Application of Self-Organizing Maps to the Maritime Environment

@inproceedings{Lobo2009ApplicationOS,
  title={Application of Self-Organizing Maps to the Maritime Environment},
  author={Victor Sousa Lobo},
  booktitle={IF\&GIS},
  year={2009}
}
  • V. Lobo
  • Published in IF&GIS 2009
  • Geography, Computer Science
Self-Organizing Maps (SOMs), or Kohonen networks, are widely used neural network architecture. This paper starts with a brief overview of how SOMs can be used in different types of prob- lems. A simple and intuitive explanation of how a SOM is trained is provided, together with a formal explanation of the algorithm, and some of the more important parameters are discussed. Finally, an overview of different applications of SOMs in maritime problems is presented. 
Brief review of self-organizing maps
  • D. Miljkovic
  • Computer Science
  • 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
  • 2017
TLDR
In this brief review paper basic tenets of self-organizing maps, including motivation, architecture, math description and applications are reviewed. Expand
Pattern recognition in lithology classification: modeling using neural networks, self-organizing maps and genetic algorithms
Effective characterization of lithology is vital for the conceptualization of complex aquifer systems, which is a prerequisite for the development of reliable groundwater-flow andExpand
SUSI: Supervised Self-Organizing Maps for Regression and Classification in Python
TLDR
The freely available SUpervised Self-organizing map (SUSI) Python package which performs supervised regression and classification datasets from two different domains of geospatial image analysis and is characterized by only small performance differences between the training and the test datasets. Expand
A Review of Self-Organizing Map Applications in Meteorology and Oceanography
Coupled ocean-atmosphere science steadily advances with increasing information obtained from long-records of in situ observations, multiple-year archives of remotely sensed satellite images, and longExpand
AN APPROPRIATE FEATURE CLASSIFICATION MODEL USING KOHONEN NETWORK 
TLDR
An Appropriate Feature Classification Model using Kohonen Network based on Recurrent Neural Network approach for feature selection which clusters relevant and irrelevant features from the dataset present in cloud environment is proposed. Expand
Automatic Classification of Sound Speed Profiles using PCA and Self-Organizing Map techniques
TLDR
An automated method of categorizing an underwater environment over time according to its Sound Speed Profile (SSP) is proposed and the Kohonen Self-Organizing Map (SOM) clustering method initialized by Principal Component Analysis (PCA) will be applied to the Strait of Gibraltar region. Expand
Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion
This study focused on demonstrating the use of a self-organizing map (SOM) algorithm to elucidate patterns among variables in simulated syngas combustion. The work was implemented in two stages: (1)Expand
A Segmentation Group by Kohonen Self Organizing Maps ( SOM ) and K-Means Algorithms ( Case Study : Malnutrition Cases in Central Java of Indonesia )
Malnutrition is the condition caused by low consumption of energy and protein in daily food intake. Central Java is one of the provinces in Indonesia which has high number cases of malnutrition.Expand
Adaptive Cooperative Learning Methodology for Oil Spillage Pattern Clustering and Prediction
TLDR
The system would provide a means of understanding the nature, type and severity of oil spillages thereby facilitating a rapid response to impending oils spillages and showing significant classification and prediction improvements. Expand
Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data
TLDR
The Supervised Self-organizing Maps (SuSi) framework is introduced, which can perform unsupervised, supervised and semi-supervised classification as well as regression on high-dimensional data and is summarized in four major findings. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 102 REFERENCES
The self-organizing map, the Geo-SOM, and relevant variants for geosciences
TLDR
A new SOM architecture is presented, the Geo-SOM, which was especially designed to take into account spatial dependency and is given through the analysis of geodemographic data from Lisbon's metropolitan area. Expand
Self-Organizing Maps
  • T. Kohonen
  • Computer Science
  • Springer Series in Information Sciences
  • 1995
TLDR
The mathematical preliminaries, background, basic ideas, and implications of the Self-Organising Map algorithm are expounded in a manner which is accessible without prior expert knowledge. Expand
Self-organizing feature maps predicting sea levels
TLDR
Two concepts, originally developed to solve the problems of convergence of other network types, are proposed to be applied to Kohonen networks: a functional relationship between the number of neurons and theNumber of learning examples and a criterion to break off learning. Expand
A taxonomy of Self-organizing Maps for temporal sequence processing
TLDR
This paper presents a taxonomy for Self-organizing Maps (SOMs) for temporal sequence processing, and a list of some of the existing and relevant papers in this area is presented, and the distinct approaches of SOMs for temporal sequencing are classified into the proposed taxonomy. Expand
Self-organizing Maps as Substitutes for K-Means Clustering
TLDR
This paper briefly reviews different initialization procedures, and proposes Kohonen’s Self-Organizing Maps as the most convenient method, given the proper training parameters, and shows that in the final stages of its training procedure the Self-organizing Map algorithms is rigorously the same as the k-means algorithm. Expand
Growing self-organizing networks - Why ?
TLDR
Two examples are presented to illustrate the speci c properties and advantages of incremental networks and a non-incremental model is used for comparison purposes. Expand
Self-organizing maps: applications to synoptic climatology
Self organizing maps (SOMs) are used to locate archetypal points that describe the multi-dimensional distribution function of a gridded sea level pressure data set for the northeast United States.Expand
Variants of self-organizing maps
TLDR
Two innovations are discussed: dynamic weighting of the input signals at each input of each cell, which improves the ordering when very different input signals are used, and definition of neighborhoods in the learning algorithm by the minimum spanning tree, which provides a far better and faster approximation of prominently structured density functions. Expand
Using self-organizing maps to identify patterns in satellite imagery
TLDR
The self-organizing map (SOM), a type of artificial neural network adept at pattern identification, is described, a promising applied mathematical tool for pattern extraction from many types of data, especially large and complex satellite data sets. Expand
Adaptive learning to environment using Self-Organizing Map and its application for underwater vehicles
  • S. Nishida, K. Ishii, T. Ura
  • Engineering
  • Proceedings of the 2004 International Symposium on Underwater Technology (IEEE Cat. No.04EX869)
  • 2004
Autonomous underwater vehicles (AUVs) have great advantages for activities in deep sea, and expected as the attractive tool. However, AUVs have various problems which should be solved. In this paper,Expand
...
1
2
3
4
5
...