J-Gate Portal

In the paper, the flight time deviation of Lithuania airports has been analyzed. The supervised machine learning model has been implemented to predict the interval of time delay deviation of new flights. The analysis has been made using seven algorithms: probabilistic neural network, multilayer perceptron, decision trees, random forest, tree ensemble, gradient boosted trees, and support vector machines. To find the best parameters which give the highest accuracy for each algorithm, the grid search has been used. To evaluate the quality of each algorithm, the five measures have been calculated: sensitivity/recall, precision, specificity, F-measure, and accuracy. All experimental investigation has been made using the newly collected dataset from Lithuania airports and weather information on departure/landing time. The departure flights and arrival flights have been investigated separately. To balance the dataset, the SMOTE technique is used. The research results showed that the highest accuracy is obtained using the tree model classifiers and the best algorithm of this type to predict is gradient boosted trees.

In Lithuania, the old archival topographic maps of locations of small and medium scale and 1 : 10,000 scale contour photo plans were created on the basis of aerial images. The material of these scales provides documented records on the condition of the objects in the location and the landscape at the moment of aerial photography. Those maps can be used to restore the accurate topographic image of the terrain and buildings in 1945–1951 and in later years and perform the necessary topographic, photogrammetric, and geodetic measurements of the parameters of objects, to identify the location of objects and changes. This information is necessary for a variety of disputed property issues and for building farmhouses in reserves, in areas of forestry land parcels, and for assessment of changes in the landscape. Studies of landscape changes are needed for the assessment of renaturalization processes. This paper presents the geodetic method used for geomorphological changes at the channel of River Žalesa during the period 1942–2017, based on the collected archival cartographic materials: historical topographic maps from archive of the Lithuanian State Company Land Fund, Land Information System, and land management projects and orthophoto maps from Lithuanian spatial information portal and free open-access Sentinel-1 satellite data from the Copernicus Open Access Hub.

This paper focuses on numerical and experimental investigations of a novel design piezoelectric energy harvester. Investigated harvester is based on polygon-shaped cantilever array and employs multifrequency operating principle. It consists of eight cantilevers with irregular design of cross-sectional area. Cantilevers are connected to each other by specific angle to form polygon-shaped structure. Moreover, seven seismic masses with additional lever arms are added in order to create additional rotation moment. Numerical investigation showed that piezoelectric polygon-shaped energy harvester has five natural frequencies in the frequency range from 10 Hz to 240 Hz, where the first and the second bending modes of the cantilevers are dominating. Maximum output voltage density and energy density equal to 50.03 mV/mm3 and 604 μJ/mm3, respectively, were obtained during numerical simulation. Prototype of piezoelectric harvester was made and experimental investigation was performed. Experimental measurements of the electrical characteristics showed that maximum output voltage density, energy density, and output power are 37.5 mV/mm3, 815.16 μJ/mm3, and 65.24 μW, respectively.