A non-specialized ensemble classifier using multi-objective optimization

Fletcher, Sam; Verma, Brijesh; Zhang, Mengjie

doi:10.1016/j.neucom.2020.05.029

Cited by 11 publications

(8 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MEG is based on MOEAs, thus it iteratively evolves a population of ensembles across multiple generations and outputs the ensembles with the best trade-off between diversity of base classifiers and overall accuracy of predictions (Section 3.2 describes the objectives). MEG differs from related work [17,23,25,28,59] in many ways. While algorithms like DIVACE [17] work as a Pareto-ensemble technique (evolve base classifiers and aggregate the non-dominated ones), MEG takes a more direct and intuitive approach where each solution in the population is a whole ensemble.…”

Section: Meg: Multi-objective Ensemble Generationmentioning

confidence: 86%

“…While algorithms like DIVACE [17] work as a Pareto-ensemble technique (evolve base classifiers and aggregate the non-dominated ones), MEG takes a more direct and intuitive approach where each solution in the population is a whole ensemble. Other work use a more similar representation as the one adopted by MEG [23,25,28,59]. However, such approaches focus on selecting a set of predefined base classifiers, as opposed to designing, configuring, and building ensembles and the constituent parts.…”

Section: Meg: Multi-objective Ensemble Generationmentioning

confidence: 99%

See 1 more Smart Citation

MEG: Multi-objective Ensemble Generation for Software Defect Prediction

Moussa

Guizzo

Sarro

2022

Proceedings of the 16th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement

View full text Add to dashboard Cite

Background: Defect Prediction research aims at assisting software engineers in the early identification of software defect during the development process. A variety of automated approaches, ranging from traditional classification models to more sophisticated learning approaches, have been explored to this end. Among these, recent studies have proposed the use of ensemble prediction models (i.e., aggregation of multiple base classifiers) to build more robust defect prediction models. Aims: In this paper, we introduce a novel approach based on multi-objective evolutionary search to automatically generate defect prediction ensembles. Our proposal is not only novel with respect to the more general area of evolutionary generation of ensembles, but it also advances the state-of-the-art in the use of ensemble in defect prediction. Method: We assess the effectiveness of our approach, dubbed as Multi-objective Ensemble Generation (MEG), by empirically benchmarking it with respect to the most related proposals we found in the literature on defect prediction ensembles and on multi-objective evolutionary ensembles (which, to the best of our knowledge, had never been previously applied to tackle defect prediction). Result: Our results show that MEG is able to generate ensembles which produce similar or more accurate predictions than those achieved by all the other approaches considered in 73% of the cases (with favourable large effect sizes in 80% of them). Conclusions: MEG is not only able to generate ensembles that yield more accurate defect predictions with respect to the benchmarks considered, but it also does it automatically, thus relieving the engineers from the burden of manual design and experimentation. CCS CONCEPTS• Software and its engineering → Search-based software engineering; Software defect analysis; • Computing methodologies → Ensemble methods.

show abstract

Section: Meg: Multi-objective Ensemble Generationmentioning

confidence: 86%

Section: Meg: Multi-objective Ensemble Generationmentioning

confidence: 99%

MEG: Multi-objective Ensemble Generation for Software Defect Prediction

Moussa

Guizzo

Sarro

2022

Proceedings of the 16th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement

View full text Add to dashboard Cite

show abstract

“…Liang et al [35] proposed classifier ensemble utilizing mean Q-statistic measure together with general classification error as the objectives of Multimodal Multi-objective algorithm (mmo) optimizing ensemble composition. A similar approach can be found in the work of Fletcher et al [15]. The authors proposed a non-specialized ensemble classifier that utilized double-fault measure as a diversity assessment and popular NSGA-II as an optimization algorithm.…”

Section: B Multi-objective Optimizationmentioning

confidence: 99%

“…Our method employs multi-objective optimization (MOO) that aims to improve all the given objectives as simple metrics, which as a result enables flexibility not possible in single-objective optimization (SOO) using a set combination of criteria. It also appears that they can achieve better results according to the same objectives than SOO algorithms [15]. In this paper, we examine the possibility of utilizing MOO algorithm to build an ensemble of classifiers directly optimizing both precision and recall.…”

Section: Introductionmentioning

confidence: 99%

Multicriteria Classifier Ensemble Learning for Imbalanced Data

2022

View full text Add to dashboard Cite

One of the vital problems with the imbalanced data classifier training is the definition of an optimization criterion. Typically, since the exact cost of misclassification of the individual classes is unknown, combined metrics and loss functions that roughly balance the cost for each class are used. However, this approach can lead to a loss of information, since different trade-offs between class misclassification rates can produce similar combined metric values. To address this issue, this paper discusses a multi-criteria ensemble training method for the imbalanced data. The proposed method jointly optimizes precision and recall, and provides the end-user with a set of Pareto optimal solutions, from which the final one can be chosen according to the user's preference. The proposed approach was evaluated on a number of benchmark datasets and compared with the single-criterion approach (where the selected criterion was one of the chosen metrics). The results of the experiments confirmed the usefulness of the obtained method, which on the one hand guarantees good quality, i.e., not worse than the one obtained with the use of single-criterion optimization, and on the other hand, offers the user the opportunity to choose the solution that best meets their expectations regarding the trade-off between errors on the minority and the majority class.

show abstract

“…In particular, scholars have combined intelligent network with the objective optimization method to build the model. Fletcher et al [25] have used multiobjective optimization to solve the nonspecialized ensemble classifier problem. Wang et al [26] have proposed an efficient sorting multiobjective optimization framework for sustainable supply network optimization and decision-making.…”

Section: Related Workmentioning

confidence: 99%

Optimal Route Selection Decision-Making Based on Intelligent Network

Zhao

Zhang

2021

Journal of Mathematics

View full text Add to dashboard Cite

Modern intelligent network provides a lot of convenience for the development of the society, especially for some practical NP-hard optimal problems. In this paper, we study a game case which is a problem of optimal strategy of desert crossing based on intelligent network and then propose an optimal route selection decision-making. We construct some dynamic multiobjective network problems and use heuristic algorithm to solve the two problems in four levels in the paper. The innovation of this paper lies in the optimal route selection strategy which considers different environment conditions and their own situations. The cross research between the practical engineering problems and mathematics is applied flexibly in this article. Moreover, the strategy given in this paper is a general direction rather than a specific result, which is also in line with the characteristics of diversity of the game optimal results.

show abstract

A non-specialized ensemble classifier using multi-objective optimization

Cited by 11 publications

References 66 publications

MEG: Multi-objective Ensemble Generation for Software Defect Prediction

MEG: Multi-objective Ensemble Generation for Software Defect Prediction

Multicriteria Classifier Ensemble Learning for Imbalanced Data

Optimal Route Selection Decision-Making Based on Intelligent Network

Contact Info

Product

Resources

About