文章基本信息

标题：Improving Farm Management Information Systems with Data Mining
本地全文：下载
作者：Cagatay CATAL ; Ayalew KASSAHUN ; Henk Jan HOVİNG 等
期刊名称：Balkan Journal of Electrical & Computer Engineering
印刷版ISSN：2147-284X
出版年度：2020
卷号：8
期号：1
页码：21-30
DOI：10.17694/bajece.555680
语种：English
出版社：Kirklareli University
摘要：Over the past severalyears, farm enterprises have grown in size substantially while their number hassteadily declined. As the size of their farms grow more and more farmers aredeploying information systems, commonly called as Farm Management InformationSystems (FMIS), to manage the day to day activities of their farms. Thedeployment of FMIS enable farmers to capture detailed data that can potentiallybe analysed by data mining tools to provide valuable information for optimizingthe farm enterprises. However, data mining is generally not a common feature ofmany FMIS. In order to evaluate the suitability of data mining for use in FMIS,we performed two case studies using data captured in FMIS and applying datamining. Microsoft Azure Machine Learning Studio is chosen because it provides asimple drag-and-drop visual interface that can be used by farm domain experts.We addressed two common problems in dairy farming: calving prediction of dairycows and prediction of lactation value of milking cows. In both cases we builtdata mining models and run experiments and our results in both cases indicatethat the required data is available from FMIS and data mining techniques providesacceptable performance. We also showed that farm domain experts can easily usea user-friendly and drag-and-drop data mining tools with minimal initialtraining. Based on the insight from the two case studies and literature study, weidentified several decision problems that can be addressed with data mining suchas heat prediction and lameness prediction.
关键词：Farm management information systems; machine learning; calving prediction; lactation prediction