Nugroho, Hanung Adi and Frannita, Eka Legya (2021) Impact of Implementing Data Balancing Method in Intelligent Thyroid Cancer Detection. In: International Conference on Computer System, Information Technology, and Electrical Engineering, COSITE 2021.
Impact_of_Implementing_Data_Balancing_Method_in_Intelligent_Thyroid_Cancer_Detection.pdf
Restricted to Registered users only
Download (309kB) | Request a copy
Abstract
Recently, artificial intelligence became an alternative powerful solution in medical cases that assist the medical personnel to be a second opinion in making diagnosis decisions. In thyroid cancer cases, the development of an intelligent system offered valuable benefits since thyroid examination procedures highly depended on the medical personnel skills and experiences. However, the number of training data still became a challenge in the development of the intelligent system. In this study, we developed an intelligent classification method for thyroid cancer completed with a data balancing method. Our proposed solution aimed to maintain the model performance in a small dataset. Our proposed solution successfully increased the classification performance with an average increasing performance of more than 60. While, the highest accuracy was 87.20. This experimental result indicated that implementing data balancing method can significantly increase the classification performance. © 2021 IEEE.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Cited by: 0 |
Uncontrolled Keywords: | Balancing; Classification (of information); Deep learning; Diagnosis; Diseases; Intelligent systems; Cancer detection; Classification performance; Deep learning; Diagnosis decision; Images classification; Medical case; Medical personnel; Second opinions; Thyroid cancers; Unbalanced datasets; Image classification |
Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
Divisions: | Faculty of Engineering > Electronics Engineering Department |
Depositing User: | Sri JUNANDI |
Date Deposited: | 24 Oct 2024 07:24 |
Last Modified: | 24 Oct 2024 07:24 |
URI: | https://ir.lib.ugm.ac.id/id/eprint/8626 |