Hybrid analysis for indicating patients with breast cancer using temperature time series
详细信息 查看全文
- 作者：Lincoln F. Silvaa ; lsilva@ic.uff.br" class="auth_mail" title="E-mail the corresponding author ; Alair Augusto S.M.D. Santosb ; Renato S. Bravoc ; Aristó ; fanes C. Silvad ; Dé ; bora C. Muchaluat-Saadea ; Aura Concia
- 关键词：Breast cancer ; Dynamic infrared thermography ; Temperature time series ; Machine learning ; Classification
- 刊名：Computer Methods and Programs in Biomedicine
- 出版年：2016
- 出版时间：July 2016
- 年：2016
- 卷：130
- 期：Complete
- 页码：142-153
- 全文大小：3541 K
文摘
- •
We have proposed a hybrid automatic method for identifying patients with breast cancer, supporting human experts.
- •
We have applied learning techniques supervised and unsupervised learning techniques.
- •
We have applied various validity indexes of clusters.
- •
In the evaluation of the proposed method, a data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem.
- •
Among the classification algorithms which have been applied, K-Star and Bayes Net has shown the best result, 100% accuracy.