Abstract
Advancement of DNA microarray technology has made it possible to get a great deal of biological information by a single experiment. Clustering algorithm is to group genes and reveal their functions or analyze unknown genes, which is categorized into hard and fuzzy clustering. For analyzing DNA microarray, fuzzy clustering can be better since genes can have several genetic information. In this paper, we present the GG (Gath-Geva) algorithm, which is one fuzzy clustering method, for clustering gene expression data. The GG algorithm is an improved version of the fuzzy c-means and GK (Gustafson-Kessel) algorithms and is appropriate for clustering gene expression data that have high dimension and ambiguous distribution. We have clustered serum and yeast data by the GG algorithm and compared it with the fuzzy c-means and GK algorithms. Through these experiments, we confirm that the GG algorithm is better for clustering gene expression data than other two algorithms.
| Original language | English |
|---|---|
| Pages (from-to) | 967-968 |
| Number of pages | 2 |
| Journal | Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) |
| Volume | 3157 |
| DOIs | |
| Publication status | Published - 2004 |
| Event | 8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence - Auckland, New Zealand Duration: 2004 Aug 9 → 2004 Aug 13 |
All Science Journal Classification (ASJC) codes
- Theoretical Computer Science
- Computer Science(all)