Search

Ensembles are a well established machine learning paradigm, leading to accurate and robust models, predominantly applied to predictive modeling tasks. Ensemble models comprise a finite set of diverse predictive models whose combined output is expected to yield an improved predictive performance as compared to an individual model. In this paper, we propose a new method for learning ensembles of process-based models of dynamic systems. The process-based modeling paradigm employs domain-specific knowledge to automatically learn models of dynamic systems from time-series observational data. Previous work has shown that ensembles based on sampling observational data (i.e., bagging and boosting), significantly improve predictive performance of process-based models. However, this improvement comes at the cost of a substantial increase of the computational time needed for learning. To address this problem, the paper proposes a method that aims at efficiently learning ensembles of process-based models, while maintaining their accurate long-term predictive performance. This is achieved by constructing ensembles with sampling domain-specific knowledge instead of sampling data. We apply the proposed method to and evaluate its performance on a set of problems of automated predictive modeling in three lake ecosystems using a library of process-based knowledge for modeling population dynamics. The experimental results identify the optimal design decisions regarding the learning algorithm. The results also show that the proposed ensembles yield significantly more accurate predictions of population dynamics as compared to individual process-based models. Finally, while their predictive performance is comparable to the one of ensembles obtained with the state-of-the-art methods of bagging and boosting, they are substantially more efficient. [ABSTRACT FROM AUTHOR]

In the theory of belief functions, the approximation of a basic belief assignment (BBA) is for reducing the high computational cost especially when large number of focal elements are available. In traditional BBA approximation approaches, a focal element’s own characteristics such as the mass assignment and the cardinality, are usually used separately or jointly as criteria for the removal of focal elements. Besides the computational cost, the distance between the original BBA and the approximated one is also concerned, which represents the loss of information in BBA approximation. In this paper, an iterative approximation approach is proposed based on maximizing the closeness, i.e., minimizing the distance between the approximated BBA in current iteration and the BBA obtained in the previous iteration, where one focal element is removed in each iteration. The iteration stops when the desired number of focal elements is reached. The performance evaluation approaches for BBA approximations are also discussed and used to compare and evaluate traditional BBA approximations and the newly proposed one in this paper, which include traditional time-based way, closeness-based way and new proposed ones. Experimental results and related analyses are provided to show the rationality and efficiency of our proposed new BBA approximation. [ABSTRACT FROM AUTHOR]

Information carried by an image can be distorted due to different image processing steps introduced by different electronic means of storage and communication. Therefore, development of algorithms which can automatically assess a quality of the image in a way that is consistent with human evaluation is important. In this paper, an approach to image quality assessment (IQA) is proposed in which the quality of a given image is evaluated jointly by several IQA approaches. At first, in order to obtain such joint models, an optimisation problem of IQA measures aggregation is defined, where a weighted sum of their outputs, i.e., objective scores, is used as the aggregation operator. Then, the weight of each measure is considered as a decision variable in a problem of minimisation of root mean square error between obtained objective scores and subjective scores. Subjective scores reflect ground-truth and involve evaluation of images by human observers. The optimisation problem is solved using a genetic algorithm, which also selects suitable measures used in aggregation. Obtained multimeasures are evaluated on four largest widely used image benchmarks and compared against state-of-the-art full-reference IQA approaches. Results of comparison reveal that the proposed approach outperforms other competing measures. [ABSTRACT FROM AUTHOR]

Ellipse fitting is a highly researched and mature topic. Surprisingly, however, no existing method has thus far considered the data point eccentricity in its ellipse fitting procedure. Here, we introduce the concept of eccentricity of a data point, in analogy with the idea of ellipse eccentricity. We then show empirically that, irrespective of ellipse fitting method used, the root mean square error (RMSE) of a fit increases with the eccentricity of the data point set. The main contribution of the paper is based on the hypothesis that if the data point set were pre-processed to strategically add additional data points in regions of high eccentricity, then the quality of a fit could be improved. Conditional validity of this hypothesis is demonstrated mathematically using a model scenario. Based on this confirmation we propose an algorithm that pre-processes the data so that data points with high eccentricity are replicated. The improvement of ellipse fitting is then demonstrated empirically in real-world application of 3D reconstruction of a plant root system for phenotypic analysis. The degree of improvement for different underlying ellipse fitting methods as a function of data noise level is also analysed. We show that almost every method tested, irrespective of whether it minimizes algebraic error or geometric error, shows improvement in the fit following data augmentation using the proposed pre-processing algorithm. [ABSTRACT FROM AUTHOR]

In this paper we consider the problem of restoration of a image contaminated by a mixture of Gaussian and impulse noises. We propose a new statistic called ROADGI which improves the well-known Rank-Ordered Absolute Differences (ROAD) statistic for detecting points contaminated with the impulse noise in this context. Combining ROADGI statistic with the method of weights optimization we obtain a new algorithm called Optimal Weights Mixed Filter (OWMF) to deal with the mixed noise. Our simulation results show that the proposed filter is effective for mixed noises, as well as for single impulse noise and for single Gaussian noise. [ABSTRACT FROM AUTHOR]

The estimation of the correct number of dimensions is a long-standing problem in psychometrics. Several methods have been proposed, such as parallel analysis (PA), Kaiser-Guttman’s eigenvalue-greater-than-one rule, multiple average partial procedure (MAP), the maximum-likelihood approaches that use fit indexes as BIC and EBIC and the less used and studied approach called very simple structure (VSS). In the present paper a new approach to estimate the number of dimensions will be introduced and compared via simulation to the traditional techniques pointed above. The approach proposed in the current paper is called exploratory graph analysis (EGA), since it is based on the graphical lasso with the regularization parameter specified using EBIC. The number of dimensions is verified using the walktrap, a random walk algorithm used to identify communities in networks. In total, 32,000 data sets were simulated to fit known factor structures, with the data sets varying across different criteria: number of factors (2 and 4), number of items (5 and 10), sample size (100, 500, 1000 and 5000) and correlation between factors (orthogonal, .20, .50 and .70), resulting in 64 different conditions. For each condition, 500 data sets were simulated using lavaan. The result shows that the EGA performs comparable to parallel analysis, EBIC, eBIC and to Kaiser-Guttman rule in a number of situations, especially when the number of factors was two. However, EGA was the only technique able to correctly estimate the number of dimensions in the four-factor structure when the correlation between factors were .7, showing an accuracy of 100% for a sample size of 5,000 observations. Finally, the EGA was used to estimate the number of factors in a real dataset, in order to compare its performance with the other six techniques tested in the simulation study. [ABSTRACT FROM AUTHOR]

The rapid worldwide evolution of LEDs as light sources has brought new challenges, which means that new methods are needed and new algorithms have to be developed. Since the majority of LED luminaries are of the multi-source type, established methods for the design of light engines cannot be used in the design of LED light engines. This is because in the latter case what is involved is not just the design of a good reflector or projector lens, but the design of several lenses which have to work together in order to achieve satisfactory results. Since lenses can also be bought off the shelf from several manufacturers, it should be possible to combine together different off the shelf lenses in order to design a good light engine. However, with so many different lenses to choose from, it is almost impossible to find an optimal combination by hand, which means that some optimization algorithms need to be applied. In order for them to work properly, it is first necessary to describe the input data (i.e. spatial light distribution) in a functional form using as few as possible parameters. In this paper the focus is on the approximation of the input data, and the implementation of the well-known mathematical procedure for the separation of linear and nonlinear parameters, which can provide a substantial increase in performance. [ABSTRACT FROM AUTHOR]

The deployment of large number of femtocell base stations allows us to extend the coverage and efficiently utilize resources in a low cost manner. However, the small cell size of femtocell networks can result in frequent handovers to the mobile user, and consequently throughput degradation. Thus, in this paper, we propose predictive association control schemes to improve the system’s effective throughput. Our design focuses on reducing handover frequency without impacting on throughput. The proposed schemes determine handover decisions that contribute most to the network throughput and are proper for distributed implementations. The simulation results show significant gains compared with existing methods in terms of handover frequency and network throughput perspective. [ABSTRACT FROM AUTHOR]

We introduce a fast error-free tracking method applicable to sequences of two and three dimensional images. The core idea is to use Quadtree (resp. Octree) data structures for representing the spatial discretization of an image in two (resp. three) spatial dimensions. This representation enables one to merge into large computational cells the regions that can be faithfully described with such a coarse representation, thus significantly reducing the total number of degrees of freedom that are processed, without compromising accuracy. This encoding is particularly effective in the case of algorithms based on moving fronts, since the adaptive refinement provides a natural means to focus the processing resources on information near the moving front. In this paper, we use an existing contour based tracker and reformulate it to the case of Quad-/Oc-tree data structures. Relevant mathematical assumptions and derivations are presented for this purpose. We then demonstrate that, on standard bio-medical image sequences, a speed up of 5X is easily achieved in 2D and about 10X in 3D. [ABSTRACT FROM AUTHOR]

Nowadays, the appetite for the investment and mergers and acquisitions (M&A) activity in RFID companies is growing rapidly. Although the huge number of papers have addressed the topic of business valuation models based on statistical methods or neural network methods, only a few are dedicated to constructing a general framework for business valuation that improves the performance with network graph (NG) and the corresponding community mining (CM) method. In this study, an NG based business valuation model is proposed, where real options approach (ROA) integrating CM method is designed to predict the company’s net profit as well as estimate the company value. Three improvements are made in the proposed valuation model: Firstly, our model figures out the credibility of the node belonging to each community and clusters the network according to the evolutionary Bayesian method. Secondly, the improved bacterial foraging optimization algorithm (IBFOA) is adopted to calculate the optimized Bayesian posterior probability function. Finally, in IBFOA, bi-objective method is used to assess the accuracy of prediction, and these two objectives are combined into one objective function using a new Pareto boundary method. The proposed method returns lower forecasting error than 10 well-known forecasting models on 3 different time interval valuing tasks for the real-life simulation of RFID companies. [ABSTRACT FROM AUTHOR]

The increasing use of species distribution modeling (SDM) has raised new concerns regarding the inaccuracies, misunderstanding, and misuses of this important tool. One of those possible pitfalls − collinearity among environmental predictors − is assumed as an important source of model uncertainty, although it has not been subjected to a detailed evaluation in recent SDM studies. It is expected that collinearity will increase uncertainty in model parameters and decrease statistical power. Here we use a virtual species approach to compare models built using subsets of PCA-derived variables with models based on the original highly correlated climate variables. Moreover, we evaluated whether modelling algorithms and species data characteristics generate models with varying sensitivity to collinearity. As expected, collinearity among predictors decreases the efficiency and increases the uncertainty of species distribution models. Nevertheless, the intensity of the effect varied according to the algorithm properties: more complex procedures behaved better than simple envelope models. This may support the claim that complex models such as Maxent take advantage of existing collinearity in finding the best set of parameters. The interaction of the different factors with species characteristics (centroid and tolerance in environmental space) highlighted the importance of the so-called “idiosyncrasy in species responses” to model efficiency, but differences in prevalence may represent a better explanation. However, even models with low accuracy to predict suitability of individual cells may provide meaningful information on the estimation of range-size, a key species-trait for macroecological studies. We concluded that the use of PCA-derived variables is advised both to control the negative effects of collinearity and as a more objective solution for the problem of variable selection in studies dealing with large number of species with heterogeneous responses to environmental variables. [ABSTRACT FROM AUTHOR]

In the variational data assimilation (VarDA), the typical way for gradient computation is using the adjoint method. However, the adjoint method has many problems, such as low accuracy, difficult implementation and considerable complexity, for high-dimensional models. To overcome these shortcomings, a new data assimilation method based on dual number automatic differentiation (AD) is proposed. The important advantages of the method lies in that the coding of the tangent-linear/adjoint model is no longer necessary and that the value of the cost function and its corresponding gradient vector can be obtained simultaneously through only one forward computation in dual number space. The numerical simulations for data assimilation are implemented for a typical nonlinear advection equation and a parabolic equation. The results demonstrate that the new method can reconstruct the initial conditions of the high-dimensional nonlinear dynamical system conveniently and accurately. Additionally, the estimated initial values can converge to the true values quickly, even if noise is present in the observations. [ABSTRACT FROM AUTHOR]

High dimensional data are commonly encountered in various scientific fields and pose great challenges to modern statistical analysis. To address this issue different penalized regression procedures have been introduced in the litrature, but these methods cannot cope with the problem of outliers and leverage points in the heavy tailed high dimensional data. For this purppose, a new Robust Adaptive Lasso (RAL) method is proposed which is based on pearson residuals weighting scheme. The weight function determines the compatibility of each observations and downweight it if they are inconsistent with the assumed model. It is observed that RAL estimator can correctly select the covariates with non-zero coefficients and can estimate parameters, simultaneously, not only in the presence of influential observations, but also in the presence of high multicolliearity. We also discuss the model selection oracle property and the asymptotic normality of the RAL. Simulations findings and real data examples also demonstrate the better performance of the proposed penalized regression approach. [ABSTRACT FROM AUTHOR]

In this study, we address the problem of noisy image super-resolution. Noisy low resolution (LR) image is always obtained in applications, while most of the existing algorithms assume that the LR image is noise-free. As to this situation, we present an algorithm for noisy image super-resolution which can achieve simultaneously image super-resolution and denoising. And in the training stage of our method, LR example images are noise-free. For different input LR images, even if the noise variance varies, the dictionary pair does not need to be retrained. For the input LR image patch, the corresponding high resolution (HR) image patch is reconstructed through weighted average of similar HR example patches. To reduce computational cost, we use the atoms of learned sparse dictionary as the examples instead of original example patches. We proposed a distance penalty model for calculating the weight, which can complete a second selection on similar atoms at the same time. Moreover, LR example patches removed mean pixel value are also used to learn dictionary rather than just their gradient features. Based on this, we can reconstruct initial estimated HR image and denoised LR image. Combined with iterative back projection, the two reconstructed images are applied to obtain final estimated HR image. We validate our algorithm on natural images and compared with the previously reported algorithms. Experimental results show that our proposed method performs better noise robustness. [ABSTRACT FROM AUTHOR]

The Single Variable Exchange algorithm is based on a simple idea; any model that can be simulated can be estimated by producing draws from the posterior distribution. We build on this simple idea by framing the Exchange algorithm as a mixture of Metropolis transition kernels and propose strategies that automatically select the more efficient transition kernels. In this manner we achieve significant improvements in convergence rate and autocorrelation of the Markov chain without relying on more than being able to simulate from the model. Our focus will be on statistical models in the Exponential Family and use two simple models from educational measurement to illustrate the contribution. [ABSTRACT FROM AUTHOR]

We describe a method of quantifying the effect of Questionable Research Practices (QRPs) on the results of meta-analyses. As an example we simulated a meta-analysis of a controversial telepathy protocol to assess the extent to which these experimental results could be explained by QRPs. Our simulations used the same numbers of studies and trials as the original meta-analysis and the frequencies with which various QRPs were applied in the simulated experiments were based on surveys of experimental psychologists. Results of both the meta-analysis and simulations were characterized by 4 metrics, two describing the trial and mean experiment hit rates (HR) of around 31%, where 25% is expected by chance, one the correlation between sample-size and hit-rate, and one the complete P-value distribution of the database. A genetic algorithm optimized the parameters describing the QRPs, and the fitness of the simulated meta-analysis was defined as the sum of the squares of Z-scores for the 4 metrics. Assuming no anomalous effect a good fit to the empirical meta-analysis was found only by using QRPs with unrealistic parameter-values. Restricting the parameter space to ranges observed in studies of QRP occurrence, under the untested assumption that parapsychologists use comparable QRPs, the fit to the published Ganzfeld meta-analysis with no anomalous effect was poor. We allowed for a real anomalous effect, be it unidentified QRPs or a paranormal effect, where the HR ranged from 25% (chance) to 31%. With an anomalous HR of 27% the fitness became F = 1.8 (p = 0.47 where F = 0 is a perfect fit). We conclude that the very significant probability cited by the Ganzfeld meta-analysis is likely inflated by QRPs, though results are still significant (p = 0.003) with QRPs. Our study demonstrates that quantitative simulations of QRPs can assess their impact. Since meta-analyses in general might be polluted by QRPs, this method has wide applicability outside the domain of experimental parapsychology. [ABSTRACT FROM AUTHOR]

Four of the most common limitations of the many available clustering methods are: i) the lack of a proper strategy to deal with outliers; ii) the need for a good a priori estimate of the number of clusters to obtain reasonable results; iii) the lack of a method able to detect when partitioning of a specific data set is not appropriate; and iv) the dependence of the result on the initialization. Here we propose Cross-clustering (CC), a partial clustering algorithm that overcomes these four limitations by combining the principles of two well established hierarchical clustering algorithms: Ward’s minimum variance and Complete-linkage. We validated CC by comparing it with a number of existing clustering methods, including Ward’s and Complete-linkage. We show on both simulated and real datasets, that CC performs better than the other methods in terms of: the identification of the correct number of clusters, the identification of outliers, and the determination of real cluster memberships. We used CC to cluster samples in order to identify disease subtypes, and on gene profiles, in order to determine groups of genes with the same behavior. Results obtained on a non-biological dataset show that the method is general enough to be successfully used in such diverse applications. The algorithm has been implemented in the statistical language R and is freely available from the CRAN contributed packages repository. [ABSTRACT FROM AUTHOR]