Protein fold classification is an important problem in bioinformatics and a challenging task for machine-learning algorithms. In this paper we present a solution which classifies protein folds using Kohonen’s Self-Organizing Map (SOM) and a comparison between few approaches for protein fold classification. We use SOM, Fisher Linear Discriminant Analysis (FLD), K-Nearest Neighbour (KNN), Support...

This paper describes the application of the Self-Organizing Map (SOM) in visual exploration of physical geography data. The main justifications for the application of SOM in this issue is that its stresses local factors and topological order. Public domain thematic maps from Portuguese Environment Institute are used. An adequate geospatial unfolding of SOM is presumed to assist a better represe...

It is expected that the agricultural intensification occurred in recent decades in the Argentine Rolling Pampa significantly alters the SOM reserves. Therefore, it is necessary to identify soil organic carbon (C) and nitrogen (N) fractions to understand the functionality and stabilization of these reserves. Our objectives were to study the NT effect in two crop rotations, corn-double cropped wh...

—This paper presents a constrained self-organizing map (SOM) model for the visualization and reconstruction of the human brain lateral ventricle. The SOM model is a widely used method to approximate large and complex high dimensional data and reduce the data dimension for advanced applications. In our applications, the SOM model is used to deform a spherical network field to a 3D crooked brain ...

In this paper we investigate the performance of the Kohonen’s self organizing map (SOM) as a strategy for the analysis of multispectral and multi-resolution remote sensed images. The paper faces the problem of data fusion, by extracting and combining multi-spectral and textural features. Moreover we address the problem of low-quantity and low-quality of labelled pixels in the training set, inve...

Somatostatin-producing neuroendocrine tumors (SOM-NETs) of the duodenum and pancreas appear to be heterogeneous. To determine their clinicopathological profiles, respective data were analyzed on a series of 82 duodenal and 541 pancreatic NETs. In addition, the clinical records of 821 patients with duodenal or pancreatic NETs were reviewed for evidence of a somatostatinoma syndrome. Predominant ...

The Self-Organizing Map (SOM) is an artificial neural network that is very effective for clustering via visualization. Ideally, so as produce a good model, the output space dimension of the SOM should match the intrinsic dimension of the data. However, because it is very difficult or even impossible to visualize SOM’s with more than two dimensions, the vast majority of applications use SOM with...

Chemical recalcitrance of biomolecules, physical protection by soil minerals and spatial inaccessibility to decomposer organisms are hypothesized to be primary controls on soil organic matter (SOM) turnover. Previous studies have observed increased sequestration of plant derived aliphatic compounds in experimentally warmed soils but did not identify the mechanisms for this enhanced preservation...

As a neural approach, Kohonen's Self-Organizing Map (SOM) has not been explored as thoroughly as the MLP, especially for the soft classification. In this paper, we propose two non-parametric algorithms for the SOM to provide soft classification outputs. These algorithms, which are labeling-frequency-based and are called SOM Commitment (SOMC) and SOM Typicality (SOM-T), expressing in the first c...

Spatiotemporal data pose serious challenges to analysts in geographic and other domains. Owing to the complexity of the geospatial and temporal components, this kind of data cannot be analyzed by fully automatic methods but require the involvement of the human analyst’s expertise. For a comprehensive analysis, the data need to be considered from two complementary perspectives: (1) as spatial di...