Divination of Down''s syndrome using Symbolic Regression
碩士 === 樹德科技大學 === 資訊管理研究所 === 92 === ABSTRACT Down syndrome is one of the most common genetic birth defects, affecting approximately one in 800 to 1,000 babies. To predict the possibility of such birth defect, tests on blood of pregnant women and comparison on statistical model are perfor...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2004
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/25956761269508998798 |
| Summary: | 碩士 === 樹德科技大學 === 資訊管理研究所 === 92 === ABSTRACT
Down syndrome is one of the most common genetic birth defects, affecting approximately one in 800 to 1,000 babies. To predict the possibility of such birth defect, tests on blood of pregnant women and comparison on statistical model are performed. This research tries to build models that connect the possibility of Down syndrome with the indicators such as HCG and AFP from experiments. The technique of symbolic regression is employed in this thesis. The model found in by symbolic regression for predicting the possiblility of Down syndrome is of 82% correctness. We present in this these how and why the problem of detecting Down syndrome can be viewed as symbolic regression. The transformation of data and related parameters are discussed. Finally, several experiments are performed and presented.
|
|---|