@InBook{himberg2001prscp, editor = {Nikhil R.~Pal}, title = {Pattern Recognition in Soft Computing Paradigm}, chapter = {The Self-Organizing Map as a Tool in Knowledge Engineering}, publisher = {World Scientific Publishing}, year = 2001, series = {Soft Computing}, pages = {38--65} }
@Article{vesanto2000tnn, author = {Juha Vesanto and Esa Alhoniemi}, title = {Clustering of the Self-Organizing Map}, journal = {IEEE Transactions on Neural Networks}, publisher = {IEEE}, year = {2000}, volume = {11}, number = {3}, month = {May}, pages = {586--600}, note = {}, annote = {} }
@Article{vesanto99ida, author = {Juha Vesanto}, title = {SOM-Based Data Visualization Methods}, journal = {Intelligent Data Analysis}, publisher = {Elsevier Science}, year = {1999}, volume = {3}, number = {2}, month = {}, pages = {111--126}, note = {}, annote = {} }
@Article{vesanto99sne, author = {Juha Vesanto and Esa Alhoniemi and Johan Himberg and Kimmo Kiviluoto and Jukka Parviainen}, title = {Self-Organizing Map for Data Mining in MATLAB: the SOM Toolbox}, journal = {Simulation News Europe}, publisher = {ARGE Simulation News}, year = {1999}, volume = {}, number = {25}, month = {March}, pages = {54}, note = {}, annote = {} }
@InBook{simula99nftt, author = {Olli Simula and Juha Vesanto and Esa Alhoniemi and Jaakko {Hollm\'en}}, title = {Neuro-Fuzzy Techniques for Intelligent Information Systems}, chapter = {Analysis and Modeling of Complex Systems Using the Self-Organizing Map}, publisher = {Physica Verlag (Springer Verlag)}, editor = {N.~Kasabov and R.~Kozma}, year = {1999}, pages = {3--22}, note = {}, isbn = {3-7908-1187-4}, annote = {} }
@Article{alhoniemi98icae, author = {Esa Alhoniemi and Jaakko {Hollm\'en} and Olli Simula and Juha Vesanto}, title = {Process Monitoring and Modeling using the Self-Organizing Map}, journal = {Integrated Computer Aided Engineering}, publisher = {John Wiley \& Sons}, year = {1999}, volume = {6}, number = {1}, month = {}, pages = {3--14}, note = {}, annote = {} }
@InBook{simula99iann, author = {Olli Simula and Petri Vasara and Juha Vesanto and Riina-Riitta Helminen}, chapter = {The Self-Organizing Map in Industry Analysis}, title = {Industrial Applications of Neural Networks}, editor = {L.C.~Jain and V.R.~Vemuri}, publisher = {CRC Press}, year = {1999}, pages = {87--112}, annote = {} }
@InProceedings{vesanto2001his, author = {Juha Vesanto and Jaakko Hollm{\'e}n}, title = {An Automated Report Generation Tool for the Data Understanding Phase}, booktitle = {Hybrid Intelligent Systems}, publisher = {Physica Verlag}, year = 2002, editor = {A.~Abraham and M.~Koeppen}, series = {Advances in Soft Computing}, address = {Heidelberg}, note = {In print.} }
@InProceedings{siponen2001wsom, author = {Markus Siponen, Juha Vesanto, Olli Simula, Petri Vasara}, title = {An Approach to Automated Interpretation of SOM}, booktitle = {Proceedings of Workshop on Self-Organizing Map 2001}, pages = {89--94}, year = 2001, editor = {Nigel Allinson, Hujun Yin, Lesley Allinson, Jon Slack}, month = {June}, publisher = {Springer} }
@InProceedings{vesanto2001pakdd, author = {Juha Vesanto}, title = {Importance of Individual Variables in the k-Means Algorithm}, booktitle = {Proceedings of the Pacific-Asia Conference Advances in Knowledge Discovery and Data Mining (PAKDD2001)}, pages = {513--518}, year = 2001, editor = {David Cheung, Graham J.~Williams, Qing Li}, month = {April}, publisher = {Springer} }
@InProceedings{jhimberg2000ijcnn, author = {Johan Himberg}, title = {A SOM Based Cluster Visualization and Its Application for False Coloring}, booktitle = {Proceedings of International Joint Conference on Neural Networks (IJCNN2000)}, pages = {587--592}, volume = {3}, year = {2000} }
@InProceedings{vesanto2000toolmet, author = {Juha Vesanto}, title = {Neural Network Tool for Data Mining: SOM Toolbox}, booktitle = {Proceedings of Symposium on Tool Environments and Development Methods for Intelligent Systems (TOOLMET2000)}, pages = {184--196}, year = {2000}, publisher = {Oulun yliopistopaino}, address = {Oulu, Finland} }
@InProceedings{simula99iwann, author = {Olli Simula and Esa Alhoniemi}, title = {{SOM Based Analysis of Pulping Process Data}}, booktitle = {Proceedings of International Work-Conference on Artificial and Natural Neural Networks (IWANN '99)}, pages = {567--577}, year = {1999}, volume = {II}, publisher = {Springer}, annote = {} }
@InProceedings{vesanto99matlab, author = {Juha Vesanto and Johan Himberg and Esa Alhoniemi and Juha Parhankangas}, title = {Self-Organizing Map in Matlab: the SOM Toolbox}, booktitle = {Proceedings of the Matlab DSP Conference 1999}, address = {Espoo, Finland}, year = {1999}, month = {November}, pages = {35-40}, annote = {} }
@InProceedings{alhoniemi99cima, author = {Esa Alhoniemi and Johan Himberg and Juha Vesanto}, title = {{Probabilistic Measures for Responses of Self-Organizing Map Units}}, pages = {286--290}, year = {1999}, booktitle = {Proceeding of the International ICSC Congress on Computational Intelligence Methods and Applications (CIMA '99)}, editor = {H. Bothe and E. Oja and E. Massad and C. Haefke}, publisher = {ICSC Academic Press}, annote = {} }
@InProceedings{vesanto99cima, author = {Juha Vesanto and Jussi Ahola}, title = {{Hunting for Correlations in Data Using the Self-Organizing Map}}, pages = {279--285}, booktitle = {Proceeding of the International ICSC Congress on Computational Intelligence Methods and Applications (CIMA '99)}, year = {1999}, editor = {H. Bothe and E. Oja and E. Massad and C. Haefke}, publisher = {ICSC Academic Press}, annote = {} }
@InProceedings{himberg98ideal, author = {Johan Himberg}, title = {Enhancing the SOM based data visualization by linking different data projections}, booktitle = {Proceedings of the International Symposium on Intelligent Data Engineering and Learning (IDEAL'98)}, address = {Hong Kong}, year = {1998}, month = {October}, pages = {427--434}, annote = {} }
@InProceedings{vesanto98iizuka, author = {Juha Vesanto and Johan Himberg and Markus Siponen and Olli Simula}, title = {Enhancing SOM based data visualization}, booktitle = {Proceedings of the International Conference on Soft Computing and Information/Intelligent Systems (IIZUKA'98)}, address = {Iizuka, Japan}, month = {October}, year = {1998}, pages = {64--67}, annote = {} }
@InProceedings{simula98kes, author = {Olli Simula and Juha Vesanto and Petri Vasara}, title = {Analysis of Industrial Systems Using the Self-Organizing Map}, booktitle = {Proceedings of the Internationa Conference on Knowledge-based Intelligent Systems (KES'98)}, address = {Adelaide, Australia}, year = {1998}, month = {April}, volume = {1}, pages = {61--68}, annote = {} }
@InProceedings{vesanto97snn, author = {Juha Vesanto and Petri Vasara and Riina-Riitta Helminen and Olli Simula}, title = {Integrating environmental, technologigal and financial data in forest industry analysis}, booktitle = {Proceedings of Stichting Neurale Netwerken Conference (SNN'97)}, address = {Amsterdam, Netherlands}, year = {1997}, month = {May}, pages = {153--156}, annote = {} }
@InProceedings{simula97iconip, author = {Olli Simula and Esa Alhoniemi and Jaakko {Hollm\'en} and Juha Vesanto}, title = {Analysis of Complex Systems Using the Self-Organizing Map}, booktitle = {Proceedings of the International Conference on Neural Information Processing and Intelligent Information Systems (ICONIP'97)}, year = {1997}, pages = {1313--1317}, annote = {} }
@InProceedings{vesanto97wsom, author = {Juha Vesanto}, title = {Using the SOM and Local Models in Time-Series Prediction}, booktitle = {Proceedings of Workshop on Self-Organizing Maps (WSOM'97)}, address = {Espoo, Finland}, year = {1997}, month = {June}, pages = {209--214}, annote = {} }
@InProceedings{Himberg97, author = {Johan Himberg and Olli Simula}, title = {Analyzing an Automatic Call Distribution System using the Self-Organizing Map}, pages = {153--157}, booktitle = {Proceedings of 1997 Finnish Signal Processing Symposium (FINSIG'97)}, address = {Pori, Finland}, year = {1997}, month = {May}, annote = {} }
InProceedings{Simula96, author = {Olli Simula and Esa Alhoniemi and Jaakko {Hollm\'en} and Juha Vesanto}, title = {Monitoring and modeling of complex processes using hierarchical self-organizing maps}, booktitle = {Proceedings of the {IEEE} International Symposium on Circuits and Systems (ISCAS'96)}, volume = {Supplement}, year = {1996}, month = {May}, pages = {73--76}, annote = {} }
@InProceedings{Hollmen96, author = {Jaakko {Hollm\'en} and Olli Simula}, title = {Prediction Models and Sensitivity Analysis of Industrial Production Process Parameters by Using the Self-Organizing Map}, booktitle = {Proceedings of {IEEE} Nordic Signal Processing Symposium (NORSIG'96)}, year = {1996}, pages = {79--82}, annote = {} }
@Unpublished{Vesanto97, author = {Juha Vesanto}, title = {The SOM in data mining: analysis of world pulp and paper technology}, note = {Presentation in SCIA'97.}, year = {1997}, annote = {} }
The Self-Organizing Map (SOM) is one of the most popular neural network models. The SOM quantizes the data space formed by the training data and simultaniously performs a topology-preserving projection of the data onto a regular low-dimensional grid. The grid can be used efficiently in visualization.
This thesis consists of an introduction and three publications. In the introduction, an overview of each step of the data mining process is first presented, primarily based on the CRoss-Industry Standard Process model for Data Mining (CRISP-DM). Then the SOM algorithm and some of its variants are introduced, and the use of SOM in data mining is discussed. The publications deal with modeling, visualization and clustering of data using the SOM. In addition, the introduction discusses the use of SOM in summarization.
The SOM is especially suitable for data understanding, but it is a robust tool suitable for modeling and preparation of data as well. It offers a convenient workbench which helps in gaining an initial understanding of the data at hand, and it can be used for creating some initial models as well.
Keywords: Self-Organizing Map, data mining, knowledge discovery in databases, visualization, clustering, summarization, data survey
@Booklet{vesanto2000licentiate, title = {Using SOM in Data Mining}, author = {Juha Vesanto}, howpublished = {Licentiate's thesis in the Helsinki University of Technology}, month = {April}, year = {2000}, annote = {} }
@Booklet{alhoniemi98licentiate, title = {Prosessin mittauksiin perustuva sulfaattisellun keiton analyysi}, author = {Esa Alhoniemi}, howpublished = {Licentiate's thesis in the Helsinki University of Technology}, month = {August}, year = {1998} annote = {} }
A hot rolled strip is a steel product. Measurements in the rolling mill, product ion line are recorded into databases. There are sometimes surface defects on the strip surface. These originate from casting, rolling, failed descaling or mechanical touch.
The connection between process parameters and surface defects was examined in the work. The aim was to find a model for controlling optimal set-up values in order to avoid surface defects, and calculate a warning of a possible defect. Self-organizing map (SOM) was used as a data mining tool.
The work is a result of NEUROLL project and carried out in the Laboratory of Computer and Information Science in Helsinki University of Technology. The project partner was Rautaruukki Steel in Raahe.
Keywords: data mining, hot rolled strip, surface quality, self-organizing map
@MastersThesis{parviainen00master, author = {Jukka K Parviainen}, title = {Data Mining for Finding Surface Defects in Steel Strips}, school = {Helsinki University of Technology}, year = {2000}, month = {September}, annote = {} }
@MastersThesis{stenberg98master, author = {Henry Stenberg}, title = {Itseorganisoiva kartta jatkuvatoimisen sinkityslinjan ohjauksessa}, school = {Helsinki University of Technology}, year = {1998}, month = {April}, annote = {} }
@MastersThesis{himberg97master, author = {Johan Himberg}, title = {Itseorganisoituvaan karttaan perustuva {ty\"okalu} ja sen soveltaminen puheludatan analyysiin}, school = {Helsinki University of Technology}, year = {1997}, month = {October}, annote = {} }
The Self-Organizing Map (SOM) is one of the most popular neural network models. The SOM quantizes the data space formed by the training data and simultaniously performs a topology-preserving projecting of the data space on a regular two-dimensional grid. The SOM also has excellent visualization capabilities including techniques to give an informative picture of the data space, and techniques to compare data vectors or whole data sets with each other. The SOM can also be used for clustering, classification and modeling. The versatile properties of the SOM make it a valuable tool in data mining and knowledge discovery.
As part of this work a SOM-based data mining tool was implemented. The methods and tools presented in the work were used to analyze the pulp and paper industry worldwide and the Scandinavian industry in more detail with encouraging results. The analysis of technological data resulted in 20 major types of pulp and paper mills. Regarding Scandinavian industry a hierarchical structure of SOMs was used to combine technological, environmental and economical data.
The work has been done in the Laboratory of Computer and Information Science at the Helsinki University of Technology as part of the corporate project Entire in the technology program "Adaptive and Intelligent Systems Applications". The project was financed by Jaakko Pöyry Consulting and the Technology Development center of Finland (TEKES).
@MastersThesis{vesanto97master, author = {Juha Vesanto}, title = {Data Mining Techniques Based on the Self-Organizing Map}, school = {Helsinki University of Technology}, year = {1997}, month = {May}, url = {http://www.cis.hut.fi/projects/monitor/publications/html/mastersJV97/}, annote = {} }
@MastersThesis{hollmen96master, author = {Jaakko {Hollm\'en}}, title = {Monitoring of Complex Processes Using the Self-Organizing Map}, school = {Helsinki University of Technology}, year = {1996}, month = {February}, annote = {} }
@MastersThesis{alhoniemi95master, author = {Esa Alhoniemi}, title = {Monitoring of Complex Processes Using the Self-Organizing Map}, school = {Helsinki University of Technology}, year = {1995}, month = {December}, annote = {} }