In this paper, we used four classification methods to classify objects and compareamong these methods, these are K Nearest Neighbor's (KNN), Stochastic Gradient Descentlearning (SGD), Logistic Regression Algorithm(LR), and Multi-Layer Perceptron (MLP). Weused MCOCO dataset for classification and detection the objects, these dataset image wererandomly divided into training and testing datasets at a ratio of 7:3, respectively. In randomlyselect training and testing dataset images, converted the color images to the gray level, thenenhancement these gray images using the histogram equalization method, resize (20 x 20) fordataset image. Principal component analysis (PCA) was used for feature extraction, andfinally apply four classification methods, the results indicate that MLP was better than otherswith precision 81% , it took the maximum execution time for processing of the data-sets.
classification coco dataset using machine learning algorithms
learning Machine
classification
MCOCO dataset
K Nearest Neighbor's
Stochastic Gradient Descent learning (SGD)
Logistic Regression Algorithm(LR)
and Multi-Layer Perceptron (MLP).
Publication Date
Sun Jun 01 2014
Journal Name
Baghdad Science Journal
Preparation and Identification of some new Pyrazolopyrin derivatives and their Polymerizations study
Synthesis
Fused Pyrazoles
1-(3
6-dimethyl-4-oxo-1
4-dihydro-5H-pyrazolo [4
3-C] pyridin-5-yl)-1H-pyrrole-2
5-Dione S1
1-[2-(3
6-dimethyl-4-oxo-1-phenyl-1
4-dihydro-5H-pyrazolo[4
3-C]pyridin-5-yl)ethyl]-1H-pyrrole-2
5-DioneS2 and 1-(3
6-dimethyl-4-oxo-1-phenyl-1
4-dihydro-5H-pyrazolo[4
3-C]pyridin-5-yl)-1H-pyrrole-2
5-Dione S3
reactivity ratios
copolymer composition
Mean Sequence lengths.
Preparation and Identification of some new Pyrazolopyrin derivatives and their Polymerizations study
