(dǎo)學(xué)習(xí)的過程。實驗表明患心臟病病人的某些屬性特征和患心臟病風險的大小有較大關(guān)系。數(shù)據(jù)挖掘的結(jié)果對于醫(yī)生臨床診斷有很重要的意義。
關(guān)鍵詞：數(shù)據(jù)挖掘 有指導(dǎo)學(xué)習(xí) 心臟病

Supervised learning based data mining technology with its application to heart diseases risk detection Cui Yuan and Feng Huanting (Department of computer, Chengdu Medical College, Chengdu China 610083; Art and Science School, Sichuan Normal University, Chengdu, China 610110 ) Abstract This paper introduces concept of data mining, and presents two methods of data mining: supervised learning and unsupervised learning.The author uses a intance about heart disease and explain the process of supervised learning.The experiment show that some attributes of patients are strongly related to heart diseases risk levels.The result of data mining is much significant to doctors'clinical diagnosis.
Keywords: data mining, supervise learning, heart diseases