In agriculture,insect pests must be identified at the initial stage of infestation to avoid their spread in the field.Leaf folders(cnaphalocrocis medinalis)and yellow stemborers(scirpophaga incertulas)are destructive ...In agriculture,insect pests must be identified at the initial stage of infestation to avoid their spread in the field.Leaf folders(cnaphalocrocis medinalis)and yellow stemborers(scirpophaga incertulas)are destructive pests of paddy crops,which are causing severe yield loss.Manual identification of insect pests in the crop is time-consuming,tedious,and ineffective.This paper focuses on a light trap based four-layer deep neural network with search and rescue optimization(DNN-SAR)method to identify leaf folders and yellow stemborers.Light traps are designed to lure the insects in the paddy field and the images of trapped insects are analyzed using the proposed detection method.In the DNN-SAR,images are contrastenhanced using deer hunting algorithm,impulse noise is removed with fast average group filter,and segmented using social ski-driver optimization.The search and rescue optimization algorithm is used for the selection of optimal weights in the deep neural network,which has improved the convergence rate,lowered the complexity of learning,and improved the accuracy of detection.The proposed method outperformed the existing methods and achieved 98.29%pest detection accuracy.展开更多
The seasonal fluctuation oflepidoptcran cereal stemborers on maize and wild host plants （i.e., grasses and a few sedges） was investigated in southern Benin from 1988 to 1998 by time series analysis and repeated-meas...The seasonal fluctuation oflepidoptcran cereal stemborers on maize and wild host plants （i.e., grasses and a few sedges） was investigated in southern Benin from 1988 to 1998 by time series analysis and repeated-measures analysis of variance （ANOVA）. In addition, a walk-in light trap was used to study the flight behavior of adult moths. On both cereals and grasses, the noctuid Sesamia calaraistis was the predominant species, followed by the pyralid Eldana saccharina. The noctuid Busseolafusca was rare on both maize and wild host plants. In general, pest populations increased during the course of the year to reach peak densities during the second short rainy season, and then crashed to close to zero during the dry season. On wild host plants, egg masses and other immature stages were collected throughout the year but they were higher on wild grasses than maize during the off-season. Thus wild host plants can be considered as refuge for both borers and natural enemies during the off-season, when maize is not available. However, only four out of the eleven wild host species played a discernable role. S. calamistis egg densities appeared to be influenced by density-dependent factors, suggesting an effect of natural enemies. Temperature and rainfall had a negative effect on egg abundance. Larval parasitism by a Kenyan strain of the braconid Cotesia sesamiae, which was released in southern Benin in the early 1990s, and by the tachinid Sturmiopsisparasitica varied between seasons and years but there were no discernable patterns. For both parasitoids and borer host species, parasitism was positively correlated with trap catches of adult moths. The recovery of C. sesamiae during a 2-year period suggests that the parasitoid has established its population in southern Benin.展开更多
文摘In agriculture,insect pests must be identified at the initial stage of infestation to avoid their spread in the field.Leaf folders(cnaphalocrocis medinalis)and yellow stemborers(scirpophaga incertulas)are destructive pests of paddy crops,which are causing severe yield loss.Manual identification of insect pests in the crop is time-consuming,tedious,and ineffective.This paper focuses on a light trap based four-layer deep neural network with search and rescue optimization(DNN-SAR)method to identify leaf folders and yellow stemborers.Light traps are designed to lure the insects in the paddy field and the images of trapped insects are analyzed using the proposed detection method.In the DNN-SAR,images are contrastenhanced using deer hunting algorithm,impulse noise is removed with fast average group filter,and segmented using social ski-driver optimization.The search and rescue optimization algorithm is used for the selection of optimal weights in the deep neural network,which has improved the convergence rate,lowered the complexity of learning,and improved the accuracy of detection.The proposed method outperformed the existing methods and achieved 98.29%pest detection accuracy.
文摘The seasonal fluctuation oflepidoptcran cereal stemborers on maize and wild host plants （i.e., grasses and a few sedges） was investigated in southern Benin from 1988 to 1998 by time series analysis and repeated-measures analysis of variance （ANOVA）. In addition, a walk-in light trap was used to study the flight behavior of adult moths. On both cereals and grasses, the noctuid Sesamia calaraistis was the predominant species, followed by the pyralid Eldana saccharina. The noctuid Busseolafusca was rare on both maize and wild host plants. In general, pest populations increased during the course of the year to reach peak densities during the second short rainy season, and then crashed to close to zero during the dry season. On wild host plants, egg masses and other immature stages were collected throughout the year but they were higher on wild grasses than maize during the off-season. Thus wild host plants can be considered as refuge for both borers and natural enemies during the off-season, when maize is not available. However, only four out of the eleven wild host species played a discernable role. S. calamistis egg densities appeared to be influenced by density-dependent factors, suggesting an effect of natural enemies. Temperature and rainfall had a negative effect on egg abundance. Larval parasitism by a Kenyan strain of the braconid Cotesia sesamiae, which was released in southern Benin in the early 1990s, and by the tachinid Sturmiopsisparasitica varied between seasons and years but there were no discernable patterns. For both parasitoids and borer host species, parasitism was positively correlated with trap catches of adult moths. The recovery of C. sesamiae during a 2-year period suggests that the parasitoid has established its population in southern Benin.
