Applications of Machine Learning on two agricultural datasets
Stuart Yeates, Kirsten Thomson · 1996
The induction of decision trees from tabulated data is a field of machine learning which has been demonstrated successfully in several practical applications. This paper looks at the application of this technology to two datasets in the agricultural domain, and show why it was not possible to achieve the success obtained in other domains. Introduction Induction of decision trees is a new field of machine learning, involving the algorithmic acquisition of structured knowledge in forms such as concepts, decision trees, discrimination nets or production rules. A common goal of such methods is to predict the value of an attribute in the data based on other attributes. The output can then be used, by either a human or a system, to classify unseen examples. Good surveys can be found in [1] and [2] Outlook Temp. °F %Hum -idity Windy Play ? sunny 85 85 false Don't Play sunny 80 90 true Don't Play overcast 83 78 false Play rain 70 96 false Play rain 68 80 false Play rain 65 70 true Don't P...