Наукові публікації та матеріали кафедри авіаційних комп'ютерно-інтегрованих комплексів (НОВА)
Permanent URI for this collectionhttp://er.nau.edu.ua/handle/NAU/58730
Browse
Browsing Наукові публікації та матеріали кафедри авіаційних комп'ютерно-інтегрованих комплексів (НОВА) by Subject "004.93(045)"
Now showing 1 - 6 of 6
- Results Per Page
- Sort Options
Item Algorithms for the formation of recommendations in the information system(National Aviation University, 2021-10-21) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Oliinuk, Yuriy; Олійник, Юрій ІвановичThe article deals with the problem of scalability and dimension reduction of data in the algorithms of recommendations. It is proposed to improve the item-to-item algorithm by excluding from the user-item matrix elements that that do not have enough estimates. Thus more denser data are used that allows to receive more exact results. Also due to the fact that the dimension of the user-item matrix decreases, the execution time of the algorithm decreases. To solve the problem, the Tachimoto coefficient, the cosine measure, the Pearson correlation coefficient and the Euclidean distance are used to calculate the degree of similarity of the elements. The efficiency of the usual item-to-item algorithm and the algorithm were compared using only the active values in the user-item matrix. The obtained results confirm the efficiency of the item-to-item algorithm based on a dense matrix. The obtained results can be used to optimize the operation of any recommendation system.Item Generation of UAV-based Training Dataset using Semi-supervised Learning(National Aviation University, 2022-09-26) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Kalmykov, Vadym; Калмиков, Вадим ВіталійовичThe paper considers the problem of constructing a training sample based on the use of semi-supervised learning a teacher. The problem statement related to the problem posed is substantiated. It is shown that obtaining a training sample in some cases is a difficult task that requires significant computational and financial costs. The use of semi-supervised learning made it possible to label unlabeled data and thus ensure the creation of a labeled sample of sufficient size. The paper gives examples of generating a training sample, as well as its use for training neural networks, which are used to solve the problem of multiclass classification. Using this approach, you can get a robust data set consisting of a small amount of manually labeled images and a huge amount of pseudo-labeled or augmented data. Using this approach, one can train a classifier to detect and classify any objects in images with bounding boxes and label them accordingly.Item Intelligent on-Board Forest Fire Search System(National Aviation University, 2022-12-27) Sineglazov, V. M.; Синєглазов, Віктор Михайлович; Komapov, A. A.; Комаров, Анатолій АнатолійовичThe paper analyzes the situation with forest fires in Ukraine. It is shown that the situation is deteriorating every year. For forest fire monitoring it is substantiated the need of the integrated use of data from satellites and unmanned aerial vehicles. It has been shown that early detection of a fire before it becomes a disaster is critical to preventing catastrophic fires and saving lives and property. A fire detection approach based on the use of computer vision methods that can work with a non-stationary camera installed on board the unmanned aerial vehicle is substantiated. An approach for detecting a "spot" of fire using convolutional neural networks is proposed. In our task of detecting a forest fire using an unmanned aerial vehicle, tracking based on detection is chosen as the model initialization method, when objects are first detected using the detection method and then linked into tracks (association). The Yolov4-tiny architecture was chosen as the architecture of the neural network detector, which provides high accuracy and speed of binary classification.Item Semi-controlled learning in information processing problems(National Aviation University, 2022-01-05) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Chumachenko, Olena; Чумаченко, Олена Іллівна; Heilyk, Eduard; Хейлик, Едуард ВолодимировичThe article substantiates the need for further research of known methods and the development of new methods of machine learning – semi-supervized learning. It is shown that knowledge of the probability distribution density of the initial data obtained using unlabeled data should carry information useful for deriving the conditional probability distribution density of labels and input data. If this is not the case, semi-supervised learning will not provide any improvement over supervised learning. It may even happen that the use of unlabeled data reduces the accuracy of the prediction. For semi-supervised learning to work, certain assumptions must hold, namely: the semi-supervised smoothness assumption, the clustering assumption (low-density partitioning), and the manifold assumption. A new hybrid semi-supervised learning algorithm using the label propagation method has been developed. An example of using the proposed algorithm is given.Item Training data sampling for conventional neural networks configuring(National Aviation University, 2020-12-12) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Kot, Ananatoliy; Кот, Анатолій ТарасовичThe problem of generating training data for setting up the convolutional neural networks is considered, which is of great importance in the construction of intelligent medical diagnostic systems, where due to the lack of elements of the training sample, it is proposed to use the approaches of artificial data multiplication based on the initial training sample of a fixed size for the image processing (the results of the ultrasound, CT and MRI). It shows that the increase of the training sample resulted in less informative and poor quality elements, which can introduce extra errors in the goal achievement. To eliminate this situation the algorithm for assessing the quality of a sample element with the subsequent removal of uninformative elements is proposed.Item Twitter Fake News Detection Using Graph Neural Networks(National Aviation University, 2023-12-27) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Bylym, Kyrylo; Билим, Кирило ІгоровичThis article is devoted to the intellectual processing of text information for the purpose of detecting rail news. To solve the given task, the use of deep graph neural networks is proposed. Fake news detection based on user preferences is augmented with deeper graph neural network topologies, including Hierarchical Graph Pooling with Structure Learning, to improve the graph convolution operation and capture richer contextual relationships in news graphs. The paper presents the possibilities of extending the framework of fake news detection based on user preferences using deep graph neural networks to improve fake news recognition. Evaluation on the FakeNewsNet dataset (a subset of Gossipcop) using the PyTorch Geometric and PyTorch Lightning frameworks demonstrates that the developed deep graph neural network model achieves 94% accuracy in fake news classification. The results show that deeper graph neural networks with integrated text and graph features offer promising options for reliable and accurate fake news detection, paving the way for improved information quality in social networks and beyond.