2018 IEEE Second International Conference on Data Stream Mining &Amp; Processing (DSMP) 2018
DOI: 10.1109/dsmp.2018.8478537
|View full text |Cite
|
Sign up to set email alerts
|

Piecewise-Linear Approach to Classification Based on Geometrical Transformation Model for Imbalanced Dataset

Abstract: The article describes the method of cost-sensitive classification for imbalanced dataset based on neural-like structure of successive geometric transformations model using piecewise-linear approach to classification. The proposed method characterized by high learning speed and accuracy of classification.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0
1

Year Published

2019
2019
2022
2022

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 9 publications
0
3
0
1
Order By: Relevance
“…Cost-sensitive learning is a cost-specific technique that assigns different costs to the samples in different classes and can be applied to many existing algorithms to turn them into imbalance recovery methods. Doroshenko et al [63] proposed a cost-sensitive classification method for imbalanced data sets based on the neural structure of successive geometric transformation models using a piecewiselinear approach for classification. Khan et al [64] proposed a cost-sensitive neural network to handle imbalanced data.…”
Section: Approaches For Imbalanced Data Classificationmentioning
confidence: 99%
“…Cost-sensitive learning is a cost-specific technique that assigns different costs to the samples in different classes and can be applied to many existing algorithms to turn them into imbalance recovery methods. Doroshenko et al [63] proposed a cost-sensitive classification method for imbalanced data sets based on the neural structure of successive geometric transformation models using a piecewiselinear approach for classification. Khan et al [64] proposed a cost-sensitive neural network to handle imbalanced data.…”
Section: Approaches For Imbalanced Data Classificationmentioning
confidence: 99%
“…Розроблені алгоритми навчання, що базуються на методі зворотного поширення похибки, є достатньо повільними, а їх прискорені варіанти втрачають у точності навчання. Додатково до традиційних алгоритмів застосовують методи оптимізації на підставі генетичних алгоритмів, або алгоритмів імітації відпалу металу (Doroshenko, 2018). Враховуючи специфіку задач великих даних, застосування для них штучних нейронних мереж неефективне в сенсі надто великої складності навчання і налагодження.…”
Section: інформація про авторівunclassified
“…The lesion segmentation task aims to detect tumor location and boundaries, and the tumor classification task aims to identify tumor histological subtypes. In previous studies, many traditional machine learning methods were presented, such as the combination of a probabilistic neural network and support vector machines (PNN-SVM) [ 3 , 4 ], the Bayesian classifier [ 5 , 6 ] and the neural-like structure of successive geometric transformations model (SGTM) [ 7 , 8 , 9 , 10 ] for tumor classification and Gibbs random field [ 11 ], fuzzy C-means [ 12 ] and Wavelet Analysis [ 13 ] for segmentation. These methods highly rely on hand-crafted feature engineering and are unable to learn deep representations from visual levels.…”
Section: Introduction and Literature Reviewmentioning
confidence: 99%