Dimension Reduction of Digital Image Descriptors in Neural Identification of Damaged Malting Barley Grains.

The paper covers the problem of determination of defects and contamination in malting barley grains. The analysis of the problem indicated that although several attempts have been made, there are still no effective methods of identification of the quality of barley grains, such as the use of information technology, including intelligent sensors (currently, quality assessment of grain is performed manually). The aim of the study was the construction of a reduced set of the most important graphic descriptors from machine-collected digital images, important in the process of neural evaluation of the quality of BOJOS variety malting barley. Grains were sorted into three size fractions and seed images were collected. As a large number of graphic descriptors implied difficulties in the development and operation of neural classifiers, a PCA (Principal Component Analysis) statistical method of reducing empirical data contained in the analyzed set was applied. The grain quality expressed by an optimal set of transformed descriptors was modelled using artificial neural networks (ANN). The input layer consisted of eight neurons with a linear Postsynaptic Function (PSP) and a linear activation function. The one hidden layer was composed of sigmoid neurons having a linear PSP function and a logistic activation function. One sigmoid neuron was the output of the network. The results obtained show that neural identification of digital images with application of Principal Component Analysis (PCA) combined with neural classification is an effective tool supporting the process of rapid and reliable quality assessment of BOJOS malting barley grains.

Aphid Assemblages Associated with Urban Park Plant Communities.

Some aphid species are important agricultural pests, sometimes also found on plants growing in urban areas. In this work, we set out to identify the plant species, communities or habitats that are more attractive to aphids in order to limit their spread into new green areas. The aim of the study was to determine and compare plant communities and the assemblages of aphids associated with them in different urban park habitats. The research hypothesis assumed that the differences between aphid assemblages depend on plant diversity and hence reflect urban park habitat environmental conditions, in particular the plant communities and the floral structure. The study was carried out in Bydgoszcz (northern Poland), and four parks were taken into consideration. Herein, floristic lists were used to calculate ecological indicator values for each park. The aphid species richness was determined, as well as the relative abundance and dominance structure similarities of the aphid assemblages. Our results demonstrated that Prunus spp. were strongly infested by Hyalopterus pruni, similarly as Philadelphus inodorus by Aphis fabae, Sambucus nigra by Aphis sambuci, and Acerplatanoides and A. pseudoplatanus by Periphyllus testudinaceus. Park plantations of Robinia pseudoacacia were not very attractive to aphids. The most attractive plant communities to aphids were syntaxonomically identifiable as alluvial alder forests in the layer of trees and Cornus sanguinea in the layer of shrubs.

Monitoring of the red-belted clearwing moth, Synanthedon myopaeformis, and its parasitoid Liotryphon crassiseta in apple orchards in yellow Moericke traps.

This study was conducted in 2008-2010 in three apple orchards in western Poland and involved a massive catch of the red-belted clearwing moth, Synanthedon myopaeformis (Borkhausen) (Lepidoptera: Sesiidae), and its parasitoid Liotryphon crassiseta (Thomson) (Hymenoptera: Ichneumonidae) in yellow Moericke traps. The flight time for both species was correlated and fell in the first half of July. However, the correlation between the occurrences of both species was statistically significant only in 2008, when most specimens were caught. A total of 7960 S. myopaeformis were caught, with a 2:1 male:female sex ratio, and 415 adult L. crassiseta. No correlation between the numbers of S. myopaeformis and L. crassiseta in relation to age, variety of trees, or orchard surface area was noted. Significant differences between the catches of S. myopaeformis and L. crassiseta were reported in particular years. Furthermore, clear differences in the yields of S. myopaeformis and L. crassiseta between traps situated in the orchard and those on its edges were recorded, particularly in the orchard surrounded by cultivated fields. Yellow pan-traps could be used more widely in order to monitor and control the abundance of S. myopaeformis, especially by catching its females.