Self-Organizing-Feature-Maps versus Statistical Clustering Methods: A Benchmark
نویسندگان
چکیده
In this paper we oppose some classical statistical clustering methods to a connectionist approach in the field of exploratory data analysis. Using an Artificial Neural network, namely Kohonen's Self-Organizing Feature Maps (SOFM), together with the Unified distance matrix or short U-matrix method we describe a new access to the domain of clustering algorithms. We investigate the clustering capabilities of the different methods by choosing a sophisticated, the chainlink example and show how SOFM are superior to the described classical approaches.
منابع مشابه
Steel Consumption Forecasting Using Nonlinear Pattern Recognition Model Based on Self-Organizing Maps
Steel consumption is a critical factor affecting pricing decisions and a key element to achieve sustainable industrial development. Forecasting future trends of steel consumption based on analysis of nonlinear patterns using artificial intelligence (AI) techniques is the main purpose of this paper. Because there are several features affecting target variable which make the analysis of relations...
متن کاملSelf Organizing Neural Networks perform different from statistical k-means clustering
If Self Organizing Feature Maps (SOFMs) are enhanced by specially designed visualization algorithms like U-Matrix methods, they can be used for clustering. A common belief is, that the clustering abilities of this type of Artificial Neural Networks is identical or at least similar to the k-means algorithm used in statistics. In this paper we show by means of an nonlinear separable dataset, that...
متن کاملAir Quality Modelling by Kohonen’s Self-organizing Feature Maps and LVQ Neural Networks
The paper presents a design of parameters for air quality modelling and the classification of districts into classes according to their pollution. Further, it presents a model design, data pre-processing, the designs of various structures of Kohonen’s Self-organizing Feature Maps (unsupervised methods), the clustering by K-means algorithm and the classification by Learning Vector Quantization n...
متن کاملHierarchical Clustering Analysis with SOM Networks
This work presents a neural network model for the clustering analysis of data based on Self Organizing Maps (SOM). The model evolves during the training stage towards a hierarchical structure according to the input requirements. The hierarchical structure symbolizes a specialization tool that provides refinements of the classification process. The structure behaves like a single map with differ...
متن کاملModelling Municipal Rating by Cluster Analysis and Neural Networks
The paper presents the design of the parameters for long-term municipal rating. Modelling of the rating is realized by means of unsupervised methods, because the rating classes are not known a priori. The model design based on statistical methods (neural networks) is represented by cluster analysis (self-organizing feature maps). Key-Words: Credit risk, rating, unsupervised learning, cluster an...
متن کامل