Marta Wlodarczyk-Sielicka

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.

Technology of Spatial Data Geometrical Simplification in Maritime Mobile Information System for Coastal Waters

Abstract The paper undertakes the subject of spatial data pre-processing for marine mobile information systems. Short review of maritime information systems is given and the focus is laid on mobile systems. The need of spatial data generalization is underlined and the concept of technology for such generalization in mobile system is presented. The research part of the paper presents the results of analyzes on selected parameters of simplification in the process of creating mobile navigation system for inland waters. In the study authors focused on selected layers of system. Models of simplification for layers with line features and with polygons were tested. The parameters of tested models were modified for the purposes of study. The article contains tabular results with statistics and spatial visualization of selected layers for individual scales.

Selection of SOM parameters for the needs of clusterization of data obtained by interferometric methods

The article presents a detailed analysis of parameter settings of self-organizing map (SOM) for the clusterization of bathymetric data obtained using interferometric techniques. Clusterization using SOM is one of the stages of a new a geodata reduction method being currently researched by the authors for the purpose of a bathymetric map construction. In the research authors used data obtained by GeoSwath+.-interferometric sonar system. Test data gathered from the area of 100m2 included 3760 data points. During the tests the authors focused primarily on setting individual network parameters in the course of network training and also on their importance in the clustering of bathymetric data. A total of forty-eight different scenarios of SOM parameter settings were tested. In the article detailed analysis of the obtained results is presented with an emphasis on the use of SOM in future studies related to new geodata reduction method.

Importance of Neighborhood Parameters During Clustering of Bathymetric Data Using Neural Network

The main component, which has a significant impact on safety of navigation, is the information about depth of a water area. The commonly used solution for depths measurement is usage the echosounders. One of the problems associated with bathymetric measurements is recording a large number of data. The fundamental objective of the author’s research is the implementation of a new reduction method for geodata to be used for the creation of bathymetric map. The main purpose of new reduction algorithm is that, the position of point and the depth value at this point will not be an interpolated value. In the article, author focused on importance of neighborhood parameters during clustering of bathymetric data using neural network (self-organizing map) – it is the first stage of the new method. During the use of Kohonen’s algorithm, the author focused on two parameters: topology and initial neighborhood size. During the test, several populations were created with number of clusters equal 25 for data collected from the area of 625 square meters (dataset contains of 28911 XYZ points). In the next step, statistics were calculated and results were presented in two forms: tabular form and as spatial visualization. The final step was their comprehensive analysis.

Comparison of selected clustering algorithms of raw data obtained by interferometric methods using artificial neural networks

The article presents a particular comparison of selected clustering algorithms of data obtained by interferometrie methods using artificial neural networks. For the purposes of the experiment original data from Szczecin Port have been tested. For collecting data authors used the interferometric sonar system GeoSwath Plus 250 kHz. GeoSwath Plus offers very efficient simultaneous swath bathymetry and side scan seabed mapping. During the use of Kohonens algorithm, the network, during learning, use the Winner Take All rule and Winner Take Most rule. The parameters of the tested algorithms were maintained at the level of default. During the research several populations were generated with number of clusters equal 9 for data gathered from the area of 100m2. In the subsequent step statistics were calculated and outcomes were shown as spatial visualization and in tabular form.

General concept of reduction process for big data obtained by interferometric methods

Interferometric sonar systems apply the phase content of the sonar signal to measure the angle of a wave front returned from the seafloor or from a target. It collect a big data - datasets that are so large or complex that traditional data processing application software is inadequate to deal with them. The recording a large number of data is associated with the difficulty of their efficient use. So data have to be reduced. The main goal of new reduction method developed by the authors is that, the data after reduction will not be an interpolated value. The proposed method is consists of two main stage: the grouping of data and the generalization of data. The first stage consists of two steps: initial division and clustering. In the first step, the area will be divided into a grid of squares. The maximum level of generalization of the grid will be founded and its size will be defined. In the second step of data grouping, namely clustering artificial neural networks will be used. Artificial neural networks are good alternative to traditional methods of clustering data. The authors decided to use artificial intelligence methods during the processing of data obtained by interferometric methods because it is novel approach to such issues and provides satisfactory results. The authors goal is to represent each group by a single sample depending on the compilation scale of final product. The article contains a detailed description of the proposed method.

Problem of Bathymetric Big Data Interpolation for Inland Mobile Navigation System

Depth information is crucial in most navigational analysis and decision support implemented in existing inland navigation systems. Bathymetric data sets needs to be preprocessed and converted into Digital Terrain Model by interpolation methods to provide different vector layer for Electronic Navigational Chart. Data for inland waters needs to be precise and valid due to quickly alternating inland environment and much shallower areas than on marine waters. At the same time visual effect of created layers needs to be readable and easily interpreted by a navigator. In this paper authors analyze different interpolation method for DTM building from the perspective of accepted criteria. Created depth contours are the base of navigational analysis provided by mobile inland navigation system MOBINAV. The experiments used real inland data from bathymetric surveys conducted on waters of Szczecin area.

MSIS sonar image segmentation method based on underwater viewshed analysis and high-density seabed model

High resolution images of Mechanically Scanned Imaging Sonars can bring detailed representation of underwater area if favorable conditions for acoustic signal to propagate are provided. However to properly asses underwater situation based solely on such data can be challenging for less than proficient interpreter. In this paper we propose a method to enhance interpretative potential of MSIS image by dividing it in to subareas depending on information about slope gradient and direction derived from high-density bathymetric model using viewshed analysis. Additional image channel is created to store data on adherence of sonar data into each class representing different information related to sea bed shape. The paper also contains details on segmentation algorithm using traditional image processing method

Interpolating Bathymetric Big Data for an Inland Mobile Navigation System

Depth information is crucial in most navigational analysis and decision support implemented in existing inland navigation systems. Bathymetric data sets need to be preprocessed and converted into Digital Terrain Model by interpolation methods to provide different vector layers for Electronic Navigational Chart. Data for inland waters needs to be precise and valid due to quickly alternating inland environment and much shallower areas than on marine waters. At the same time visual effect of created layers needs to be readable and easily interpreted by a navigator. In this paper authors analyze different interpolation method for DTM building from the perspective of accepted criteria. Created depth contours are the base of navigational analysis provided by mobile inland navigation system MOBINAV. The experiments used real inland data from bathymetric surveys conducted on waters of Szczecin area. DOI: http://dx.doi.org/10.5755/j01.itc.47.2.19561

The Use of an Artificial Neural Network for a Sea Bottom Modelling.

Currently data are often acquired by using various remote sensing sensors and systems, which produce big data sets. One of important product are digital models of geographical surfaces that include the sea bottom surface. To improve their processing, visualization and management is often necessary reduction of data points. Paper presents research regarding the application of neural networks for bathymetric geodata reductions. Research take into consideration radial networks, single layer perceptron and self-organizing Kohonen network. During reconstructions of sea bottom model, results shows that neural network with less number of hidden neurons can replace original data set. While the Kohonen network can be used for clustering during reduction of big geodata. Practical implementation of neural network with creation of surface models and reduction of bathymetric data is presented.