Name
Title | ||
|---|---|---|
A comparative study on using unsupervised learning based data analysis techniques for breast cancer detection |
Abstract | ||
|---|---|---|
As stated by the World Health Organisation, breast cancer is the most frequent form of cancer among women, being responsible for 15% of all cancer-related deaths in this group. A lot of research has been carried out, so far, in using various machine learning models for breast cancer prediction, ranging from conventional classifiers to deep learning techniques. Three unsupervised learning models (t-Distributed Stochastic Neighbor Embedding, autoencoders and self-organizing maps) are comparatively analysed in this paper with the aim of unsupervisedly detecting the classes of benign and malignant instances. Experiments performed on data sets previously used in the literature for breast cancer detection reveal a good performance of the proposed unsupervised learning models. The best performance was obtained using autoencoders, which provided values higher than 0.935 for the area under the ROC curve evaluation measure. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/SACI49304.2020.9118783 | 2020 IEEE 14th International Symposium on Applied Computational Intelligence and Informatics (SACI) |
Keywords | DocType | ISBN |
Unsupervised learning,breast cancer detection,t-SNE,autoencoders,self-organizing maps | Conference | 978-1-7281-7378-8 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stefan Nitica | 1 | 0 | 0.34 |
| Gabriela Czibula | 2 | 80 | 19.53 |
| Vlad-Ioan Tomescu | 3 | 0 | 0.34 |