| Author | Achmad, Rozali |
| Call Number | AIT Thesis no. CA-83-2 |
| Subject(s) | Time-series analysis
|
| Note | A thesis submitted in partial fulfillment of the requirement for the degree of Master of Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | An empirical heuristic self-organization approach, referred to as the group method of data handling (GMDH) was investigated in this study. Three different algorithms-namely, the basic procedure developed by Ivankhnenko and two modified versions suggested by Ikeda and Sawaragi, were considered in regard to several problems, (b) input data, (c) data splitting scheme, (d) the quality criterion and (e) the stopping rule.
Two sets of data were used for investigating the effects of the selection corresponding to each of the aforementioned problems in the estimation of monthly streamflow for the Huai Sato and Ping River basins in Thailand. The appropriate selection was then applied to the estimation of the paddy production of two areas in The Mekong Delta (Vietnam) and satisfactory estimates were obtained.
Three general computer programs were developed according to the three different algorithms considered with due regard to the storage requirement, CPU time, and portability. Having been tested in many trials carried out in this study, they are readily workable in dealing with applications of the GMDH. |
| Year | 1983 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Application (CA) |
| Chairperson(s) | Huynh, Ngoc Phien |
| Examination Committee(s) | Sharif, M. Nawaz ; Omura, T.
|
| Scholarship Donor(s) | Carl Duisberg Gesellschaft, Federal Republic of Germany |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology 1983 |