Flocks of birds may cause major damage to fruit crops in the ripening phase. This problem is addressed by various methods for bird scaring; in many cases, however, the birds become accustomed to the distraction, and the applied scaring procedure loses its purpose. To help eliminate the difficulty, we present a system to detect flocks and to trigger an actuator that will scare the objects only when a flock passes through the monitored space. The actual detection is performed with artificial intelligence utilizing a convolutional neural network. Before teaching the network, we employed videocameras and a differential algorithm to detect all items moving in the vineyard. Such objects revealed in the images were labeled and then used in training, testing, and validating the network. The assessment of the detection algorithm required evaluating the parameters precision, recall, and F1 score. In terms of function, the algorithm is implemented in a module consisting of a microcomputer and a connected videocamera. When a flock is detected, the microcontroller will generate a signal to be wirelessly transmitted to the module, whose task is to trigger the scaring actuator.

The large set of scientific activities supported by MRI includes, among others, the research of water and mineral compounds transported within a plant, the investigation of cellular processes, and the examination of the growth and development of plants. MRI is a method of major importance for the measurement of early somatic embryos (ESE) during cultivation, and in this respect it offers several significant benefits discussed within this paper. We present the following procedures: non-destructive measurement of the volume and content of water during cultivation; exact three-dimensional differentiation between the ESEs and the medium; investigation of the influence of ions and the change of relaxation times during cultivation; and multiparametric segmentation of MR images to differentiate between embryogenic and non-embryogenic cells. An interesting technique consists in two-parameter imaging of the relaxation times of the callus; this method is characterized by tissue changes during cultivation at a microscopic level, which can be monitored non-destructively.

No abstract

No abstract

Deploying new wireless systems is very difficult in the current system of frequency spectrum assignments. The most prospective spectrum bands are fixed allocated for specific services and these bands are controlled by national telecommunication (governmental) organizations. Measurements of the frequency spectrum background show that a huge underutilization of the frequency spectrum exists. Overall effectiveness of spectrum utilization is widely discussed in the context of cognitive radio and dynamic spectrum allocation. An autonomous and intelligent system should improve spectrum sharing capabilities by detecting current, licensed usersprimary users with established connections in unused spectrum bands for cognitive radio -and secondary users. In this paper, a machine learning algorithm is used and channels in particular bands are scored according to a weight function. Real measured data are used as frequency spectrum background. This system should decrease interference in communication channels efficiently and increase data throughput with minimal costs. A further significant reduction of radiation power should be obtained by spectrum efficient communication. Smart buildings represent a great opportunity for this type of cognitive system.