Generating Concept Trees From Dynamic Self-Organizing Map

Neural Networks, 2013

This paper presents a new unsupervised learning method based on growing processes and autonomous self-assembly rules. This method, called Growing Self-organizing Trees (GSoT), can grow both network size and tree topology to represent the topological and hierarchical dataset organization, allowing a rapid and interactive visualization. Tree construction rules draw inspiration from elusive properties of biological organization to build hierarchical structures. Experiments conducted on real datasets demonstrate good GSoT performance and provide visual results that are generated during the training process.

Information Sciences, 2004

The Self-Organizing Map (SOM) is a powerful tool in the exploratory phase of data mining. It is capable of projecting high-dimensional data onto a regular, usually 2-dimensional grid of neurons with good neighborhood preservation between two spaces. However, due to the dimensional conflict, the neighborhood preservation cannot always lead to perfect topology preservation. In this paper, we establish an Expanding SOM (ESOM) to preserve better topology between the two spaces. Besides the neighborhood relationship, our ESOM can detect and preserve an ordering relationship using an expanding mechanism. The computation complexity of the ESOM is comparable with that of the SOM. Our experiment results demonstrate that the ESOM constructs better mappings than the classic SOM, especially, in terms of the topological error. Furthermore, clustering results generated by the ESOM are more accurate than those obtained by the SOM.

Pattern discovery from time series is an important task in many applications. The unsupervised self-organizing map (SOM) has been widely used in data mining as well as in time series knowledge discovery. However, the traditional SOM has two main limitations: the static architecture and the lacking ability for the representing of hierarchical relations of the data. To overcome these limitations the growing hierarchical self-organizing map (GHSOM) is used to analyze time series in this paper. The experiments conducted on several data sets confirm that the GHSOM can form an adaptive architecture, which grows in size and depth during its training process, thus to unfold the hierarchical structure of the analyzed time series data. It is expected that this method will be effective and efficient to implement and will provide a useful practical tool for pattern discovery from large time series databases.

Abstract—The self-organizing map (SOM) is an excellent tool in exploratory phase of data mining. It projects input space on prototypes of a low-dimensional regular grid that can be effectively utilized to visualize and explore properties of the data. When the number of SOM units is large, to facilitate quantitative analysis of the map and the data, similar units need to be grouped, i.e., clustered. In this paper, different approaches to clustering of the SOM are considered. In particular, the use of hierarchical agglomerative clustering and partitive clustering using -means are investigated. The two-stage procedure—first using SOM to produce the prototypes that are then clustered in the second stage—is found to perform well when compared with direct clustering of the data and to reduce the computation time.

Due to the characteristics offered by automated management systems , municipal administrations are now attempting to store digital information instead of keeping their physical documents. One consequence of such fact is the generation of large volume of data. Usually, these data are collected by ICT technologies and then stored in transactional databases. In this environment, collected data might have complex internal relationships. This may be an issue to identify patterns and behaviors. Many institutions use data mining techniques for recognize hidden patterns and behaviors in their operational data. These patterns can assist to future activities planning and provide better management to financial resources. Intelligent analysis can be realized using the Support Tools and Support Decision Making (STSDM). These tools can analyze large volume of data through previously established rules. These rules are presented for STSDM in the training phase, and the tool learns about the patterns that should look. This paper proposes a model to support decision making based on self-organized maps. This model, applied to electronic government tools, can recognize patterns in large volume of data without the set of rules for training. To perform our case study, we use data provided by the city of Campinas, Sao Paulo.

2003

New data acquisition techniques are offering tremendous opportunities that result in more and more geospatial data to be handled. Analyzing these data becomes a difficult task due to the size of datasets, their complexity, scaling problems, and hidden patterns. The complexity of the attribute or feature space in such large datasets as well as related computational burdens, do not always allow traditional deductive and statistically based approaches to analysis to scale well to the data. Like many techniques applied to data analysis (statistical methods, artificial intelligence using rulebased systems and decision trees), Artificial Neural Networks are an emerging solution for data analysis and pattern recognition. Among the Neural Network models, Self-Organizing Map (SOM) is often seen as a promising technique for exploratory analysis of data. There is also an increasing need to organize and support user’s information exploration in a way that reduces complexity and facilitates the ...

Growing self-organizing map (GSOM) has been introduced as an improvement to the self-organizing map (SOM) algorithm in clustering and knowledge discovery. Unlike the traditional SOM, GSOM has a dynamic structure which allows nodes to grow reflecting the knowledge discovered from the input data as learning progresses. The spread factor parameter (SF) in GSOM can be utilized to control the spread of the map, thus giving an analyst a flexibility to examine the clusters at different granularities. Although GSOM has been applied in various areas and has been proven effective in knowledge discovery tasks, no comprehensive study has been done on the effect of the spread factor parameter value to the cluster formation and separation. Therefore, the aim of this paper is to investigate the effect of the spread factor value towards cluster separation in the GSOM. We used simple k-means algorithm as a method to identify clusters in the GSOM. By using Davies–Bouldin index, clusters formed by different values of spread factor are obtained and the resulting clusters are analyzed. In this work, we show that clusters can be more separated when the spread factor value is increased. Hierarchical clusters can then be constructed by mapping the GSOM clusters at different spread factor values.

2009

2006

The Self-Organizing map (SOM), a powerful method for data mining and cluster extraction, is very useful for processing data of high dimensionality and complexity. Visualization methods present different aspects of the information learned by the SOM to gain insight and guide segmentation of the data. In this work, we propose a new visualization scheme that represents data topology superimposed on the SOM grid, and we show how it helps in the discovery of data structure.

1999

Exploratory data mining using artificial neural networks offers an alternative dimension to data mining, in particular techniques geared towards data clustering and classification. In this paper, we argue the case for using neural networks as a viable data mining tool that can provide statistical insights and models from large data-sets. We demonstrate how Self-Organizing Kohonen Maps, an unsupervised learning neural network paradigm, can be efficaciously used for data mining purposes, in particular for data clustering applications. We show that high-dimensional data can be projected to a lower dimension and that data can be clustered together whilst preserving essential information. The Kohonen Map based data-clustering technique is applied to the 1991 World Bank social economics indicators, to show how multi-dimensional data sets can be reduced to two-dimensional (feature) maps, manifesting clusters of similar data items.