Персона:
Кулик, Сергей Дмитриевич

Организационные подразделения

Организационная единица

Институт интеллектуальных кибернетических систем

Цель ИИКС и стратегия развития - это подготовка кадров, способных противостоять современным угрозам и вызовам, обладающих знаниями и компетенциями в области кибернетики, информационной и финансовой безопасности для решения задач разработки базового программного обеспечения, повышения защищенности критически важных информационных систем и противодействия отмыванию денег, полученных преступным путем, и финансированию терроризма.

Фамилия

Кулик

Имя

Сергей Дмитриевич

Полная страница элемента

Результаты поиска

Теперь показываю 1 - 10 из 12

Только метаданные
Topological Analysis of Protein Surfaces and Its Role in the Development of New Medicines
(2024) Bystrov, O. V.; Kulik, S. D.; Быстров, Олег Владимирович; Кулик, Сергей Дмитриевич
Открытый доступ
Effective scientific personnel training in the field of modern computer technologies for the implementation of advanced research projects of the Megascience class
(2020) Shtanko, A. N.; Kulik, S. D.; Kondakov, A. A.; Кулик, Сергей Дмитриевич
© Published under licence by IOP Publishing Ltd.Successful research projects of the Megascience class usually require a well-trained team of scientists from various fields of knowledge. These scientists must be high-skilled experts. Each member of a team like that must have the necessary, specialized cross-industry skills, for example, in such areas as artificial intelligence, convolutional neural networks, specialized intelligent search engines, and full-text analysis. One of the key aspects of effective personnel training for successful implementation of Megascience projects into reality is the acquisition by students professional skills, abilities, and knowledge to use tools of modern scientific technologies, containing, for example, libraries of programs (functions). In particular, convolutional neural networks and intelligent search systems can be applied in various research projects in the field of physics, chemistry, biology, and medicine, for example, in telemedicine, for effective decision-making in diagnosing a patient. Therefore, understanding the principles of neural networks and intelligent search systems is a necessary competence of researchers working in the framework of Megascience projects. Classic search engines are based on indexing the textual information of the database that is being searched. Intelligent search engines can improve the search experience through intelligent data processing, including using convolutional neural networks. This report examines practical examples and areas of the successful application of convolutional neural networks and information systems in practice.
Только метаданные
Experiments with Neural Net Object Detection System YOLO on Small Training Datasets for Intelligent Robotics
(2020) Kulik, S. D.; Shtanko, A. N.; Кулик, Сергей Дмитриевич
© 2020, Springer Nature Switzerland AG.In this paper we’ve conducted multiple experiments with modern object detection system YOLO. Object detection systems are fundamental to many robotics tasks. Recognition algorithms involving object detection are often part of various intelligence systems for robots. Training object detection systems usually requires waste amounts of training data which can be expensive and time-consuming. In this paper we’ve conducted several experiments with YOLO on small training datasets investigating YOLO’s capacity to train on small number of examples. We measured accuracy metrics for object detector depending on the size of training dataset, compared training process of full and smaller versions of YOLO and their speed. Gathered information will be used for creating visual factographic intelligence system for robots. YOLO (You Only Look Once) is a special intelligent technology for computer vision techniques. Our results are useful for industry professionals and students from a broad range of disciplines related to robotics, intelligent technologies and other fields.
Только метаданные
The Problem of Efficiency of Microscopic Human Hair Analysis in the Forensic Biological Examination
(2020) Suchkova, E. V.; Nikonets, D. A.; Kulik, S. D.; Кулик, Сергей Дмитриевич
The main aim of this research work is to study new approaches to assessing the results of forensic microscopic analysis of the investigated person's hair, which will improve the effectiveness of forensic biological examination of human hair. The forensic examination of human hair includes an analysis of their morphological characteristics. If all individualising features coincide, a conclusion can be drawn that this very hair probably belongs to the investigated person. However, a "probabilistic" conclusion cannot be the basis for a court decision. A mathematical model for assessing the probabilistic-statistical estimate of the set of matching features that characterise human hair (random match probability) has been developed to improve the evaluation of the forensic microscopic hair analysis. The identification significance (rarity) has been estimated for all morphological features characterising human hair. The aggregated identification significance of the set of matching features (morphological hair profile) has been estimated, and the probability and the frequency of morphological hair profiles have been evaluated for a control dataset of hair samples. As a result of the work, it can be concluded that, in most cases, the probabilistic-statistical estimate of appearance of morphological profiles of human hair does not give us precise data to make an unequivocal positive conclusion in the identification of a person by hair. However, the microscopic hair analysis is scientifically justified, and its results have a good correlation with the results of the DNA analysis, especially if the analysis made an unequivocal negative conclusion. The most accurate method of forensic hair analysis is the DNA analysis. However, despite the fact that the nuclear DNA analysis is more suitable for an identification of a person by hair than the microscopic hair analysis, it should be noted that, in two-thirds of cases, the probability of appearance of a genetic profile is in the same range of values as the probability of appearance of a morphological profile of human hair. Only in one-third of cases, this probability has values that are difficult to achieve in the microscopic hair analysis. Moreover, there are situations when it is impossible to perform the DNA analysis, but the microscopic analysis of human hair can be done without any restriction. As a result, it is concluded that, to increase the expert biologist's efficiency, it makes sense to use an integrated approach to the forensic examination of human hair. The integrated approach combines a consistent application of the method of the microscopic analysis of human hair and the method of the DNA hair analysis, which allows obtaining the most compete forensic information on human hair.
Только метаданные
Intelligence Information System for Forensic Microscopical Hair Analysis
(2020) Suchkova, E. V.; Nikonets, D. A.; Kulik, S. D.; Кулик, Сергей Дмитриевич
© 2020, Springer Nature Switzerland AG.The problem of identification by human hair has been considered in the paper. The main aim of this paper is to present a new intelligence information system for forensic microscopical hair analysis. In our research we used micromorphological characteristics of the human hair: cuticle scale pattern, cortical layer background colour, pigment colour, pigment granule size, pigment aggregate size and pigment distribution. The micromorphological characteristics of the hair specimens have been investigated with the special microscope, such as Leica DM 1000 microscope. The result of the work is very important for the development of a mathematical model for the evaluating of the probability of a set of the matching features in the investigated hair object and comparative hair samples. Pattern recognition and decision making is special intelligent technology for forensic examination of human hair. Our results are useful for forensic experts and students from a broad range of disciplines related to intelligent technologies, for forensic microscopical hair analysis and other fields. Gathered information will be used for creating effective intelligence information system for forensic microscopical hair analysis.
Только метаданные
Factographic Information Retrieval for Biological Objects
(2020) Kulik, S. D.; Кулик, Сергей Дмитриевич
© 2020, Springer Nature Switzerland AG.This paper describes the results of work to develop an automated factographic information retrieval system for biological forensic objects. The effective factographic information retrieval problem has been investigated in the paper. This factographic information retrieval includes a pattern recognition algorithm, and they are implemented for retrieval only one image among the variety of similar images of biological forensic objects. The automated factographic information retrieval system includes special retrieval block and human operator. Analytical formula was obtained to evaluate the effectiveness of factographic information retrieval using indicator. This formula is presented by effectiveness indicator: average length of the recommendatory list provided by the retrieval block enabling the human operator to take the final decision. The paper describes the structure of the algorithm for factographic information retrieval. Properties of the important indicator of effectiveness – the average length of the recommendatory list for the human operator were explored.
Только метаданные
Recognition Algorithm for Biological and Criminalistics Objects
(2020) Kulik, S. D.; Shtanko, A. N.; Кулик, Сергей Дмитриевич
© 2020, Springer Nature Switzerland AG.This paper describes the results of a work to develop an algorithm for analyzing images of embossed impressions in paper documents under oblique lighting. The described algorithm could also be used for recognition of similarly-structured objects, for example, some of biological structures. This type of analysis is necessary during forensic analysis of certain security features of paper documents. Part of this analysis is determining to which category new, uncategorized impression belongs to. This research explores the potential for automation of this task using neural networks. The core element of the algorithm is a neural network which determines the similarity between two embossed impressions. The paper describes the structure of the algorithm, a method for creating an image database for training and testing, as well as testing results for proposed algorithm.
Только метаданные
Genetic Algorithm and Software Tools for Solving Optimization Problems in Intelligent Robotics
(2020) Kulik, S. D.; Protopopova, J.; Кулик, Сергей Дмитриевич
© 2020, Springer Nature Switzerland AG.This paper concentrates on application of genetic algorithm in area of intelligent robotics. It raises the following issues: what optimization problems are faced in robotics, how they can be solved and how genetic algorithm can be useful in this area. The first section explains the role, kinds and examples of optimization problems in field of robotics and what solutions they can have. The second section of the paper covers the basic concepts of genetic algorithm, the steps it performs, and its possibilities. The third section contains an overview and a comparison of existing software implementations of genetic algorithm. This section also presents the system that we have developed for solving optimization problems with genetic algorithm and describes its main features and capabilities, gives a list of configuration parameters that user is allowed to change, and demonstrates its graphical interface for manipulating different types of objects that are managed by genetic algorithm.
Только метаданные
Factographic information retrieval for semiconductor physics, micro - And nanosystems
(2019) Kulik, S. D.; Кулик, Сергей Дмитриевич
© 2019 Published under licence by IOP Publishing Ltd. This paper proposes a factographic information retrieval for semiconductor physics, as well as micro - and nanosystems. This factographic information retrieval includes a pattern recognition algorithm and factographic database. The first factographic database includes special keywords from semiconductor physics and micro - and nanosystems. The second factographic database includes document descriptions in the form of Searching Documents Patterns for the fields of semiconductor physics and microelectronics. An analytical model of the factographic information retrieval system is developed. This model is presented by an effectiveness indicator: the average length of the recommendatory list used for semiconductor physics and micro - and nanosystems for space application.
Открытый доступ
Scientific personnel training in convolutional neural networks for the implementation of research projects of the MegaScience class
(2019) Shtanko, A. N.; Kulik, S. D.; Кулик, Сергей Дмитриевич
© Published under licence by IOP Publishing Ltd.Megascience projects require an all-inclusive interdisciplinary approach. Because of that scientific personnel engaged in projects of this type must possess relevant required interdisciplinary skills. Artificial intelligence in particular convolutional neural networks has a wide range of applications, and it could be used to solve complicated problems in all kinds of various fields of science. Thus, the understanding of the principles of neural networks' working is a necessary skill for scientific personnel. In this paper, we're considering practical examples and fields of applications of neural networks in the real world.