Nearest-neighbor classification for facies delineation
โ Scribed by Tartakovsky, Daniel M.; Wohlberg, Brendt; Guadagnini, Alberto
- Book ID
- 119674723
- Publisher
- American Geophysical Union
- Year
- 2007
- Tongue
- English
- Weight
- 204 KB
- Volume
- 43
- Category
- Article
- ISSN
- 0043-1397
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
A novel neuralnet-based method of constructing optimized prototypes for nearest-neighbor classiรฟers is proposed. Based on an e ective classiรฟcation oriented error function containing class classiรฟcation and class separation components, the corresponding prototype and feature weight update rules are
k-nearest neighbor (k-NN) classiรฟcation is a well-known decision rule that is widely used in pattern classiรฟcation. However, the traditional implementation of this method is computationally expensive. In this paper we develop two e ective techniques, namely, template condensing and preprocessing, to