Перегляд за Автор "Kussul, N. M."

Зараз показуємо 1 - 2 з 2
  • Ескіз
    ДокументВідкритий доступ
    Enhancing Rural Infrastructure in Ukraine: An Integrated Geospatial Approach
    (КПІ ім. Ігоря Сікорського, 2024) Potuzhnyi, B. V.; Svirsh, V. R.; Kussul, N. M.
    This study introduces a unified framework for improving rural infrastructure in Ukraine, combining geospatial data analysis and clustering techniques. By meticulously preparing and validating OpenStreetMap data for over 10 000 villages, we create a reliable foundation for our analysis. Utilizing this validated dataset, we apply advanced clustering to categorize villages by infrastructure quality, highlighting developmental gaps. Our approach merges data validation with an evaluative system to model village infrastructure, offering targeted insights for policy and development strategies. This integrated method provides a way to address infrastructure disparities, enabling data-driven decision-making for rural enhancement. Our findings aim to guide policymakers and development agencies towards strategic interventions, showcasing the potential of combining geospatial analysis with clustering for rural development.
  • Ескіз
    ДокументВідкритий доступ
    Statistical methods of feature engineering for the problem of forest state classification using satellite data
    (КПІ ім. Ігоря Сікорського, 2024) Salii, Y. V.; Lavreniuk, A. M.; Kussul, N. M.
    Timely detection of forest diseases is an important task for their prevention and spread limitation. The usage of satellite imagery provides capabilities for large-scale forest monitoring. Machine learning models allow to automate the analysis of these data for anomaly detection indicating diseases. However, selecting informative features is key to building an effective model. In this work, the application of Bhattacharyya distance and Spearman’s rank correlation coefficient for feature selection from satellite images was investigated. A greedy algorithm was applied to form a subset of weakly correlated features. The experiment showed that selected features allow for improving the classification quality compared to using all spectral bands. The proposed approach demonstrates effectiveness for informative and weakly correlated feature selection and can be utilized in other remote sensing tasks.