Catalin Stoean

Multimodal Optimization by Means of a Topological Species Conservation Algorithm

Any evolutionary technique for multimodal optimization must answer two crucial questions in order to guarantee some success on a given task: How to most unboundedly distinguish between the different attraction basins and how to most accurately safeguard the consequently discovered solutions. This paper thus aims to present a novel technique that integrates the conservation of the best successive local individuals (as in the species conserving genetic algorithm) with a topological subpopulations separation (as in the multinational genetic algorithm) instead of the common but problematic radius-triggered manner. A special treatment for offspring integration, a more rigorous control on the allowed number and uniqueness of the resulting seeds, and a more efficient fitness evaluations budget management further augment a previously suggested naïve combination of the two algorithms. Experiments have been performed on a series of benchmark test functions, including a problem from engineering design. Comparison is primarily conducted to show the significant performance difference to the naïve combination; also the related radius-dependent conserving algorithm is subsequently addressed. Additionally, three more multimodal evolutionary methods, being either conceptually close, competitive as radius-based strategies, or recent state-of-the-art are also taken into account. We detect a clear advantage of three of the six algorithms that, in the case of our method, probably comes from the proper topological separation into subpopulations according to the existing attraction basins, independent of their locations in the function landscape. Additionally, an investigation of the parameter independence of the method as compared to the radius-compelled algorithms is systematically accomplished.

Modeling medical decision making by support vector machines, explaining by rules of evolutionary algorithms with feature selection

Machine learning support for medical decision making is truly helpful only when it meets two conditions: high prediction accuracy and a good explanation of how the diagnosis was reached. Support vector machines (SVMs) successfully achieve the first target due to a kernel-based engine; evolutionary algorithms (EAs) can greatly accomplish the second owing to their adaptable nature. In this context, the current paper puts forward a two-step hybridized methodology, where learning is accurately performed by the SVMs and a comprehensible emulation of the resulting decision model is generated by EAs in the form of propositional rules, while referring only those indicators that highly influence the class separation. An individual highlighting of the medical attributes that trigger a specific diagnosis for a current patient record is additionally obtained; this feature thus increases the confidence of the physician in the resulting automated diagnosis. Without loss of generality, we aim to model three breast cancer instances, for reasons of both high incidence of the disease and the large application of state of the art artificial intelligence methods for this medical task. As such, the prediction of a benign/malignant condition as well as the recurrence/nonrecurrence of a cancer event are studied on the Wisconsin corresponding data sets from the UCI Machine Learning Repository. The proposed hybridization reached its goals. Rule prototypes evolve against a SVM consistent training data, while diversity among the different classes is implicitly preserved. Feature selection eventually leads to a resulting rule set where only the significant medical indicators together with the discriminating threshold values are referred, while individual relevance of attributes can be additionally obtained for each patient. The gain is thus dual: the EA benefits from a noise-free SVM preprocessed data and the resulting SVM model is able to output rules in a comprehensible, concise format for the physician.

Disburdening the species conservation evolutionary algorithm of arguing with radii

The present paper investigates the hybridization of two well-known multimodal optimization methods, i.e. species conservation and multinational algorithms. The topological species conservation algorithm embraces the vision of the existence of subpopulations around seeds (the best local individuals) and the preservation of these dominating individuals from one generation to another, but detects multimodality by means of the hill-valley mechanism employed by multinational algorithms. The aim is to inherit the strengths of both parent techniques and at the same time overcome their flaws. The species conservation algorithm efficiently keeps track of several good search space regions at once, but is difficult to parametrize without prior problem knowledge. Conversely, the multinational algorithms use many functionevaluations to establish subpopulations, but do not depend onprovided radius parameter values. Experiments with all threealgorithms are made on a wide range of test problems in order toinvestigate their advantages and shortcomings.

Evolutionary-driven support vector machines for determining the degree of liver fibrosis in chronic hepatitis C

OBJECTIVEnHepatic fibrosis, the principal pointer to the development of a liver disease within chronic hepatitis C, can be measured through several stages. The correct evaluation of its degree, based on recent different non-invasive procedures, is of current major concern. The latest methodology for assessing it is the Fibroscan and the effect of its employment is impressive. However, the complex interaction between its stiffness indicator and the other biochemical and clinical examinations towards a respective degree of liver fibrosis is hard to be manually discovered. In this respect, the novel, well-performing evolutionary-powered support vector machines are proposed towards an automated learning of the relationship between medical attributes and fibrosis levels. The traditional support vector machines have been an often choice for addressing hepatic fibrosis, while the evolutionary option has been validated on many real-world tasks and proven flexibility and good performance.nnnMETHODS AND MATERIALSnThe evolutionary approach is simple and direct, resulting from the hybridization of the learning component within support vector machines and the optimization engine of evolutionary algorithms. It discovers the optimal coefficients of surfaces that separate instances of distinct classes. Apart from a detached manner of establishing the fibrosis degree for new cases, a resulting formula also offers insight upon the correspondence between the medical factors and the respective outcome. What is more, a feature selection genetic algorithm can be further embedded into the method structure, in order to dynamically concentrate search only on the most relevant attributes. The data set refers 722 patients with chronic hepatitis C infection and 24 indicators. The five possible degrees of fibrosis range from F0 (no fibrosis) to F4 (cirrhosis).nnnRESULTSnSince the standard support vector machines are among the most frequently used methods in recent artificial intelligence studies for hepatic fibrosis staging, the evolutionary method is viewed in comparison to the traditional one. The multifaceted discrimination into all five degrees of fibrosis and the slightly less difficult common separation into solely three related stages are both investigated. The resulting performance proves the superiority over the standard support vector classification and the attained formula is helpful in providing an immediate calculation of the liver stage for new cases, while establishing the presence/absence and comprehending the weight of each medical factor with respect to a certain fibrosis level.nnnCONCLUSIONnThe use of the evolutionary technique for fibrosis degree prediction triggers simplicity and offers a direct expression of the influence of dynamically selected indicators on the corresponding stage. Perhaps most importantly, it significantly surpasses the classical support vector machines, which are both widely used and technically sound. All these therefore confirm the promise of the new methodology towards a dependable support within the medical decision-making.

Feature selection for a cooperative coevolutionary classifier in liver fibrosis diagnosis

This paper presents an automatic tool capable to learn from a patients data set with 24 medical indicators characterizing each sample and to subsequently use the acquired knowledge to differentiate between five degrees of liver fibrosis. The indicators represent clinical observations and the liver stiffness provided by the new, non-invasive procedure of Fibroscan. The proposed technique combines a hill climbing algorithm that selects subsets of important attributes for an accurate classification and a core represented by a cooperative coevolutionary classifier that builds rules for establishing the diagnosis for every new patient. The results of the novel method proved to be superior as compared to the ones obtained by other important classification techniques from the literature. Additionally, the proposed methodology extracts a set of the most meaningful attributes from the available ones.

Concerning the potential of evolutionary support vector machines

Within the present paper, we put forward a novel hybridization between support vector machines and evolutionary algorithms. Evolutionary support vector machines consider the classification task as in support vector machines but use an evolutionary algorithm to solve the optimization problem of determining the decision function. They can explicitly acquire the coefficients of the separating hyperplane, which is often not possible within the classical technique. More important, evolutionary support vector machines obtain the coefficients directly from the evolutionary algorithm and can refer them at any point during a run. In addition, they do not require properties of positive (semi-)definition for kernels within nonlinear learning. The concept can be furthermore extended to handle large amounts of data, a problem frequently occurring e.g. in spam mail detection, one of our test cases. An adapted chunking technique is therefore alternatively used. In addition to two different representations, a crowding variant of the evolutionary algorithm is tested in order to investigate whether the performance of the algorithm is maintained; its global search capabilities would be important for the prospected coevolution of non-standard kernels. Evolutionary support vector machines are validated on four real-world classification tasks; obtained results show the promise of this new approach.

Support vector machine learning with an evolutionary engine

The paper presents a novel evolutionary technique constructed as an alternative of the standard support vector machines architecture. The approach adopts the learning strategy of the latter but aims to simplify and generalize its training, by offering a transparent substitute to the initial black-box. Contrary to the canonical technique, the evolutionary approach can at all times explicitly acquire the coefficients of the decision function, without any further constraints. Moreover, in order to converge, the evolutionary method does not require the positive (semi-)definition properties for kernels within nonlinear learning. Several potential structures, enhancements and additions are proposed, tested and confirmed using available benchmarking test problems. Computational results show the validity of the new approach in terms of runtime, prediction accuracy and flexibility.

Elitist generational genetic chromodynamics - a new radii-based evolutionary algorithm for multimodal optimization

A new radii-based evolutionary algorithm (EA) designed for multimodal optimization problems is proposed. The approach can be placed within the genetic chromodynamics framework and related to other EAs with local interaction, e.g. using species formation or clearing procedures. The underlying motivation for modifying the original algorithm was to preserve its ability to search for many optima in parallel while increasing convergence speed, especially for complex problems, through generational selection and different replacement schemes. The algorithm is applied to function optimization and classification; obtained experimental results, in part improved immensely by state-of-the-art parameter tuning (SPO), and encouraged further investigation.

Evolution of Cooperating Classification Rules with an Archiving Strategy to Underpin Collaboration

Individuals encoding potential rules to model an actual partition of samples into categories may be evolved by means of several well-known evolutionary classification techniques. Nevertheless, since a canonical evolutionary algorithm progresses towards one (global or local) optimum, some special construction or certain additional method are designed and attached to the classifier in order to maintain several basins of attraction of the different prospective rules. With the aim of offering a simpler option to these complex approaches and with an inspiration from the state-of-the-art cooperative coevolutionary algorithms, this chapter presents a novel classification tool, where rules for each class are evolved by a distinct population. Prototypes evolve simultaneously while they collaborate towards the goal of a good separation, in terms of performance and generalization ability. A supplementary archiving mechanism, which preserves a variety of the best evolved rules and eventually yields a thorough and diverse rule set, increases the forecasting precision of proposed technique. The novel algorithm is tested against two real-world decision problems regarding tumor diagnosis and obtained results demonstrate the initial presumption.

Evolutionary Support Vector Regression Machines

Evolutionary support vector machines (ESVMs) are a novel technique that assimilates the learning engine of the state-of-the-art support vector machines (SVMs) but evolves the coefficients of the decision function by means of evolutionary algorithms (EAs). The new method has accomplished the purpose for which it has been initially developed, that of a simpler alternative to the canonical SVM approach for solving the optimization component of training. ESVMs, as SVMs, are natural tools for primary application to classification. However, since the latter had been further on extended to also handle regression, it is the scope of this paper to present the corresponding evolutionary paradigm. In particular, we consider the hybridization with the classical epsi-support vector regression (epsi-SVR) introduced by Vapnik and the subsequent evolution of the coefficients of the regression hyperplane. epsi-evolutionary support regression (epsi-ESVR) is validated on the Boston housing benchmark problem and the obtained results demonstrate the promise of ESVMs also as concerns regression