Browsing by Author "Belenok, Vadym"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Device for automated leveling(News of the National Academy of Sciences of the Republic of Kazakhstan, 2018) Belenok, Vadym; Burachek, Vsevolod; Malik, Tetiana; Kryachok, Sergíy; Bryk, YaroslavThe article describes the issue of automation of surface leveling performed during the reconstruction of artificial aerodrome covers. The existing methods of surface leveling using satellite technologies, electronic (digital) and laser rotational levels are described. The main drawbacks of existing methods are analyzed, the essence of which is reduced mainly to the large amount of manual measurements. A new mobile device for automated surface leveling is proposed, the distinctive parts of which are mobile platform, leveling optoelectronic device (LOED) and ultrasonic location block. The LOED includes lenses and a double Charge-Coupled Device (CCD) Matrix. To perform the leveling of the surface in the leveling marking the ends of the leveling lines, which are parallel to the longitudinal axis of the leveling plot is done. The leveling lines fix two points (benchmarks) where elevation points are first-order as compared with elevation points of leveling the surface. Two reference sighting targets on the benchmarks are installed. In the memory of the device such data as: instrumental elevations, elevations LOED and elevations sighting targets, as well as the scanning step are entered. The device LOED is installed to the alignment between sighting targets the position in the alignment of the images of targets on the display are controlled. The device is installed sequentially to the points of scanning the surface along the alignment line and define the readings on the LOED matrixes at the points of leveling the surface during stops or movement of the device on the alignment line. As a result of measurements in automatic mode, the instrumental elevations along the alignment line with an adjustable scan step are obtained. Such a device due to increased mobility is effective for leveling large and length areas, such as take-off and landing strip, take-off starts, airplane platforms, etc.Item Machine learning based combinatorial analysis for land use and land cover assessment in Kyiv City (Ukraine)(SPIE (the international society for optics and photonics), 2023-01-24) Belenok, Vadym; Hebryn-Baidy, Liliia; Bielousova, Nataliia; Gladilin, Valeriy; Kryachok, Sergíy; Tereshchenko, Andrii; Alpert, Sofiia; Bodnar, Sergii; Беленок, Вадим Юрійович; Гебрин-Байди, Лілія Василівна; Бєлоусова, Наталія Володимирівна; Гладілін, Валерій Миколайович; Крячок, Сергій Дмитрович; Терещенко, Андрій Олександрович; Альперт, Софія Іоганівна; Боднар, Сергій ПетровичThe main goal of this study is to evaluate different models for further improvement of the accuracy of land use and land cover (LULC) classification on Google Earth Engine using random forest (RF) and support vector machine (SVM) learning algorithms. Ten indices, namely normalized difference vegetation index, normalized difference soil index, index-based built-up index, biophysical composition index, built-up area extraction index (BAEI), urban index, new built-up index, band ratio for built-up area, bare soil index, and normalized built up area index, were used as input parameters for the machine learning algorithms to improve classification accuracy. The combinatorial analysis of the Sentinel-2 bands and the aforementioned indices allowed us to create four combinations based on surface reflectance characteristics. The study includes data from April 2020 to September 2021 and April 2022 to June 2022. The multitemporal Sentinel-2 data with spatial resolutions of 10 m were used to determine the LULC classification. The major land use classes such as water, forest, grassland, urban areas, and other lands were obtained. Generally, the RF algorithm showed higher accuracy than the SVM. The overall accuracy for RF and SVM was 86.56% and 84.48%, respectively, and the mean Kappa was 0.82 and 0.79, respectively. Using the combination 2 with the RF algorithm and combination 4 with the SVM algorithm for LULC classification was more accurate. The additional use of vegetation indices allowed to increase in the accuracy of LULC classification and separate classes with similar reflection spectra