Efendy, Agung (2026) IDENTIFIKASI TINGKAT KEPADATAN TULANG MENGGUNAKAN METODE GAUSSIAN MIXTURE MODELS – EXPECTATION MAXIMIZATION (GMM-EM). Masters thesis, Institut Teknologi Nasional Malang.
![[img]](http://eprints.itn.ac.id/style/images/fileicons/text.png)
Abstract
The human body contains bones that support the body. These bones have a specific density level. This density is influenced by various factors, including age, gender, and lifestyle. Bone mineral density (BMD) is divided into three categories: normal bone, osteopenia, and osteoporosis. By utilizing X-ray images of bones, the authors attempted to design and create software that can detect bone density levels for use in the medical field. Therefore, the author intends to develop this research by applying the Gaussian Mixture Model (GMM) method. The GMM algorithm used in this study is a method for obtaining estimates that provide good results by maximizing the likelihood function. Expectation Maximization (EM) is a model-based clustering algorithm that uses probability calculations. After segmentation for diagnosis, classification is required, which the author classified into three types: Normal Bone, Osteopenia, and Osteoporosis. Classification using the Random Forest method produced a fairly high confidence value. In system testing, the classification system achieved a sensitivity of 64%, a specificity of 86.76%, an F1-score of 73.66%, and an accuracy of 75%. These results indicate that this research was successful.
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | Agung Efendy (24131003) |
| Uncontrolled Keywords: | Bones, BMD, X-ray, GMM, EM |
| Subjects: | Engineering > Electrical Engineering |
| Divisions: | Program Pasca Sarjana > Teknik Elektro S2 > Teknik Elektro S2 (Tesis) |
| Depositing User: | Agung Efendy |
| Date Deposited: | 13 Jul 2026 03:30 |
| Last Modified: | 13 Jul 2026 03:30 |
| URI: | http://eprints.itn.ac.id/id/eprint/16266 |
Actions (login required)
 |
View Item |
