Browsing by Author "Yevseyeva, Iryna"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
- 3D fast convex-hull-based evolutionary multiobjective optimization algorithmPublication . Zhao, Jiaqi; Jiao, Licheng; Liu, Fang; Basto-Fernandes, Vitor; Yevseyeva, Iryna; Xia, Shixiong; Emmerich, Michael T.M.The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves have been widely used in the machine learning community to analyze the performance of classifiers. The area (or volume) under the convex hull has been used as a scalar indicator for the performance of a set of classifiers in ROC and DET space. Recently, 3D convex-hull-based evolutionary multiobjective optimization algorithm (3DCH-EMOA) has been proposed to maximize the volume of convex hull for binary classification combined with parsimony and three-way classification problems. However, 3DCH-EMOA revealed high consumption of computational resources due to redundant convex hull calculations and a frequent execution of nondominated sorting. In this paper, we introduce incremental convex hull calculation and a fast replacement for non-dominated sorting. While achieving the same high quality results, the computational effort of 3DCH-EMOA can be reduced by orders of magnitude. The average time complexity of 3DCH-EMOA in each generation is reduced from to per iteration, where n is the population size. Six test function problems are used to test the performance of the newly proposed method, and the algorithms are compared to several state-of-the-art algorithms, including NSGA-III, RVEA, etc., which were not compared to 3DCH-EMOA before. Experimental results show that the new version of the algorithm (3DFCH-EMOA) can speed up 3DCH-EMOA for about 30 times for a typical population size of 300 without reducing the performance of the method. Besides, the proposed algorithm is applied for neural networks pruning, and several UCI datasets are used to test the performance.
- An automatic generation of textual pattern rules for digital content filters proposal, using grammatical evolution genetic programmingPublication . Basto-Fernandes, Vitor; Yevseyeva, Iryna; Frantz, Rafael Z.; Grilo, Carlos Fernando Almeida; Díaz, Noemí Pérez; Emmerich, Michael
- Characterising Enterprise Application Integration Solutions as Discrete-Event SystemsPublication . Sawicki, Sandro; Frantz, Rafael Z.; Basto-Fernandes, Vitor; Fabricia Roos-Frantz, Fabricia; Yevseyeva, Iryna; Corchuelo, RafaelIt is not difficult to find an enterprise which has a software ecosystem composed of applications that were built using different technologies, data models, operating systems, and most often were not designed to exchange data and share functionalities. Enterprise Application Integration provides methodologies and tools to design and implement integration solutions. The state-of-the-art integration technologies provide a domain-specific language that enables the design of conceptual models for integration solutions. The analysis of integration solutions to predict their behaviour and find possible performance bottlenecks is an important activity that contributes to increase the quality of the delivered solutions, however, software engineers follow a costly, risky, and time-consuming approach. Integration solutions shall be understood as a discrete-event system. This chapter introduces a new approach based on simulation to take advantage of well-established techniques and tools for discrete-event simulation, cutting down cost, risk, and time to deliver better integration solutions.
- A decision support system for corporations cybersecurity managementPublication . Roldan-Molina, Gabriela; Almache-Cueva, Mario; Silva-Rabadão, Carlos; Yevseyeva, Iryna; Basto-Fernandes, VitorThis paper presents ongoing work on a decision aiding software intended to support cyber risks and cyber threats analysis of an information and communications technological infrastructure. The software will help corporations Chief Information Security Officers on cyber security risk analysis, decision-making, prevention measures and risk strategies for the infrastructure and information assets protection.
- Multiobjective optimization of classifiers by means of 3D convex-hull-based evolutionary algorithmsPublication . Zhao, Jiaqi; Basto-Fernandes, Vitor; Jiao, Licheng; Yevseyeva, Iryna; Maulana, Asep; Li, Rui; Bäck, Thomas; Tang, Ke; Emmerich, Michael T.M.The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves are frequently used in the machine learning community to analyze the performance of binary classifiers. Recently, the convex-hull-based multiobjective genetic programming algorithm was proposed and successfully applied to maximize the convex hull area for binary classification problems by minimizing false positive rate and maximizing true positive rate at the same time using indicator-based evolutionary algorithms. The area under the ROC curve was used for the performance assessment and to guide the search. Here we extend this research and propose two major advancements: Firstly we formulate the algorithm in detection error tradeoff space, minimizing false positives and false negatives, with the advantage that misclassification cost tradeoff can be assessed directly. Secondly, we add complexity as an objective function, which gives rise to a 3D objective space (as opposed to a 2D previous ROC space). A domain specific performance indicator for 3D Pareto front approximations, the volume above DET surface, is introduced, and used to guide the indicator-based evolutionary algorithm to find optimal approximation sets. We assess the performance of the new algorithm on designed theoretical problems with different geometries of Pareto fronts and DET surfaces, and two application-oriented benchmarks: (1) Designing spam filters with low numbers of false rejects, false accepts, and low computational cost using rule ensembles, and (2) finding sparse neural networks for binary classification of test data from the UCI machine learning benchmark. The results show a high performance of the new algorithm as compared to conventional methods for multicriteria optimization.
- Multiobjective sparse ensemble learning by means of evolutionary algorithmsPublication . Zhao, Jiaqi; Jiao, Licheng; Xia, Shixiong; Basto-Fernandes, Vitor; Yevseyeva, Iryna; Zhou, Yong; Emmerich, Michael T.M.Ensemble learning can improve the performance of individual classifiers by combining their decisions. The sparseness of ensemble learning has attracted much attention in recent years. In this paper, a novel multiobjective sparse ensemble learning (MOSEL) model is proposed. Firstly, to describe the ensemble classifiers more precisely the detection error trade-off (DET) curve is taken into consideration. The sparsity ratio (sr) is treated as the third objective to be minimized, in addition to false positive rate (fpr) and false negative rate (fnr) minimization. The MOSEL turns out to be augmented DET (ADET) convex hull maximization problem. Secondly, several evolutionary multiobjective algorithms are exploited to find sparse ensemble classifiers with strong performance. The relationship between the sparsity and the performance of ensemble classifiers on the ADET space is explained. Thirdly, an adaptive MOSEL classifiers selection method is designed to select the most suitable ensemble classifiers for a given dataset. The proposed MOSEL method is applied to well-known MNIST datasets and a real-world remote sensing image change detection problem, and several datasets are used to test the performance of the method on this problem. Experimental results based on both MNIST datasets and remote sensing image change detection show that MOSEL performs significantly better than conventional ensemble learning methods.
- A spam filtering multi-objective optimization study covering parsimony maximization and three-way classificationPublication . Basto-Fernandes, Vitor; Yevseyeva, Iryna; Méndez, José R.; Zhao, Jiaqi; Fdez-Riverola, Florentino; Emmerich, Michael T.M.Classifier performance optimization in machine learning can be stated as a multi-objective optimization problem. In this context, recent works have shown the utility of simple evolutionary multi-objective algorithms (NSGA-II, SPEA2) to conveniently optimize the global performance of different anti-spam filters. The present work extends existing contributions in the spam filtering domain by using three novel indicator-based (SMS-EMOA, CH-EMOA) and decomposition-based (MOEA/D) evolutionary multiobjective algorithms. The proposed approaches are used to optimize the performance of a heterogeneous ensemble of classifiers into two different but complementary scenarios: parsimony maximization and e-mail classification under low confidence level. Experimental results using a publicly available standard corpus allowed us to identify interesting conclusions regarding both the utility of rule-based classification filters and the appropriateness of a three-way classification system in the spam filtering domain.
- A survey of diversity-oriented optimizationPublication . Basto-Fernandes, Vitor; Yevseyeva, Iryna; Emmerich, Michael
- Two-stage Security Controls SelectionPublication . Yevseyeva, Iryna; Basto-Fernandes, Vitor; van Moorsel, Aad; Janicke, Helge; Emmerich, Michaelo protect a system from potential cyber security breaches and attacks, one needs to select efficient security controls, taking into account technical and institutional goals and constraints, such as available budget, enterprise activity, internal and external environment. Here we model the security controls selection problem as a two-stage decision making: First, managers and information security officers define the size of security budget. Second, the budget is distributed between various types of security controls. By viewing loss prevention with security controls measured as gains relative to a baseline (losses without applying security controls), we formulate the decision making process as a classical portfolio selection problem. The model assumes security budget allocation as a two objective problem, balancing risk and return, given a budget constraint. The Sharpe ratio is used to identify an optimal point on the Pareto front to spend the budget. At the management level the budget size is chosen by computing the trade-offs between Sharpe ratios and budget sizes. It is shown that the proposed two-stage decision making model can be solved by quadratic programming techniques, which is shown for a test case scenario with realistic data.