DocumentCode
2714602
Title
Important numerical features for novel endoplasmic reticulum genes classification of protein localizations in micrographs
Author
Dan, Han-Wei ; Lin, Chung-Chih ; Tsai, Yuh-Show
Author_Institution
Dept. of Biomed. Eng., Chung Yuan Christian Univ., Jhongli, Taiwan
fYear
2011
fDate
3-5 Nov. 2011
Firstpage
178
Lastpage
181
Abstract
Localization of proteins ties closely with the protein functions-the disorder of protein delivering can cause misfunction of the protein and genetic diseases. The analysis of micrographs can help to understand the distribution of proteins in the cell. ER protein´s images analysis leads the researches to know that the same protein localization means the proteins have same function, and to understand the phylogenetic relationship by image´s morphologies. This research uses SDA to find the best combination of features from original, skeletonized and brighter area images, which then utilized in SVM classification. The accuracy of this system can achieve 74% for the images acquired by the same hardware equipment.
Keywords
biomedical optical imaging; cellular biophysics; diseases; feature extraction; genetics; image classification; medical image processing; molecular biophysics; support vector machines; SDA; SVM classification; brighter area images; endoplasmic reticulum gene classification; feature extraction; genetic diseases; micrographs; phylogenetic relationship; protein delivery disorder; protein distribution; protein function; protein localization; skeletonized images; Accuracy; Educational institutions; Erbium; Feature extraction; Protein engineering; Proteins; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Bioelectronics and Bioinformatics (ISBB), 2011 International Symposium on
Conference_Location
Suzhou
Print_ISBN
978-1-4577-0076-7
Type
conf
DOI
10.1109/ISBB.2011.6107675
Filename
6107675
Link To Document