No abstract

A machine vision system for detecting apples in orchards was developed. The system was designed to be used in harvesting robots and is based on a YOLOv3 algorithm with special pre- and post-processing. The proposed pre- and post-processing techniques made it possible to adapt the YOLOv3 algorithm to be used in an apple-harvesting robot machine vision system, providing an average apple detection time of 19 ms with a share of objects being mistaken for apples at 7.8% and a share of unrecognized apples at 9.2%. Both the average detection time and error rates are less than in all known similar systems. The system can operate not only in apple-harvesting robots but also in orange-harvesting robots.

This article is an attempt to rethink the concepts of “methodic” and “methodologic / methodical system” as basic to educational technology. What should be the structure of a methodical system? What is primary – the methodical system or the methodology? How are methodical systems created and developed? How do educational technology and a methodical system relate? How does changing the components of a system make it emergent? These and other issues are explored through the development of a new class of teaching methods – computer-based training systems.

The authors of the given article continue the series presented by the 2018 paper “Computer Simulation of Neural Networks Using Spreadsheets: The Dawn of the Age of Camelot”. This time, they consider mathematical informatics as the basis of higher engineering education fundamentalization. Mathematical informatics deals with smart simulation, information security, long-term data storage and big data management, artificial intelligence systems, etc. The authors suggest studying basic principles of mathematical informatics by applying cloud-oriented means of various levels including those traditionally considered supplementary – spreadsheets. The article considers ways of building neural network models in cloud-oriented spreadsheets, Google Sheets. The model is based on the problem of classifying multi-dimensional data provided in “The Use of Multiple Measurements in Taxonomic Problems” by R. A. Fisher. Edgar Anderson’s role in collecting and preparing the data in the 1920s-1930s is discussed as well as some peculiarities of data selection. There are presented data on the method of multi-dimensional data presentation in the form of an ideograph developed by Anderson and considered one of the first efficient ways of data visualization.

The instability of the price dynamics of the energy market from a theoretical point of view indicates the inadequacy of the dominant paradigm of the quantitative description of pricing processes, and from a practical point of view, it leads to abnormal shocks and crashes. A striking example is the COVID-stimulated spring drop of spot prices for crude oil by 305% to $36.73 a barrel. The theory of complex systems with the latest complex networking achievements using pragmatically verified econophysical approaches and models can become the basis of modern environmental science. In this case, it is possible to introduce certain measures of complexity, the change in the dynamics of which makes it possible to identify and prevent characteristic types of critical phenomena. In this paper, the possibility of using some econophysical approaches for quantitative assessment of complexity measures: (1) informational (Lempel-Ziv measure, various types of entropies (Shannon, Approximate, Permutation, Recurrence), (2) fractal and multifractal (Multifractal Detrended Fluctuation Analysis), (3) recurrent (Recurrence Plot and Recurrence Quantification Analysis), (4) Lévy’s stable distribution properties, (5) network (Visual Graph and Recurrence based) and (6) quantum (Heisenberg uncertainty principle) is investigated. Each of them detects patterns that are general for crisis states. We conclude that these measures make it possible to establish that the socially responsive exhibits characteristic patterns of complexity and the proposed measures of complexity allow us to build indicators-precursors of critical and crisis phenomena. Proposed quantitative measures of complexity classified and adapted for the crude oil market. Their behavior in the face of known market shocks and crashes has been analyzed. It has been shown that most of these measures behave characteristically in the periods preceding the critical event. Therefore, it is possible to build indicators-precursors of crisis phenomena in the crude oil market.