With the continuous air traffic growth and limits of resources, there is a need for reducing congestion airspace systems. Nowadays, several projects are launched, aimed at modernizing global transportation system management. In recent years, special interest has been paid to solution dynamic configuration problem. Airspace sector configurations be dynamically adjusted provide maximum efficiency flexibility in response changing weather conditions. The main objective this work automatically...

In this paper, we present an efficient lung nodule classification system. The proposed system extracts various texture and morphological features from the pre-marked regions of interest containing nodules. Gray Level Co-occurrence Matrix method is applied to extract characteristics Additional are extracted images transformed by discrete wavelet transform extend variety features. Attribute selection performed on resulting feature vector reduce redundancy dataset. Resulting collection used...

In recent years, special interest has been paid to the solution of sector design problem. The airspace is partitioned into sectors, each them being controlled by a group controllers. Airspace sectors should be designed cautiously, ensuring that no would overloaded during day. objective an process adapt according evolution traffic. aim presented work propose new global method for sectorization European based on novel mathematical modeling and heuristic optimization methods. main purpose this...

Objective. To develop criteria for prognosis of the outcome ischemic stroke, taking into account age, dynamics state assessment, Rankin and NIHSS scales readings fact disability in long-term period. The universal reliable criteria, that allow to predict have not been developed yet. Material methods. study group consisted 246 patients with stroke aged 18 44 who were observed from 2008 2021. Results. It is impossible a period reliably. Predicting using significant acute allows recovery mild...

This paper focuses on the process of generating a sequence sector configurations composed two airspace component types Sharable Airspace Modules (SAMs) and Sectors Building Blocks (SBBs). An algorithm has been developed that manages main features dynamic sectors configuration (including design criteria). In order to make it run efficiently pre-processing step will be presented create graph modelling inputs. Based this initial graph, mathematical model is defined which can summarized by...

Creating models which are able to accurately predict the distribution of pollutants based on a limited set input data is an important task in environmental studies. In paper two neural approaches: (multilayer perceptron (MLP)) and generalized regression network (GRNN)), geostatistical (kriging cokriging), using for modeling forecasting dust concentrations snow cover. The area study under influence emissions from copper quarry several industrial companies. comparison mentioned approaches...

The paper considered the use of one most accurate artificial neural networks for predicting time series - a nonlinear autoregressive network with external input (NARX) dynamics changes in concentrations main greenhouse gases. data were obtained course monitoring gases on Arctic island Belyy, Russia. surface concentration methane, carbon dioxide, monoxide and water vapor used. A interval 168 hours was chosen study during summer period (July-August 2016). NARX model accurately predicted all

The work deals with the application of neural networks residual kriging (NNRK) to spatial prediction abnormally distributed soil pollutant (Cr). It is known that combination geostatistical interpolation approaches (kriging) and leads significantly better accuracy productivity. Generalized regression multilayer perceptrons are classes widely used for continuous function mapping. Each network has its own pros cons; however both demonstrated fast training good mapping possibilities. In work, we...

The study is based on the data obtained as a result of soil screening in city Noyabrsk, Russia. A comparison two types neural networks most commonly used this type research was carried out: multi-layer perceptron (MLP), generalized regression network (GRNN), and combined MLP ordinary kriging approach (MLPRK) for predicting spatial distribution chemical element Chromium (Cr) surface layer urbanized territory. model structures were developed using computer modeling, minimizing root mean...

When studying the processes associated with global warming, forecasts of time series are very important. The present study used data concentration greenhouse gas methane in surface layer atmospheric air on Arctic island Belyi, Russia. For work, a interval 170 hours was chosen. modelling, model based nonlinear autoregressive neural network an external input (NARX) used. As training algorithm three types were applied: Levenberg-Marquart (LM), LM Bayesian regularization (BR), and gradient...

The paper predicts the changes in concentration of one main greenhouse gases - methane (CH4). forecast was made for three different time periods, each which had its own characteristics dynamics CH4. Data study were collected while monitoring content surface layer atmospheric air Russian Arctic (Bely Island, Yamalo-Nenets Autonomous Okrug). We compared results models prediction based on two types artificial neural networks: Elman and nonlinear autoregressive network with external input...

Statistical analysis of the monitoring data industrial enterprises influence zones is an important part researches related to natural environment changes. In present study, a cluster elemental composition snow cover in vicinity copper mine was carried out. The were obtained as result chemical samples collected during annual environmental region Rezh town (the Middle Ural Russia), where Safyanovsky Copper Mine and Rezhevsky Nickel Plant are located. elements identified by grouped according...

A method of the data partitioning to restore spatial distribution trait was proposed. The controlled procedure source applied model based on artificial neural networks (ANN). content chemical element Chromium (Cr) in surface layer soil urbanized area modelled. most accurate results were shown by model, method, which took into account quota and variation values Cr soil. described is relatively simple implement modern computational packages can be used for modeling variables.

The paper proposes an original approach for predicting the values of spatial series. This can be used, in particular, to recover missing data. counter-prediction method was tested on a model artificial neural network (ANN), which is sequentially trained preceding predicted segment series left and right. final prediction weighted average results these two sets. We have work using example dust content snow cover. 256 samples were taken with step 0.2 m along line area dumps existing open pit...

In this paper, several types of artificial neural networks (ANNs) are considered to predict changes in the concentration one main greenhouse gases - carbon dioxide. The study is based on data from surface CO2 obtained course monitoring dynamics Arctic island Belyy, Russia. forecast was using following ANN: Nonlinear Autoregressive Neural Network with an External Input (NARX), Elman (ENN), and Multi-Layer Perceptron (MLP). For study, time interval 168 hours chosen summer period (July-August...

Objective: to study the anamnestic, clinical and laboratory features of acute period ischemic stroke (IS) determine risk factors for its development in young patients. Patients methods. Clinical statistical processing data 256 patients aged 18 44 years included, who had IS, confirmed by computed and/or magnetic resonance imaging brain period, was carried out. Furthermore, 154 117 healthy participants, made up control group, eight polymorphisms thrombophilic spectrum genes were determined –...

This paper gives a comparative analysis of methods for classifying pulmonary nodules using computer-tomography images and evaluation the information content attributes that are used, as well an estimate effectiveness various machine-learning algorithms. Problems involving visual classification conditions improving its accuracy investigated. Sets most informative chosen nodules. The accuracies with which classified into benign malignant obtained.