This paper introduces a novel approach to Self-Organizing Maps which is capable of processing graphs such that the context of vertices and sub-graphs are considered in the mapping process. The result is that any vertex in a graph is mapped onto an n-dimensional map depending on its label and the graph structure as a whole. Experimental results demonstrate that the proposed approach achieves the...

Both Topic Maps and RDF are popular semantic web standards designed for machine processing of web documents. Since these representations were originally created for different purposes, they have conceptual differences in their data models, and therefore have different tools to parse, store, and query them. However, there are more tools to handle RDF data than those existing for Topic Maps. Our ...

More and more private citizens collect and publish environmental data via web-based geographic information systems. These systems face two challenges: The user interface must be intuitive and the processing of geographic information must account for cognitive impact. We propose to use sketch maps as the medium for interaction, because they reflect a person’s spatial knowledge. Information from ...

Abstract Animals can efficiently process sensory stimuli whose attributes vary over orders of magnitude by devoting specific neural pathways to process specific features in parallel. Weakly electric fish offer an attractive model system as electrosensory pyramidal neurons responding to amplitude modulations of their self-generated electric field are organized into three parallel maps of the bod...

This paper presents a taxonomy for Self-organizing Maps (SOMs) for temporal sequence processing. Four main application areas for SOMs with temporal processing have been identified. These are prediction, control, monitoring and data mining. Three main techniques have been used to model temporal relations in SOMs: 1) pre-processing or post-processing the data, but keeping the basic SOM algorithm;...

Ribosomal RNA precursors and mature 28S ribosomal RNA from HeLa cells display a highly reproducible secondary structure of hairpin loops after they are spread and examined in an electron microscope. This structure was used to map the linear arrangement of these molecules. Partial digestion with 3'-exonuclease from ascites cell nuclei established that the 28S RNA region is located at the 5'-end ...

Kohonen’s Self-Organizing Map (SOM) is a general unsupervised tool for ordering highdimensional statistical data so that neighboring nodes on the map represent similar inputs. Often the SOM is applied to numerical data in application areas like pattern recognition, signal processing, and multivariate statistical analysis. The SOM can also be used to find statistical similarities between symbols...

Artificial neural networks (ANNs) have found widespread application in human image processing systems, but often they play only a small part in a large complex process. We investigate the Self-Organizing Map or SOM, a particular type of unsupervised ANN, as a core image processing component, by applying the standard SOM to the common tasks of image quantisation, skin detection and feature locat...

Perhaps the clearest organizing principle in sensory systems is the existence of maps, in which there is an orderly and systematic layout of the stimulus space on a two-dimensional array of neurons. Usually, the layout of the stimulus on the receptor sheet is reproduced so that neurons that innervate adjacent sites on the receptor sheet project to adjacent sites in the central map. Thus, in the...

Environment maps are a popular method of reproducing complex natural lighting. However, current methods for hardware environment map shadows depend on significant pre-computation and cannot support dynamic objects. This work presents a pre-process that decomposes an environment map into two components: a set of area lights and an ambient map. Once the map is split into these components, each is...