Name
Abstract | ||
|---|---|---|
Proteomic analysis is a rapidly developing research field that has recently been used in the diagnosis and treatment of various diseases by analyzing the structure and functions of protein patterns in the cell. Numerous computer based decision support mechanisms implemented in this context have mostly used special image processing techniques until now. Recently, high performance self-learning deep learning methods have taken place in the classification studies over the conventional methods examining the structural features of the patterns, shapes and the texture properties in the images. In this study, different. intracellular patterns of HeLa cells taken by the microscope used in the testing of pattern analysis and the output is compared by classifying these patterns by using both deep learning methods and bag-of-features method. As a result of the experiments, it is seen that the success of the proposed deep learning model has a very high performance in classifying compared to the existing models and bag-of-features technique. |
Year | Venue | Keywords |
|---|---|---|
2017 | Signal Processing and Communications Applications Conference | deep learning,convolutional deep neural networks,protein,genome,proteomic analysis,classification |
Field | DocType | ISSN |
Pattern recognition,Computer science,Pattern analysis,Decision support system,Image processing,Artificial intelligence,Deep learning,Artificial neural network,Machine learning | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Aysun Sezer | 1 | 5 | 3.51 |
| Ugur Cekmez | 2 | 6 | 2.36 |