wFDT-Weighted Fuzzy Decision Trees for Breast Cancer Survivability Analysis
wFDT-Weighted Fuzzy Decision Trees for Breast Cancer Survivability Analysis
- 발행기관 아주대학교
- 지도교수 김민구
- 발행년도 2009
- 학위수여년월 2009. 2
- 학위명 석사
- 학과 및 전공 정보통신전문대학원 정보통신공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000009854
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Accurate and less invasive personalized predictive medicine can spare many breast cancer patients from receiving complex surgical biopsies, unnecessary adjuvant treatments and its expensive medical cost. Cancer prognosis estimates recurrence of disease and predict survival of patient; hence resulting in improved patient management. To develop such knowledge based prognostic system, this thesis examines potential hybridization of accuracy and interpretability in the form of Fuzzy Logic and Decision Trees, respectively. Effect of rule weights on fuzzy decision trees is investigated to be an alternative to membership function modifications for performance optimization. Experiments were performed using different combinations of: number of decision tree rules, types of fuzzy membership functions and inference techniques for breast cancer survival analysis. SEER breast cancer data set (1973-2003), the most comprehensible source of information on cancer incidence in United States, is considered. Performance comparisons suggest that predictions of weighted fuzzy decision trees (wFDT) are more accurate and balanced, than independently applied crisp decision tree classifiers; moreover it has a potential to adapt for significant performance enhancement.
more목차
Contents
Acknowledgements ii
Abstract v
Contents vi
Chapter 1: Introduction 8
Chapter 2: Related Work 13
Chapter 3: Materials and Methods 15
3.1 Prognostic and Predictive Factors in Breast Cancer 15
3.2 Data 16
3.3 Decision Trees 19
3.3.1 C4.5 Limitations, Interpretability and Model Selection 20
3.4 Weighted Fuzzy Decision Trees (wFDT) 22
3.4.1 Fuzzy Inference 24
3.4.2 Fuzzy Membership Functions 24
3.4.3 Effect of Weights on Fuzzy Rules 26
Chapter 4: Performance Evaluation 29
4.1 Accuracy, Sensitivity and Specificity 29
4.2 10-Fold Cross Validation 29
Chapter 5: Conclusion and Future Work 34
References: 35
