poster session (2)
Wednesday, 2007-09-05 - from 15:00 to 16:00
Cluster Analysis using Spherical SOM
|Presenting Author: Prof. H. Tokutaka|
|Authors: Heizo Tokutaka, Kikuo Fujimura, Masaaki Ohkita|
A cluster analysis method is proposed in this paper. As benchmark data, the Fisher's iris and the Wine recognition data sets are used. As a result of the numerical experiment, a clustering method using the dendrogram yielded 97 % in accuracy. It is difficult to display a multi-dimensional data by the dendrogram in one dimension. The ultimate visualization is by means of 3 dimensional rendition. We conclude that the best way that a multi-dimensional data set is visualized is by a sphere, since the phase relationship of it is smooth everywhere.
Failure detection and separation in SOM based decision support
|Presenting Author: Golan Lampi|
|Authors: Miki Sirola, Golan Lampi, Jukka Parviainen|
Failure management in process industry has difficult tasks. Decision support in control rooms of nuclear power plants is needed. A prototype that uses Self-Organizing Map (SOM) method is under development in an industrial project. This paper has focus on failure detection and separation. A literature survey outlines the state-of-the-art and reflects our study to related works. Different SOM visualizations are used. Failure management scenarios are carried out to experiment the methodology and the Man-Machine Interface (MMI). U-matrix trajectory analysis and quantization error are discussed more in detail. The experiments show the usefulness of the chosen approach. Next step will be to add more practical views by analyzing real and simulated industrial data with the control room tool and by feedback from the end users.
Self-Organizing Map with False Neighbor Degree between Neurons for Effective Self-Organization
|Presenting Author: Haruna Matsushita|
|Authors: Haruna Matsushita and Yoshifumi Nishio|
In the real world, it is not always true that the nextdoor house is close to my house, in other words, "neighbors" are not always "true neighbors".
In this study, we propose a new Self-Organizing Map (SOM) algorithm,
SOM with False Neighbor degree between neurons (called FN-SOM).
The behavior of FN-SOM is investigated with learning for various input data.
We confirm that FN-SOM can obtain the more effective map reflecting the distribution state of input data
than the conventional SOM and Growing Grid.
A news-based financial time series discretization
|Presenting Author: Danilo Di Stefano|
|Authors: Danilo Di Stefano, Valentino Pediroda|
In this paper a new method for financial time series discretization
that allows to take into account qualitative features about
financial indicators is proposed. Qualitative features are extracted
from financial news web sites and they are inserted into the
learning phase of a recursive Self Organizing Map by means of a
suitable parameter derived from statistical analysis of document
collections. A postprocessing phase based on unsupervised clustering
by U-Matrix method leads to the actual discretization of the time
series. A real case application to a stock closing price series
reveals that the inclusion of qualitative features leads to a more
compact discretization of the series. This could be useful if a
compact coding of the series is sought, for example in the
preprocessing phase of a forecasting methodology.
In the quest of specific-domain ontology components for the semantic
|Presenting Author: Rafael
|Authors: J.R.G. Pulido, S.B.F. Flores, P.D. Reyes, R.A. Diaz, J.J.C. Castillo|
This paper describes an approach we have been using to
identify specific-domain ontology components by using Self-Organizing Maps.
These components are clustered together in a natural way according to
their similarity. The knowledge maps, as we call them, show colored
regions containing knowledge components that may be used to populate
an specific-domain ontology.
Later, these ontology may be used by software agents to carry out
basic reasoning task on our behalf.
In particular, we deal with the issue of not constructing the ontology from
scratch, our approach helps us to speed up the ontology creation process.
The activation frequency self-organizing map (AFSOM)
|Presenting Author: Antonio Neme|
|Authors: Antonio Neme, Pedro Miramontes|
In the self-organizing map (SOM), the best matching units (BMUs) affect neurons as a function of distance
and the learning parameter.
Here we study the effects in SOM when a new parameter in the learning rule, the activation frequency, is
This parameter is based on the relative frequency by which each neuron is included in each
so there is an individual memory (synapse strength) of the activation received from each neuron.
The parameter leads to non-radial influence areas for BMUs, what is
a more realistic feature observed in the brain cortex which modifies the map formation dynamics,
the fact that the weight vector for BMU may not be the closest one to the input stimulus
after weight adaptation.
Also, two error measures are lower for the maps trained with this model
than those obtained with SOM, as shown in several experiments with six data sets.
Detection of ambiguous patterns in a SOM based recognition system: application to handwritten numeral classification
|Presenting Author: Leticia Maria Seijas|
|Authors: Leticia Maria Seijas, Enrique Carlos Segura|
This work presents a system for pattern recognition that combines a self-organising unsupervised technique (via a Kohonen-type SOM) with a bayesian strategy in order to classify input patterns from a given probability distribution and, at the same time, detect ambiguous cases and explain answers. We apply the system to the recognition of handwritten digits. This proposal is intended as an improvement of a model previously introduced by our group, consisting basically of a hybrid unsupervised, self-organising model, followed by a supervised stage. Experiments were carried out on the handwritten digit database of the Concordia University, which is generally accepted as one of the standards in most of the literature in the field.
Speaker Identification by BYY Automatic Local Factor Analysis based Three-Level Voting Combination
|Presenting Author: Lei Shi|
|Authors: Lei Shi, Dingsheng Luo, Lei Xu|
Local Factor Analysis (LFA) is known as more general and powerful than Gaussian Mixture Model (GMM) in unsupervised learning with local subspace structure analysis. In the literature of text-independent speaker identification, GMM has been widely used and investigated, with some preprocessing or postprocessing approaches, while there still lacks efforts on LFA for this task. In pursuit of fast implementation for LFA modeling, this paper focuses on the Bayesian Ying-Yang automatic learning with data smoothing based regularization (BYY-A), which makes automatic model selection during parameter learning. Furthermore for sequence classification, based on trained LFA models, we design and analyze a three-level combination, namely sequence, classifier and committee, respectively. Different combination approaches are designed with variant sequential topologies and voting schemes. Experimental results on the KING speech corpus demonstrate the proposed approaches' effectiveness and potentials.
Task Segmentation in a Mobile Robot by mnSOM and Hierarchical Clustering
|Presenting Author: Muhammad Aziz Muslim|
|Authors: Muhammad Aziz Muslim, Masumi Ishikawa, Tetsuo Furukawa|
Our previous studies assigned labels to mnSOM modules based on the assumption that winner modules corresponding to subsequences in the same class share the same label. We propose segmentation using hierarchical clustering based on the resulting mnSOM. Since it does not need the above unrealistic assumption, it gains practical importance at the sacrifice of the deterioration of the segmentation performance by 1.2%. We compare the performance of task segmentation for two kinds of module architecture in mnSOM. The result is that module architecture with sensory-motor signals as target outputs has superior performance to that with only sensory signals as target outputs.