Browsing by Subject "algorytm C4.5"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item type:Thesis, Access status: Restricted , Generalizacja algorytmu indukcji drzew decyzyjnych za pomocą pseudokodu(Data obrony: 2019-09-19) Kulig, Magdalena
Wydział Inżynierii Metali i Informatyki PrzemysłowejItem type:Article, Access status: Open Access , Metoda automatycznego wyznaczania indeksu mitotycznego populacji komórek cebuli z wykorzystaniem drzewa decyzyjnego(Wydawnictwa AGH, 2008) Gocławski, Jarosław; Sekulska-Nalewajko, Joanna; Anioł, PatrykThe evaluation of mitotic index is the method of estimation of cell division ability in cell populations treated by growth inhibitors or accelerators. The image processing algorithms for the segmentation of onion cells and their nuclei elements appearing in the process of mitosis is proposed. Then a set of geometrical, textural and topological features of nuclei elements was extracted, which can distinguish interphase from the stages of mitosis. A decision tree was built according to C4.5 method using the maximum of information gain ratio of the feature values. To evaluate classification error, a series of 10-fold crossvalidations were performed. The feature space was reduced by applying PCA method. The value of mitotic index for the tested onion cell population as well as the estimator index error was evaluated. The errors were compared with an average classification error.
