Table of contents

The collection contains papers by the participants of the international conference «Intelligent Systems in Science and Technology« (ICISST), which was successfully held from 12 to 18 October 2020 at the Perm State University.

More than a hundred papers from various regions of Russia and other countries were sent to the conference. 105 oral presentations were presented. 32 papers are recommended for publication in the Journal of Physics: Conference Series (JPCS). The expert committee were selected six articles for publication. Each paper was evaluated by the expert group in the field considered by the author.

The presented papers cover a wide range of areas such as cyber-physical systems, IoT (smart home, smart city), robotics, mechatronics, Artificial Intelligence, systems for working with big data (big data, data mining, blockchain), computer vision and visualization systems, additive technologies, fundamental problems of data mining.

The ICISST Organizing and editorial committee hopes you will enjoy reading this JPCS volume. We would like to thank all authors and participants for providing their valuable contributions for this proceeding as well as the reviewers for their constructive recommendations and critical comments, helped to improve of the submitted papers.

List of Organizing Committee, Scientific Committee, Editorial Committee

PERM DEPARTMENT OF THE SCIENTIFIC COUNCIL AT THE PRESIDIUM OF THE RAS ON THE METHODOLOGY OF ARTIFICIAL INTELLIGENCE

PERM STATE NATIONAL RESEARCH UNIVERSITY

PERM NATIONAL RESEARCH POLYTECHNICAL UNIVERSITY

NATIONAL RESEARCH UNIVERSITY HIGHER SCHOOL OF ECONOMICS PERM STATE HUMANITARIAN AND PEDAGOGICAL UNIVERSITY

COMPANY PROMOBOT

All papers published in this volume of Journal of Physics: Conference Series have been peer reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.

• Type of peer review: Open (Several experts checked the article and provided grades. The organizers calculated the arithmetic mean of the article grades and gave the article a final grade).

• Conference submission management system: standard

• Number of submissions received: 9

• Number of submissions sent for review: 6

• Number of submissions accepted: 6

• Acceptance Rate (Number of Submissions Accepted / Number of Submissions Received X 100): 66,7%

• Average number of reviews per paper: 2,5

• Total number of reviewers involved: 8

• Any additional info on review process: Several experts checked the article and provided grades. The organizers calculated the arithmetic mean of the article grades and gave the article a final grade

Contact person for queries(please include: name, affiliation, institutional email address)

Shkaraputa Alexander P. (A. P. Shkaraputa)

Perm State University, Faculty of Mechanics and Mathematics

Address: Russia, Perm city, 614990, Genkelya str. 7, office. 123a

Tel: +79526585835, +79129873458

E-mail: shkaraputa@psu.ru

The paper confirms a conclusion that there is no unified approach to the issue of civil liability for the actions of artificial intelligence. The authors propose to consider fault-based liability, liability regardless of fault and liability founded on a risk-based approach. To determine a type of liability for the actions of AI, the authors outline a classification of AI technologies on four grounds: autonomy, self-learning, feature and availability of data recorders. According to the authors, the most promising approach to the legal regulation of liability for the functioning of artificial intelligence technologies is a risk-based approach. The conclusions presented in the paper testify to the relevance of the topic of the research and prove the beginning of the formation of a scientific understanding of civil liability for the actions of AI in Russia and abroad.

The article is devoted to the application of convolutional neural networks and cascade classifiers for tracking smoking facts in relation to video surveillance systems. Two methods of smoking detection are proposed. The first method involves detecting a cigarette against the background of a human face. The second method involves detecting a hand with a cigarette in it. On the basis of the proposed methods, software for a video surveillance system is being developed, which makes it possible to determine the facts of smoking in real time, and thereby prematurely prevent possible undesirable consequences.

This work is devoted to the study of the dependence of the temperature fields of the mammary glands on external conditions and the parameters of the anamnesis, and preliminary examination of patients. As a result, it was possible to significantly improve the space of thermometric diagnostic signs intended for the intelligent system. The initial set of highly informative diagnostic thermometric signs was earlier obtained by A. G. Losev and V. V. Levshinsky. To take into account the influence of external factors on the temperature during the formation of the feature space, regression models were proposed. They were built by the method of neural network modeling. These models have sufficient performance and low error value, which allows them to be used in practice. The use of neural networks made it possible to scale the database of thermometric data obtained using a combined and EMC-sensor. As a consequence, it became possible to analyze the influence of the previously revealed heterogeneity of data in the context of age and diameter of the mammary glands on the effectiveness of highly informative diagnostic signs.

At the beginning of this paper, we consider the solution to the problem of constructing relations between mixed central moments and cumulants (semi-invariants) of an arbitrary vector random variable. The sought relations are derived on the basis of formal operations over the Maclaurin series, which are various expansions of the characteristic function of the random vector. In the case under consideration, the coefficients of the expansions are mixed moments, cumulants, and central moments. One of the applications for the recurrence relations obtained is their usage to closure systems of ordinary differential equations (ODE) for the functions of the mathematical expectations and the functions of central moments until a given order. These functions are the main probabilistic speci cations for the state vectors of systems of stochastic ordinary differential equations (SODE) describing a behavior of stochastic dynamic systems. Therefore we have devoted the last part of the paper to derivation of the ODE system satisfied by the indicated moment functions.

The article presents a methodology for developing an intelligent system for optimizing adaptive control of business planning processes in conditions of uncertainty. The results of the work are based on a new method for optimizing adaptive project management using network economic and mathematical modeling. The article describes a methodology for computer implementation of the proposed intelligent system, which is designed to automate the modeling of business planning processes and optimize adaptive decision-making management during their implementation based on network economic and mathematical modeling, as well as methods and tools for the development of intelligent computer systems. The developed system takes into account the existing specific technical and economic conditions and the available information support. The results obtained in this work can serve as a basis for the creation of intelligent computer systems to support management decisions in the implementation of business planning processes in conditions of information uncertainty.

This work was carried outaspartof research on the development of methods forthe intelligent analysis of medical thermometric data. These methods are designed to create a consultative intelligent system for the diagnosis of breast cancer. The previously developed approach to the formation of the feature space based on microwave radiothermometry data and the created algorithm forthe localization of malignant neoplasms in the mammary gland were applied. This algorithm is a weighted voting algorithm that is configured using a genetic algorithm. The operation of the algorithm was tested separately on the results of modeling the temperature fields of the mammary glands, as w'cll as on real data. In addition, it was crosschecked against real data and simulation results. In these cases, the localization algorithm can achieve accuracy from 55 to 65% on test samples.