A case-acquisition and decision-support system for the analysis of group-average lactation curves

Citation
D. Pietersma et al., A case-acquisition and decision-support system for the analysis of group-average lactation curves, J DAIRY SCI, 84(3), 2001, pp. 730-739
Citations number
23
Categorie Soggetti
Food Science/Nutrition
Journal title
JOURNAL OF DAIRY SCIENCE
ISSN journal
00220302 → ACNP
Volume
84
Issue
3
Year of publication
2001
Pages
730 - 739
Database
ISI
SICI code
0022-0302(200103)84:3<730:ACADSF>2.0.ZU;2-8
Abstract
A case-acquisition and decision-support system was developed to support the analysis of group-average lactation curves and to acquire example cases fr om domain specialists. This software was developed through several iteratio ns of a three-step approach involving 1) problem analysis and formulation i n consultation with two dairy nutrition specialists; 2) development of a ca se-acquisition and decision-support prototype by the system developer; and 3) use of the prototype by the domain specialists to analyze and classify m ilk-recording data from example herds. The overall problem was decomposed i nto three subproblems: removal of outlier tests and lactation curves of ind ividual cows; interpretation of group-average lactation curves; and diagnos is of detected abnormalities at the herd level through the identification o f potential management deficiencies. For each subproblem, a software module was developed allowing the user to analyze both graphical and numerical pe rformance representations and classify these representations using predefin ed linguistic descriptors. The example-based method for the development of the program proved to be very useful, facilitating the communication betwee n system developer and domain specialists, and allowing the specialists to explore the appropriateness of the various prototypes developed. The result ing software represents a formalization of the approach to group-average la ctation curve analysis, elicited from the two domain specialists. In future research, the case acquisition and decision-support system will be complem ented with knowledge to automate identified classification tasks, which wil l be captured through the application of machine-learning techniques to exa mple cases, acquired from domain specialists using the software.