Abstract:
The current study was conducted to develop a new approach for revealing egg-laying behaviour of alfalfa weevil, Hypera postica (Gyllenhal) (Coleoptera: Curculionidae) laying in alfalfa fields at late fall. Totally, the infected 675 alfalfa plants were evaluated with the objective to predict height of eggs laid by the alfalfa weevil at the plant stem from plant height, number of eggs per cluster, number of egg clusters at the plant stem, and location as potential predictors. In the prediction of height of eggs, CHAID (Chi-square Automatic Interaction Detection) and MARS (Multivariate Adaptive Regression Splines) algorithms were implemented for describing egg laying behaviour of the alfalfa weevil and giving an idea on minimizing loss of the fields, in practice. In conclusion, a new scale developed by CHAID indicated that height of eggs was found higher as the plant height increased from Node 1 (plant height < 23 cm) to Node 10 (plant height > 74 cm), and in MARS, number of egg cluster and plant height affected height of eggs (P<0.05), which may help to describe egg laying behaviour of alfalfa weevil, H. postica.
Keywords:
Data Mining
,
Alfalfa
,
Egg laying behaviour
,
Alfalfa weevil
,
Hypera postica