Персона: Кулик, Сергей Дмитриевич
Загружается...
Email Address
Birth Date
Научные группы
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.
Статус
Фамилия
Кулик
Имя
Сергей Дмитриевич
Имя
5 results
Результаты поиска
Теперь показываю 1 - 5 из 5
- ПубликацияТолько метаданныеUsing Electronic Nose in Forensic Odor Analysis(2024) Shtanko, A.; Kulik, S.; Кулик, Сергей Дмитриевич
- ПубликацияОткрытый доступUsing convolutional neural networks for recognition of objects varied in appearance in computer vision for intellectual robots(2020) Kulik, S.; Shtanko, A.; Кулик, Сергей Дмитриевич© 2020 The Authors. Published by Elsevier B.V.The paper describes an effort to train a convolutional neural network capable of reliably recognizing complex objects that are highly varied in their shapes and appearances in images. Neural networks show very good results on objects that have constant appearances but may have trouble recognizing abstract objects that appear in different shapes, art-styles and lack solid structure, for example, national flags. In an image, a flag may appear waving on a pole, as an element of clothes, in a form of stickers, etc. Due to these differences in appearance computer vision systems may show unsatisfactory results on these types of objects. However, detecting such objects is a necessary task in computer vision, especially for intelligent robots in order to understand the environment. The aim of the research is to apply convolutional neural networks for the detection of flags. In this research, we prepared training and testing sets of objects, trained a neural network for detection task, conducted testing experiments and measured the neural net's performance. These results can be applied in cognitive and robotics technologies as well as general computer vision tasks.
- ПубликацияТолько метаданныеPreliminary Experiment on Emotion Detection in Illustrations Using Convolutional Neural Network(2021) Shtanko, A.; Kulik, S.; Кулик, Сергей Дмитриевич© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.The paper describes an experiment on emotion detection in images, specifically illustrations and cartoon images. Usually, detection and classification of emotions are performed on human faces so the algorithm can learn, for example, what a “happy human face” looks like. These algorithms probably can’t transfer their understanding of happiness features onto different types of objects, like animals or cartoon illustrations. We, humans, can recognize and detect signs of emotions (although maybe falsely) in new and unusual objects. Developing an algorithm capable of recognizing emotions in objects it wasn’t trained on would allow for better human-like robots and systems. This is a preliminary study on how well knowledge gained by a typical neural network detection system on a set of objects transfers to new, unknown objects. The neural network detection system used in this study is YOLO. We collected small training datasets using cartoon illustrations of several animals of two categories: happy and sad. We tested the trained network on a set of illustrations depicting a different animal the network hasn’t seen in training. The best performance achieved is 0.69 F1-score.
- ПубликацияОткрытый доступIncreasing the effectiveness of intelligent module by enlarging training dataset from real data(2021) Shtanko, A.; Kulik, S.; Кулик, Сергей Дмитриевич© 2020 Elsevier B.V.. All rights reserved.This paper concentrates on the design of the intelligent module and neural networks in the area of intelligent data processing. It raises the following issues: what real problems are faced in training datasets for neural networks, how they can be solved, and how an intelligent module can be useful in this area. During the development of a neural network system, it is important to improve the network performance after the system's release. Additional training data need to be taken from real-life data, combined with existing training data to produce a better version of the neural network's weights. Since the number of these samples can be large, it's useful to filter out samples similar to those already included in training data. We designed a module architecture and an algorithm that employ cascading filters in order to find the best samples from real data for the training dataset. The key feature of the intelligent module is that it does not generate a completely new dataset, but uses saved data from the real-life samples and samples from the existing database. Weights are then updated during the training of the neural network and then filtered using a special algorithm.
- ПубликацияТолько метаданныеPreliminary experiments on psoriasis classification in images(2022) Shtanko, A.; Kulik, S.; Кулик, Сергей Дмитриевич