Narrow Results

Ensembles with several classifiers (such as neural networks or decision trees) are widely used to improve the generalization performance over a single classifier. Proper diversity among component classifiers is considered an important parameter for ensemble construction so that failure of one may be compensated by others. Among various approaches, data sampling, i.e., different data sets for different classifiers, is found more effective than other approaches. A number of ensemble methods have been proposed under the umbrella of data sampling in which some are constrained to neural networks or decision trees and others are commonly applicable to both types of classifiers. We studied prominent data sampling techniques for neural network ensembles, and then experimentally evaluated their effectiveness on a common test ground. Based on overlap and uncover, the relation between generalization and diversity is presented. Eight ensemble methods were tested on 30 benchmark classification problems. We found that bagging and boosting, the pioneer ensemble methods, are still better than most of the other proposed methods. However, negative correlation learning that implicitly encourages different networks to different training spaces is shown as better or at least comparable to bagging and boosting that explicitly create different training spaces.

An ensemble performs well when the component classifiers are diverse yet accurate, so that the failure of one is compensated for by others. A number of methods have been investigated for constructing ensemble in which some of them train classifiers with the generated patterns. This study investigates a new technique of training pattern generation. The method alters input feature values of some patterns using the values of other patterns to generate different patterns for different classifiers. The effectiveness of neural network ensemble based on the proposed technique was evaluated using a suite of 25 benchmark classification problems, and was found to achieve performance better than or competitive with related conventional methods. Experimental investigation of different input values alteration techniques finds that alteration with pattern values in the same class is better for generalization, although other alteration techniques may offer more diversity.

Recommender systems are becoming a popular and important set of personalization techniques that assist individual users with navigating through the rapidly growing amount of information. A good recommender system should be able to not only find out the objects preferred by users, but also help users in discovering their personalized tastes. The former corresponds to high accuracy of the recommendation, while the latter to high diversity. A big challenge is to design an algorithm that provides both highly accurate and diverse recommendation. Traditional recommendation algorithms only take into account the contributions of similar users, thus, they tend to recommend popular items for users ignoring the diversity of recommendations. In this paper, we propose a recommendation algorithm by considering both the effects of similar and dissimilar users under the framework of collaborative filtering. Extensive analyses on three datasets, namely MovieLens, Netflix and Amazon, show that our method performs much better than the standard collaborative filtering algorithm for both accuracy and diversity.

Excitable cellular automata with dynamical excitation interval exhibit a wide range of space-time dynamics based on an interplay between propagating excitation patterns which modify excitability of the automaton cells. Such interactions leads to formation of standing domains of excitation, stationary waves and localized excitations. We analyzed morphological and generative diversities of the functions studied and characterized the functions with highest values of the diversities. Amongst other intriguing discoveries we found that upper boundary of excitation interval more significantly affects morphological diversity of configurations generated than lower boundary of the interval does and there is no match between functions which produce configurations of excitation with highest morphological diversity and configurations of interval boundaries with highest morphological diversity. Potential directions of future studies of excitable media with dynamically changing excitability may focus on relations of the automaton model with living excitable media, e.g. neural tissue and muscles, novel materials with memristive properties and networks of conductive polymers.

We investigate expressiveness, a parameter of one-dimensional cellular automata, in the context of simulated biological systems. The development of elementary cellular automata is interpreted in terms of biological systems, and biologically inspired parameters for biodiversity are applied to the configurations of cellular automata. This paper contains a survey of the Elementary Cellular Automata in terms of their expressiveness and an evaluation whether expressiveness is a meaningful term in the context of simulated biology.

The diversity of people’s musical tastes is one of the significant parts which helps people to better understand the behavior trends and cultural preferences of people. In this paper, based on Hill-type true diversity, we propose an improved diversity metric that fairly captures the diversity of musical tastes. This diversity efficiently considers all the three aspects of diversity definitions: variety, balance, and disparity, and keeps higher discriminatory power. Using this diversity metric, one can analyze users’ music tastes on Xiami.com, one of the largest social music media in China; we explore the association between the diversity and various variables which represent users’ personal traits, as well as the difference between different genre levels and map the cultural pattern of difference genres. Our findings dig out many efficient factors that deeply impact users’ music tastes, and provide the global pattern of musical cultural structure on the Chinese online music society.

This paper will setup a trade model to explore the impact of the diversity of talent distribution and the technology difference on the pattern of trade (POT) and income inequality of an economy. We find that not only the diversity effect but also the technology effect can matter for the pattern of POT. We demonstrate that, in the free-trade equilibrium, if the technology effect dominates the diversity effect then the country with a more (less) diverse distribution of talent may export the goods produced by a technology with supermodularity (submodularity). In addition, we prove that the relative technology difference will affect income inequality. If the technological advance for the submodular sector S is better than for the supermodular sector C, then income inequality would increase.

We consider a version of large population games whose players compete for resources using strategies with adaptable preferences. The system efficiency is measured by the variance of the decisions. In the regime where the system can be plagued by the maladaptive behavior of the players, we find that diversity among the players improves the system efficiency, though it slows the convergence to the steady state. Diversity causes a mild spread of resources at the transient state, but reduces the uneven distribution of resources in the steady state.

An effective way to improve a classification method's performance is to create ensembles of classifiers. Two elements are believed to be important in constructing an ensemble: (a) the performance of each individual classifier; and (b) diversity among the classifiers. Nevertheless, most works based on diversity suggest that there exists only weak correlation between classifier performance and ensemble accuracy. We propose compound diversity functions which combine the diversities with the performance of each individual classifier, and show that there is a strong correlation between the proposed functions and ensemble accuracy. Calculation of the correlations with different ensemble creation methods, different problems and different classification algorithms on 0.624 million ensembles suggests that most compound diversity functions are better than traditional diversity measures. The population-based Genetic Algorithm was used to search for the best ensembles on a handwritten numerals recognition problem and to evaluate 42.24 million ensembles. The statistical results indicate that compound diversity functions perform better than traditional diversity measures, and are helpful in selecting the best ensembles.

The manifold-based learning methods have recently drawn more and more attention in dimension reduction. In this paper, a novel manifold-based learning method named enhanced parameter-free diversity discriminant preserving projections (EPFDDPP) is presented, which effectively avoids the neighborhood parameter selection and characterizes the manifold structure well. EPFDDPP redefines the weighted matrices, the discriminating similarity matrix and the discriminating diversity matrix, respectively. The weighted matrices are computed by the cosine angle distance between two data points and take special consideration of both the local information and the class label information, which are parameterless and favorable for face recognition. After characterizing the discriminating similarity scatter matrix and the discriminating diversity scatter matrix, the novel feature extraction criterion is derived based on maximum margin criterion. Experimental results on the Wine data set, Olivetti Research Laboratory (ORL); AR (face database created by Aleix Martinez and Robert Benavente); and Pose, Illumination, and Expression (PIE) face databases show the effectiveness of the proposed method.

The performance of the traditional Pareto-based evolutionary algorithms sharply reduces for many-objective optimization problems, one of the main reasons is that Pareto dominance could not provide sufficient selection pressure to make progress in a given population. To increase the selection pressure toward the global optimal solutions and better maintain the quality of selected solutions, in this paper, a new dominance method based on expanding dominated area is proposed. This dominance method skillfully combines the advantages of two existing popular dominance methods to further expand the dominated area and better maintain the quality of selected solutions. Besides, through dynamically adjusting its parameter with the iteration, our proposed dominance method can timely adjust the selection pressure in the process of evolution. To demonstrate the quality of selected solutions by our proposed dominance method, the experiments on a number of well-known benchmark problems with 5–25 objectives are conducted and compared with that of the four state-of-the-art dominance methods based on expanding dominated area. Experimental results show that the new dominance method not only enhances the selection pressure but also better maintains the quality of selected solutions.

The purpose of this paper is to analyze in some detail the arguably simplest case of diversity-induced resonance: that of a system of globally-coupled linear oscillators subjected to a periodic forcing. Diversity appears as the parameters characterizing each oscillator, namely its mass, internal frequency and damping coefficient are drawn from a probability distribution. The main ingredients for the diversity-induced-resonance phenomenon are present in this system as the oscillators display a variability in the individual responses but are induced, by the coupling, to synchronize their responses. A steady-state solution for this model is obtained. We also determine the conditions under which it is possible to find a resonance effect.

A lot of schemes have been proposed for the establishment of u-city. Especially, most of the schemes are based on ubiquitous networks. In this paper, it is assumed that the ubiquitous networks include some mobile agents. Therefore, an intelligent positioning scheme is proposed for the efficient positioning of the mobile agents in the ubiquitous networks. The approach consists of location detection and location tracking. Furthermore, an optimal diversity technique is presented in this paper to improve the positioning performance. Simulation results indicate that using the suggested algorithms, the excellent detection and tracking performance can be achieved in ubiquitous networks for u-city.

Motivated by Leinster-Cobbold measures of biodiversity, the notion of the spread of a finite metric space is introduced. This is related to Leinster’s magnitude of a metric space. Spread is generalized to infinite metric spaces equipped with a measure and is calculated for spheres and straight lines. For Riemannian manifolds the spread is related to the volume and total scalar curvature. A notion of scale-dependent dimension is introduced and seen for approximations to certain fractals to be numerically close to the Minkowski dimension of the original fractals.

Evolutionary algorithms (EAs) can be used to find solutions in dynamic environments. In such cases, after a change in the environment, EAs can either be restarted or they can take advantage of previous knowledge to resume the evolutionary process. The second option tends to be faster and demands less computational effort. The preservation or growth of population diversity is one of the strategies used to advance the evolutionary process after modifications to the environment. We propose a new adaptive method to control population diversity based on a model-reference. The EA evolves the population whereas a control strategy, independently, handles the population diversity. Thus, the adaptive EA evolves a population that follows a diversity-reference model. The proposed model, called the Diversity-Reference Adaptive Control Evolutionary Algorithm (DRAC), aims to maintain or increase the population diversity, thus avoiding premature convergence, and assuring exploration of the solution space during the whole evolutionary process. We also propose a diversity models based on the dynamics of heterozygosity of the population, as models to be tracked by the diversity control. The performance of DRAC showed promising results when compared with the standard genetic algorithm and six other adaptive evolutionary algorithms in 14 different experiments with three different types of environments.

Centrality measures have been helping to explain the behavior of objects, given their relation, in a wide variety of problems, since sociology to chemistry. This work considers these measures to assess the importance of every classifier belonging to an ensemble of classifiers, aiming to improve a Multiple Classifier System (MCS). Assessing the classifier’s importance by employing centrality measures, inspired two different approaches: one for selecting classifiers and another for fusion. The selection approach, called Centrality Based Selection (CBS), adopts a trade-off between the classifier’s accuracy and their diversity. The sub-optimal selected subset presents good results against selection methods from the literature, being superior in 67.22% of the cases. The second approach, the integration, is named Centrality Based Fusion (CBF). This approach is a weighted combination method, which is superior to literature in 70% of the cases.

Many real-world problems involve measures of objectives that may be dynamically optimized. The application of evolutionary algorithms, such as genetic algorithms, in time dependent optimization is currently receiving growing interest as potential applications are numerous ranging from mobile robotics to real time process command. Moreover, constant evaluation functions skew results relative to natural evolution so that it has become a promising gap to combine effectiveness and diversity in a genetic algorithm. This paper features both theoretical and empirical analysis of the behavior of genetic algorithms in such an environment. We present a comparison between the effectivenss of traditional genetic algorithm and the dual genetic algorithm which has revealed to be a particularly adaptive tool for optimizing a lot of diversified classes of functions. This comparison has been performed on a model of dynamical environments which characteristics are analyzed in order to establish the basis of a testbed for further experiments. We also discuss fundamental properties that explain the effectiveness of the dual paradigm to manage dynamical environments.

A general model linking environmental fluctuations and species richness is proposed. This model includes two important biological mechanisms. The first term describes the global negative effect of fluctuations on richness via stress and density-independent mortality; the second term represents the positive effect of perturbations on richness by competitive relaxation. Both effects are modeled as exponential functions. The model can be made richness-dependent putting the average competition coefficients as a function of the actual diversity. The system shows a non-trivial behavior since it has local maxima or minima in the richness function at intermediate values of environmental variability. The existence of these points depends on the ratio between stress sensitivity and competition coefficients. The discrete version of the model exhibits chaotic fluctuations when the initial richness is high.

The Council on Social Work Education's (CSWE) instruction on diversity and social justice is central to the mission of social work education. The population of the United States has become more diverse and social work education has a pressing need to ensure students understand how diversity and social justice issues shape human experiences. Little research has systematically examined Bachelor of Social Work (BSW) programs in that regard. This paper examines correlations among demographic characteristics and program directors' impressions on teaching diversity and social justice in the United States' (BSW) programs. Using Qualtrics, a web-based survey tool, 36 program directors responded to a 47-item instrument composed of both closed and open-ended questions. Content analysis of the data was conducted with the assistance of Nvivo 12 to identify themes and nodes. However, due to inadequate information from the program directors, the open-ended questions were analyzed using thematic analysis. Emergent themes primarily pertained to implicit and explicit curricula. A central finding from the data was that there was variation in the way schools approached instruction regarding diversity and social justice assessment. The study raises questions for continued research and may have implications for the role of accrediting organizations in offering guidelines for diversity and social justice instruction and assessment.

We develop a quantitative framework for understanding the class of wicked problems that emerge at the intersections of natural, social, and technological complex systems. Wicked problems reflect our incomplete understanding of interdependent global systems and the systemic risk they pose; such problems escape solutions because they are often ill-defined, and thus mis-identified and under-appreciated by communities of problem-solvers. While there are well-documented benefits to tackling boundary-crossing problems from various viewpoints, the integration of diverse approaches can nevertheless contribute confusion around the collective understanding of the core concepts and feasible solutions. We explore this paradox by analyzing the development of both scholarly (social) and topical (cognitive) communities — two facets of knowledge production studies here that contribute towards the evolution of knowledge in and around a problem, termed a knowledge trajectory — associated with three wicked problems: deforestation, invasive species, and wildlife trade. We posit that saturation in the dynamics of social and cognitive diversity growth is an indicator of reduced uncertainty in the evolution of the comprehensive knowledge trajectory emerging around each wicked problem. Informed by comprehensive bibliometric data capturing both social and cognitive dimensions of each problem domain, we thereby develop a framework that assesses the stability of knowledge trajectory dynamics as an indicator of wickedness associated with conceptual and solution uncertainty. As such, our results identify wildlife trade as a wicked problem that may be difficult to address given recent instability in its knowledge trajectory.