Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 2.111

An overview of the use of neural networks for data mining tasks

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

In the recent years, the area of data mining has been experiencing considerable demand for technologies that extract knowledge from large and complex data sources. There has been substantial commercial interest as well as active research in the area that aim to develop new and improved approaches for extracting information, relationships, and patterns from large datasets. Artificial neural networks (NNs) are popular biologically‐inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas, including science, engineering, medicine, business, banking, telecommunication, and many other fields. This paper highlights from a data mining perspective the implementation of NN, using supervised and unsupervised learning, for pattern recognition, classification, prediction, and cluster analysis, and focuses the discussion on their usage in bioinformatics and financial data analysis tasks. © 2012 Wiley Periodicals, Inc.

Figure 1.

The knowledge discovery process, comprising four important steps: data integration and cleaning; data selection and transformation; data mining; and evaluation and interpretation.

[ Normal View | Magnified View ]
Figure 2.

An artificial neuron (a perceptron) with adjustable weights; it consists of a set of links, a summation function, and a transfer function.

[ Normal View | Magnified View ]
Figure 3.

An NN organized in interconnected neurons. The weighted input is squashed through a transfer function and the output from one layer is the input for the next one, and so on, until the NN output is produced (NN with only one hidden layer is shown).

[ Normal View | Magnified View ]
Figure 4.

The Data Mining Step of the KDD process using Neural Networks, comprises four important sub‐steps: Prepare data for the NN; Learn the NN; Extract rules from the trained NN and Asses the extracted rules.

[ Normal View | Magnified View ]
Figure 5.

Training and testing of a classifier/predictor. First, the classifier is generated from training data; then the classifier is either applied to new unlabeled data or refined by testing it on labeled test data.

[ Normal View | Magnified View ]
Figure 6.

The top half of this figure shows a rule‐based classifier in the form of a decision tree. The bottom half shows some of the rules, encoded in the tree, in the form of IF–THEN rules.

[ Normal View | Magnified View ]
Figure 7.

Cluster analysis portrayed as a four‐step process comprising the extraction and selection of features; application of the clustering technique; validation of the derived clusters; and the interpretation of the clusters.

[ Normal View | Magnified View ]
Figure 8.

Self‐organizing map with two inputs and 49 outputs. Each output unit will represent one cluster (class) of inputs and is associated with a weight vector, size of which is the same as the input vector size.

[ Normal View | Magnified View ]

Browse by Topic

Technologies > Classification
Technologies > Computational Intelligence
Technologies > Prediction
Technologies > Structure Discovery and Clustering

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts