Data augmentation importance for classification of skin lesions via deep learning
| dc.contributor.author | Ayan E. | |
| dc.contributor.author | Unver H.M. | |
| dc.date.accessioned | 2020-06-25T15:17:57Z | |
| dc.date.available | 2020-06-25T15:17:57Z | |
| dc.date.issued | 2018 | |
| dc.department | Kırıkkale Üniversitesi | |
| dc.description | 4th Electric Electronics, Computer Science, Biomedical Engineerings' Meeting, EBBT 2018 -- 18 April 2018 through 19 April 2018 -- -- 137380 | |
| dc.description.abstract | Melanoma is a fatal type of cancer which is mostly curable if detected in early stages. Various machine learning algorithms are used for distinguishing benign lesions from malignant such as deep learning. To obtain successful result from deep learning, large and quality training data set is essential. But, existing data sets maybe insufficient for training a deep learning network. Building a powerful classifier from insufficient data, data augmentation methods are useful. In this article the same network trained with augmented skin lesion images and non- augmented skin lesion images for detecting malignant skin lesions. When compered results, it has been seen that the network using augmented data for training has achieved better results than training with non-augmented data. © 2018 IEEE. | en_US |
| dc.identifier.doi | 10.1109/EBBT.2018.8391469 | |
| dc.identifier.endpage | 4 | en_US |
| dc.identifier.isbn | 9781538651353 | |
| dc.identifier.scopus | 2-s2.0-85050224605 | |
| dc.identifier.scopusquality | N/A | |
| dc.identifier.startpage | 1 | en_US |
| dc.identifier.uri | https://doi.org/10.1109/EBBT.2018.8391469 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12587/2578 | |
| dc.indekslendigikaynak | Scopus | |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
| dc.relation.ispartof | 2018 Electric Electronics, Computer Science, Biomedical Engineerings' Meeting, EBBT 2018 | |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/closedAccess | en_US |
| dc.subject | convolutional neural networks | en_US |
| dc.subject | data augmentation | en_US |
| dc.subject | deep learning | en_US |
| dc.subject | melanoma | en_US |
| dc.subject | skin lesions | en_US |
| dc.title | Data augmentation importance for classification of skin lesions via deep learning | en_US |
| dc.type | Conference Object |
