Klasifikasi Sel Darah Putih Menggunakan Metode Support Vector Machine (SVM) Berbasis Pengolahan Citra Digital
| Autor: | Bakhtiar Alldino Ardi Sumbodo, Ika Candradewi, Bhima Caraka |
|---|---|
| Jazyk: | indonéština |
| Rok vydání: | 2017 |
| Předmět: |
business.industry
Lymphoblast 05 social sciences Feature extraction lcsh:Electronics lcsh:Control engineering systems. Automatic machinery (General) lcsh:TK7800-8360 Image processing Pattern recognition 02 engineering and technology White blood cells Feature extraction Histogram oriented gradient Classification Support vector machine Linear Radial basis function Support vector machine lcsh:TJ212-225 020204 information systems Kernel (statistics) Histogram 0502 economics and business 0202 electrical engineering electronic engineering information engineering Artificial intelligence business 050203 business & management Mathematics |
| Zdroj: | IJEIS (Indonesian Journal of Electronics and Instrumentation Systems), Vol 7, Iss 1, Pp 25-36 (2017) IJEIS (Indonesian Journal of Electronics and Instrumentation Systems); Vol 7, No 1 (2017): April; 25-36 |
| ISSN: | 2460-7681 2088-3714 |
| Popis: | White blood cells are classified into five types (basophils, eosinophils, neutrophils, lymphocytes and monocytes) with additional classes lymphoblast cells from microscope images are processed. By applying image processing, image its white blood cells extracted using the Histogram Oriented Gradient. Feature extraction results obtained then classified using Support Vector Machine method by comparing the results of two different kernel parameters: kernel Linear and kernel Radial Basis Function (RBF). Classification evaluated with these parameters: Accuracy, specificity, and sensitivity. Obtained an accuracy of 72.26% from the detection of white blood cells in the microscope image. The average value of microscope images of patients and different kernel every white blood cells (monocytes, basophils, neutrophils, eosinophils, lymphocytes and lymphoblast) were evaluated with these parameters. Results of the study show the classification system has an average value of 82.20% accuracy (RBF Patient 1), 81.63% (RBF Patient 2) and 78.73% (Linear Patient 1), 79.55% (Linear Patient 2 ), then the value of specificity of 89.91% (RBF patient 1), 92.18% (RBF patient 2) and 88.06% (Linear patient 1), 91.34% (Linear patient 2), and sensitivity values 15 , 45% (RBF patient 1), 12.97% (RBF patient 2) and 13.33% (Linear patient 1), 12.50% (Linear patient 2). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|