Self-Organizing Map with Input Data Represented as Graph

2006 ◽  
pp. 907-914 ◽  
Author(s):  
Takeshi Yamakawa ◽  
Keiichi Horio ◽  
Masaharu Hoshino
Keyword(s):  
Input Data ◽  
Self Organizing Map ◽  
As Graph ◽  
Self Organizing

Using an Extended Self-Organizing Map Network to Forecast Market Segment Membership

2011 ◽  
pp. 142-157
Author(s):  
Melody Y. Kiang ◽  
Dorothy M. Fisher ◽  
Michael Y. Hu ◽  
Robert T. Chi
Keyword(s):  
Input Data ◽  
Self Organizing Map ◽  
Market Segment ◽  
Extended Version ◽  
Extended Self ◽  
Data Set ◽  
Step Procedure ◽  
Som Network ◽  
Residential Market ◽  
Self Organizing

This chapter presents an extended Self-Organizing Map (SOM) network and demonstrates how it can be used to forecast market segment membership. The Kohonen’s SOM network is an unsupervised learning neural network that maps n-dimensional input data to a lower dimensional (usually one- or two-dimensional) output map while maintaining the original topological relations. We apply an extended version of SOM networks that further groups the nodes on the output map into a user-specified number of clusters to a residential market data set from AT&T. Specifically, the extended SOM is used to group survey respondents using their attitudes towards modes of communication. We then compare the extended SOM network solutions with a two-step procedure that uses the factor scores from factor analysis as inputs to K-means cluster analysis. Results using AT&T data indicate that the extended SOM network performs better than the two-step procedure.

scholarly journals Pengelompokan Berita Indonesia Berdasarkan Histogram Kata Menggunakan Self-Organizing Map

2014 ◽  
Vol 8 (1) ◽  
pp. 101
Author(s):  
Ambarwati Ambarwati ◽  
Edi Winarko
Keyword(s):  
Feature Extraction ◽  
Data Processing ◽  
System Application ◽  
Input Data ◽  
Information Resources ◽  
The Self ◽  
News Article ◽  
Self Organizing Map ◽  
Map Algorithm ◽  
Self Organizing

AbstrakBerita merupakan sumber informasi yang dinantikan oleh manusia setiap harinya. Manusia membaca berita dengan kategori yang diinginkan. Jika komputer mampu mengelompokkan berita secara otomatis maka tentunya manusia akan lebih mudah membaca berita sesuai dengan kategori yang diinginkan. Pengelompokan berita yang berupa artikel secara otomatis sangatlah menarik karena mengorganisir artikel berita secara manual membutuhkan waktu dan biaya yang tidak sedikit.Tujuan penelitian ini adalah membuat sistem aplikasi untuk pengelompokkan artikel berita dengan menggunakan algoritma Self Organizing Map. Artikel berita digunakan sebagai input data. Kemudian sistem melakukan pemrosesan data untuk dikelompokkan. Proses yang dilakukan sistem meliputi preprocessing, feature extraction, clustering dan visualize.Sistem yang dikembangkan mampu menampilkan hasil clustering dengan algoritma Self Organizing Map dan memberikan visualisasi dengan smoothed data histograms berupa island map dari artikel berita. Selain itu sistem dapat menampilkan koleksi dokumen dari lima kategori berita yang ada pada tiap tahunnya dan banyaknya kata (histogram kata) yang sering muncul pada tiap arikel berita. Pengujian dari sistem ini dengan memasukan artikel berita, kemudian sistem memprosesnya dan mampu memberikan hasil cluster dari artikel berita yang dimasukan. Kata kunci—Pengelompokkan berita Indonesia, pengelompokkan berdasar histogram kata, pengelompokan berita menggunakan SOM  Abstract News is awaited information resources by humans every day. Human reading the news with the desired category. If the computer able to news clustering with automatically, humans of course will be easier to read the news according to the desired category. News clustering in the form of news articles with automatically very interesting because it organizes news articles manually takes time and costs not a little bit.The purpose of this research is to create a system application for grouping news articles by using the Self Organizing Map algorithm. News article be used as input into the system. News articles used as input data. Then the system performs data processing until to be clustered. Processes performed by the system covers: preprocessing, feature extraction, clustering and visualize.The system developed is able to display the results clustering of the Self Organizing Map algorithm and gives visualization of the Smoothed Data Histograms in the form of island map from news articles. Additionally the system can display a word histogram and news articles from five categories news in each year. Testing of this system by entering the news articles, then the system performs data processing and gives results of a cluster from news articles that input. Keywords—Indonesia news clustering, clustering based on words histograms, news clustering using SOM

Growing Hierarchical Self-Organizing Map Using Category Utility

2016 ◽  
Vol 26 (02) ◽  
pp. 217-237
Author(s):  
Kazushi Murakoshi ◽  
Satoshi Fujikawa
Keyword(s):  
Knowledge Representation ◽  
Unsupervised Learning ◽  
Input Data ◽  
Computer Experiments ◽  
Quantization Error ◽  
Self Organizing Map ◽  
Conceptual Clustering ◽  
The Hierarchical Structure ◽  
Evaluation Measure ◽  
Self Organizing

In order to automatically obtain hierarchical knowledge representation from a certain data, an unsupervised learning method has been developed that overcomes two problems of the growing hierarchical self-organizing map (GHSOM) method, which uses the quantization error, the deviation of the input data, as evaluation measure of the growing maps: proper control of the growth process of each map is difficult due to the use of the quantization error and the clusters in the hierarchical structure may be excessively subdivided. This improved GHSOM method uses the category utility (CU), a measure used in conceptual clustering for predicting the preferred level of categorization, instead of the quantization error. The CU is useful for organizing the clustering so that people can effortlessly understand it. The basic principle of this method is that the growth and unification processes are appropriately and autonomously controlled by the CU. Evaluation using computer experiments showed that the proposed method can automatically construct an appropriate hierarchical and topological knowledge representation for high-dimensional input data through unsupervised learning. It also showed that it is easier to use and more effective than the original conventional GHSOM method using the quantization error as an evaluation measure.

scholarly journals A structural self-organizing map (S-SOM) algorithm for weather typing

2020 ◽  
Author(s):  
Quang-Van Doan ◽  
Hiroyuki Kusaka ◽  
Takuto Sato ◽  
Fei Chen
Keyword(s):  
Input Data ◽  
Structural Similarity ◽  
Superior Performance ◽  
Self Organizing Map ◽  
Weather Patterns ◽  
Weather Typing ◽  
Synoptic Weather Typing ◽  
Clustering Quality ◽  
Som Algorithm ◽  
Self Organizing

Abstract. In this study, we propose a novel structural self-organizing map (S-SOM) algorithm for synoptic weather typing. A novel feature of the S-SOM compared with traditional SOMs is its ability to deal with input data that have spatial or temporal structures. In detail, the search scheme for the best matching unit (BMU) in a S-SOM is built based upon a structural similarity (S-SIM) index rather than by using the traditional Euclidean distance (ED). S-SIM enables the BMU search to consider the correlation in space between weather states, such as the location of highs of lows, that is impossible when using ED. The S-SOM performance is evaluated by multiple demo simulations of clustering weather patterns over Japan using the ERA-Interim sea-level pressure data. The results show the superiority of the S-SOM compared with a standard SOM with ED (or ED-SOM) in two respects: clustering quality based on silhouette analysis and topological preservation based on topological error analysis. The superior performance of the S-SOM compared with an ED-SOM is probably independent of both the input data and SOM configuration.

Self-organizing map clustering technique for ANN-based spatiotemporal modeling of groundwater quality parameters

2015 ◽  
Vol 18 (2) ◽  
pp. 288-309 ◽  
Author(s):  
Vahid Nourani ◽  
Mohammad Taghi Alami ◽  
Farnaz Daneshvar Vousoughi
Keyword(s):  
Groundwater Quality ◽  
Input Data ◽  
Quality Parameters ◽  
Quality Data ◽  
Self Organizing Map ◽  
Feed Forward Neural Network ◽  
Clustering Technique ◽  
Proposed Model ◽  
Spatially Homogeneous ◽  
Self Organizing

The present study integrates co-kriging as spatial estimator and self-organizing map (SOM) as clustering technique to identify spatially homogeneous clusters of groundwater quality data and to choose the most effective input data for feed-forward neural network (FFNN) model to simulate electrical conductivity (EC) and total dissolved solids (TDS) of groundwater. The methodology is presented in three stages. In the first stage, a geostatistics approach of co-kriging is used to estimate groundwater quality parameters at locations where the groundwater levels are measured. In stage two, a SOM clustering technique is used to identify spatially homogeneous clusters of groundwater quality data. The dominant input data, selected by spatial clustering and mutual information are then imposed into the FFNN model for one-step-ahead predictions of groundwater quality parameters at stage three. The performance of the newly proposed model is compared to a conventional linear forecasting method of multiple linear regression (MLR). The results suggest that the proposed model decreases dimensionality of the input layer and consequently the complexity of the FFNN model with acceptable efficiency in spatiotemporal simulation of groundwater quality parameters. The application of FFNN for modeling EC and TDS parameters increases the accuracy of predictions respectively up to 84.5% and 17% on average with regard to the MLR model.

A Massively Parallel Implementation of a Modular Self-Organizing Map on FPGAs

2019 ◽  
Vol 28 (03) ◽  
pp. 1950054 ◽  
Author(s):  
Khaled Ben Khalifa ◽  
Mohamed Hédi Bedoui
Keyword(s):  
Neural Networks ◽  
Online Learning ◽  
Input Data ◽  
Parallel Implementation ◽  
Fpga Implementation ◽  
Massively Parallel ◽  
Self Organizing Map ◽  
Element Input ◽  
Working Frequency ◽  
Self Organizing

This paper describes the architecture design of novel massively parallel self-organizing map (SOM) neural networks. The proposed architecture, referred to as the planar SOM (PSOM), is described as a soft IP core synthesized in VHDL. The SOM neural network’s size and the input data vectors’ dimension are adjustable parameters. In this work, several SOM architectures are synthesized and their performance is evaluated for Xilinx Virtex-7 FPGAs. The presented hardware architecture allows online learning and can be easily adapted to a large variety of SOM topologies without a considerable design effort. A [Formula: see text] SOM hardware is validated through the FPGA implementation and its performances with an estimated working frequency of 297[Formula: see text]MHz for a 23-element input vector will reach 21,970 MCUPS in the learning phase and 35,902 MCPS in the recall one.

Sign in / Sign up

Export Citation Format

Share Document