Ensemble learning by means of a multi-objective optimization design approach for dealing with imbalanced data sets

2020 ◽  
Vol 147 ◽  
pp. 113232 ◽  
Author(s):  
Victor Henrique Alves Ribeiro ◽  
Gilberto Reynoso-Meza
2015 ◽  
Vol 34 ◽  
pp. 705-720 ◽  
Author(s):  
Julie Jacques ◽  
Julien Taillard ◽  
David Delerue ◽  
Clarisse Dhaenens ◽  
Laetitia Jourdan

2013 ◽  
Vol 756-759 ◽  
pp. 3652-3658
Author(s):  
You Li Lu ◽  
Jun Luo

Under the study of Kernel Methods, this paper put forward two improved algorithm which called R-SVM & I-SVDD in order to cope with the imbalanced data sets in closed systems. R-SVM used K-means algorithm clustering space samples while I-SVDD improved the performance of original SVDD by imbalanced sample training. Experiment of two sets of system call data set shows that these two algorithms are more effectively and R-SVM has a lower complexity.


2021 ◽  
Vol 13 (4) ◽  
pp. 1929
Author(s):  
Yongmao Xiao ◽  
Wei Yan ◽  
Ruping Wang ◽  
Zhigang Jiang ◽  
Ying Liu

The optimization of blank design is the key to the implementation of a green innovation strategy. The process of blank design determines more than 80% of resource consumption and environmental emissions during the blank processing. Unfortunately, the traditional blank design method based on function and quality is not suitable for today’s sustainable development concept. In order to solve this problem, a research method of blank design optimization based on a low-carbon and low-cost process route optimization is proposed. Aiming at the processing characteristics of complex box type blank parts, the concept of the workstep element is proposed to represent the characteristics of machining parts, a low-carbon and low-cost multi-objective optimization model is established, and relevant constraints are set up. In addition, an intelligent generation algorithm of a working step chain is proposed, and combined with a particle swarm optimization algorithm to solve the optimization model. Finally, the feasibility and practicability of the method are verified by taking the processing of the blank of an emulsion box as an example. The data comparison shows that the comprehensive performance of the low-carbon and low-cost multi-objective optimization is the best, which meets the requirements of low-carbon processing, low-cost, and sustainable production.


Sign in / Sign up

Export Citation Format

Share Document