APPLICATION OF NUMERICAL INTELLIGENCE METHODS FOR THE AUTOMATIC QUALITY GRADING OF AN EMBRYO DEVELOPMENT
Autor: | Domas Jonaitis, Vidas Raudonis, Arunas Lipnickas |
---|---|
Rok vydání: | 2016 |
Předmět: |
0301 basic medicine
Computer Networks and Communications Computer science 0206 medical engineering Feature extraction 02 engineering and technology computer.software_genre 03 medical and health sciences Computer Science (miscellaneous) Artificial neural network business.industry Pattern recognition Video sequence 020601 biomedical engineering Support vector machine ComputingMethodologies_PATTERNRECOGNITION 030104 developmental biology Hardware and Architecture Video tracking Principal component analysis Classification methods Data mining Artificial intelligence business computer Software Information Systems |
Zdroj: | International Journal of Computing. :177-183 |
ISSN: | 2312-5381 1727-6209 |
DOI: | 10.47839/ijc.15.3.850 |
Popis: | In vitro fertilization – a procedure which aims to get the embryo to adapt the methods of "oocyte" fertilized sperm outside the human body. At the end of this procedure there are several embryos. This paper represents overview of tracking-free and tracking-based methods for detection of important embryo development stages. Tracking-based method represents well known classical object tracking techniques. For tracking-free method were selected statistical feature extraction techniques and classification methods: Classification with training and classification without training. For the feature extraction proposed statistical methods: entropy, invariant moments and principal components analyses. For the classification are used neural networks, support vector machine and K-nearest neighbor method. Data collected consist of 500 images for each class. 70 percent of images are dedicated for training, and 30 percent for testing. The proposed method is checked by experiment. It is expected that this method will work well in video sequences. |
Databáze: | OpenAIRE |
Externí odkaz: |