Multi-class K-support Vector Nearest Neighbor for Mango Leaf Classification

(ProQuest: ... denotes formulae omitted.) 1.Introduction The previous research in mango leaf classification used image texture as the feature with K-Nearest Neighbour (K-NN) and Artificial Neural Network (ANN) Back-propagation as the classification methods [1]. A data with the lowest SD value, which...

Full description

Saved in:
Bibliographic Details
Published in:Telkomnika 2018-08, Vol.16 (4), p.1826-1837
Main Authors: Prasetyo, Eko, Adityo, R. Dimas, Suciati, Nanik, Fatichah, Chastine
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Back propagation
Back propagation networks
Classification
Computer engineering
Data mining
Data reduction
Experiments
Feature extraction
Image classification
Mangoes
Methods
Morphology
Neural networks
Seminars
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:(ProQuest: ... denotes formulae omitted.) 1.Introduction The previous research in mango leaf classification used image texture as the feature with K-Nearest Neighbour (K-NN) and Artificial Neural Network (ANN) Back-propagation as the classification methods [1]. A data with the lowest SD value, which is equal to zero, is a data with no impact to decision boundary. [...]all data having SD or entropy equal to zero, can be removed from the list of training data. The performance comparation to SVM and Artificial Neural Network Error Back-Propagation (ANN-EBP) show the data reduction result used by K-NN is relatively higher accuracy compared to the others [11]. The time spent by K-SVNN is required to know the amount of time it should be provided during the reduction process because the data reduction process becomes an additional process in the classification stage. 4.Results and Discussion 4.1.Data Reduction Using Multi-class K-SVNN The author performs reduction rate testing by calculate the percentage of data released from the original training data.
ISSN:1693-6930
2302-9293
DOI:10.12928/telkomnika.v16i4.8482