Browsing by Author "Soldatenko, Dmytro V."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery through Data Augmentation(Copernicus GmbH (Copernicus Publications) on behalf of the International Society of Photogrammetry and Remote Sensing, 2023) Hnatushenko, Viktoriia V.; Hnatushenko, Volodymyr V.; Soldatenko, Dmytro V.; Heipke, ChristianENG: This study aims to enhance the quality of detecting burned areas in satellite imagery using deep learning by optimizing the training dataset volume through the application of various augmentation methods. The study analyzes the impact of image flipping, rotation, and noise addition on the overall accuracy for different classes of burned areas in a forest: fire, burned, smoke and background. Results demonstrate that while single augmentation techniques such as flipping and rotation alone did not result in significant improvements, a combined approach and the addition of noise resulted in an enhancement of the classification accuracy. Moreover, the study shows that augmenting the dataset through the use of multiple augmentation methods concurrently, resulting in a fivefold increase in input data, also enhanced the recognition accuracy. The study also highlights the need for further research in developing more efficient CNN models and in experimenting with additional augmentation methods to improve the accuracy of burned area detection, which would benefit environmental protection and emergency response services.Item Study of Efficiency of Using IT-Infrastructure as a Service For Cloud Computing(Український державний університет науки і технологій, ННІ «Інститут промислових та бізнес технологій», 2022) Soldatenko, Dmytro V.; Gnatushenko, Viktorija V.ENG: With the growth of the information technology market and the constant increase in demand, companies began to carry an unprecedented burden on their own infrastructure, trying to meet t customers’ growing expectations. Safe, reliable, and fast services are a top priority for companies that are largely trying to meet the expectations of their customers and adjust to the constant changes in the service market. With constant efforts to increase their own computing power, infrastructure and storage space, companies are increasingly finding that the cost of developing and maintaining a reliable, secure, and at the same time scalable infrastructure is prohibitive. To cope with the challenges of acquiring and maintaining their own infrastructure solutions, companies can take advantage of off-the-shelf solutions such as cloud computing. Cloud computing is a fast-growing industry that allows companies not to focus on expanding their own local infrastructure and, instead, move to the use of ready-made Internet services. Cloud service providers provide access to storage and processing, as well as software at affordable and dynamic prices, which allows companies to save money by adopting cloud solutions. Cloud services provide a variety of service models, each capable of meeting a specific set of business requirements and needs. The main service models include Infrastructure as a Service (IaaS), Software as a Service (SaaS) and Platform as a Service (PaaS), the features and disadvantages of which vary and are interchangeable, allowing you to choose a more suitable model. This article explores existing solutions and services and provides the advantages and disadvantages of using one or another solution for various needs and highlighted the most universal solution suitable for most requests. In the study, the most popular solutions related to cloud computing present and analyze their key features. The most powerful and attractive service for processing a large amount of input data, including space images, is IaaS. When used, it provides high speed and availability of resources, adaptation to the task, data security due to distributed storage and processing, which allows increasing performance and minimizing latency for the end user.