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
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.