| Author | Tatpong Katanyukul |
| Call Number | AIT Thesis no. CS-00-09 |
| Subject(s) | Data mining
|
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. CS-00-09 |
| Abstract | Clustering is the important preliminary task for data mining. Its result is useful for data reduction and hypothesis extraction from data. The complication of data characteristics can degrade the clustering performance. Multivariate time-series data is one of the complications. In the study, a new method for graphical display was proposed for efficient representation. Three classical clustering algorithms and the self-organizing map with three ways of distance measurement were applied to cluster the multivariate time-series data set obtained from the UCI KDD Archive. The results were inspected by graphical views accompanied with the statistical figures. It was shown that the proposed method can display the results obtained from the four different clustering methods very well. It was found that the Euclidean distance performs very satisfactorily for the data set employed. |
| Year | 2000 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. CS-00-09 |
| Type | Thesis |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Huynh Ngoc Phien; |
| Examination Committee(s) | Phan Minh Dung;Hoang Le Tien; |
| Scholarship Donor(s) | Royal Thai Government; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2000 |
| Contributor(s) | Cluster set theory |