Andrzej Stateczny

Self-organizing Artificial Neural Networks into Hydrographic Big Data Reduction Process

The article presents the reduction problems of hydrographic big data for the needs of gathering sound information for Navigation Electronic Chart (ENC) production. For the article purposes, data was used from an interferometric sonar, which is a modification of a multi-beam sonar. Data reduction is a procedure meant to reduce the size of the data set, in order to make them easier and more effective for the purposes of the analysis. The authors‘ aim is to examine whether artificial neural networks can be used for clustering data in the resultant algorithm. Proposed solution based on Kohonen network is tested and described. Experimental results of investigation of optimal network configuration are presented.

Concept of Neural Model of the Sea Bottom Surface

This paper presents concept of neural model of the sea bottom surface, which could be implemented in marine numerical maps. The model consists of self-organizing network and set of trained networks used in surface approximation. Self-organizing networks firstly solves problem of division of data points into training subsets. Secondly it classifies any input data to one of approximating network. Set of approximating networks is used to calculate depth value at any coordinates of point within surface domain. An example illustrates reconstruction of surface based on neural model of bottom surface.

Radar and Automatic Identification System Track Fusion in an Electronic Chart Display and Information System

This paper presents the results of research on the fusion of tracking radar and an Automatic Identification System (AIS) in an Electronic Chart Display and Information System (ECDIS). First, the concept of these systems according to the International Maritime Organization (IMO) is described, then a set of theoretical information on radar tracking and the fusion method itself is given and finally numerical results with real data are presented. Two methods of fusion, together with their parameters, are examined. A proposal for calculating the covariance matrix for radar and AIS data is also given, and the paper ends with conclusions.

Diffraction of a Gaussian beam in a three-dimensional smoothly inhomogeneous medium: an eikonal-based complex geometrical-optics approach

We present an ab initio account of the paraxial complex geometrical optics (CGO) in application to scalar Gaussian beam propagation and diffraction in a 3D smoothly inhomogeneous medium. The paraxial CGO deals with quadratic expansion of the complex eikonal and reduces the wave problem to the solution of ordinary differential equations of the Riccati type. This substantially simplifies the description of Gaussian beam diffraction as compared with full-wave or parabolic (quasi-optics) equations. For a Gaussian beam propagating in a homogeneous medium or along the symmetry axis in a lenslike medium, the CGO equations possess analytical solutions; otherwise, they can be readily solved numerically. As a nontrivial example we consider Gaussian beam propagation and diffraction along a helical ray in an axially symmetric waveguide medium. It is shown that the major axis of the beams elliptical cross section grows unboundedly; it is oriented predominantly in the azimuthal (binormal) direction and does not obey the parallel-transport law.

Sensor data fusion techniques for environment modelling

In the article data fusion techniques for underwater environment modelling are presented. For better understanding the problem, authors divided data fusion techniques into three parts, in reference to the output information that needed to be obtained.

Clustering Bathymetric Data for Electronic Navigational Charts

An electronic navigational chart is a major source of information for the navigator. The component that contributes most significantly to the safety of navigation on water is the information on the depth of an area. For the purposes of this article, the authors use data obtained by the interferometric sonar GeoSwath Plus. The data were collected in the area of the Port of Szczecin. The samples constitute large sets of data. Data reduction is a procedure to reduce the size of a data set to make it easier and more effective to analyse. The main objective of the authors is the compilation of a new reduction algorithm for bathymetric data. The clustering of data is the first part of the search algorithm. The next step consists of generalisation of bathymetric data. This article presents a comparison and analysis of results of clustering bathymetric data using the following selected methods: K -means clustering algorithm, traditional hierarchical clustering algorithms and self-organising map (using artificial neural networks).

Hierarchical Hydrographic Data Fusion for Precise Port Electronic Navigational Chart Production

One of crucial problems in the process of precise Port Electronic Navigational Chart (Port ENC) production is the seabed objects charting. General knowledge about the underwater objects is very important for the improvement in navigational safety, especially important in harbour areas. The article presents the concept of hierarchical hydrographic data fusion from different hydrographical sources for seabed object‘s detection. Simultaneous processing of 3D seabed model obtained by measuring the water depths, sonar mosaicked images (illustrating the seabed characteristic) and the magnetic anomalies map could be remarkably helpful for discrimination of ferrous features, establishing their highly precise positions and to determine their placing characteristics. An attempt to integrate all the above is expected to provide a significant enhancement of the interpretation of the whole context of the seabed situation. The image obtained from hydrographic data will be much more helpful than considering all acquired information separately as individual data sets. This approach is believed to be of great importance for Port ENC production process.

Radar sensors implementation in river information services in Poland

Implementation of River Information Services in Poland on area of Lower Odra river according to RIS Directive was done in 2014. Several kinds of sensors was used during system construction like AIS base station, CCTV cameras, FMCW radars, radar water level gauges, hydro meteorological station. In the article problems of radar sensors - surveillance radar and radar water level sensors implementation are described.

Verification of multiple model neural tracking filter with ship's radar

The paper presents the research focused on verification of multiple model neural filter in real environment. The filter is a result of the works in the research project and is implemented as a software application. The application is then connected to real radar making the off-line verification possible. The filter was checked against IMO requirements and was compared to other commercially used filters. Estimation errors and delay was the basis for the verification. Achieved results show that proposed solution might be an interesting alternative for numerical filters.

Optimization of multiple model neural tracking filter for marine targets

The paper presents the research on optimizing multiple model neural filter with the use of Monte Carlo simulation. GRNN filters are used as elementary filters and different parameters of them are examined. The paper includes theoretical background of the research, analysis of a problem and a set of numerical experiments. The research was made with the use of Monte Carlo simulation. The results of the optimization can be used in further works with the filter and for final verification of the method.