Name
Abstract | ||
|---|---|---|
Cancer prediction models provide an important approach to assess risk and prognosis by identifying individuals and enabling estimates of the population burden and cost of cancer. Models also may aid in the evaluation of treatments and interventions. A number of statistical and machine learning techniques have been employed to develop various cancer prediction models. Meanwhile, gene selection is very important for cancer classification. We need to deal with high-dimensional gene space and few samples. But the epistasis means that some genes maybe cover or affect other genes. Fuzzy measure can describe the interaction between genes very well. In this article, we proposed one new model based on fuzzy integral with respect to fuzzy measure for cancer prediction with sparse genes. We can obtain a group of combinations of genes with the highest fuzzy measure values. The new method is applied to two cancer data for testifying the performance. Experimental results show that the proposed model has the highest testing accuracy and F-score by comparing with several state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/BIBM.2018.8621186 | PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) |
Keywords | Field | DocType |
Cancer prediction, Gene selection, Fuzzy measure | Cancer classification,Population,Gene selection,Epistasis,Computer science,Fuzzy logic,Artificial intelligence,Predictive modelling,Cancer,Machine learning | Conference |
ISSN | Citations | PageRank |
2156-1125 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jinfeng Wang | 1 | 5 | 3.20 |
| Jiajie Chen | 2 | 0 | 1.35 |
| hui wang | 3 | 76 | 17.01 |