Model Selection in SVMs Using Differential Evolution

To improve the performance of classification using Support Vector Machines (SVMs) while reducing the model selection time, this paper introduces Differential Evolution, a heuristic method for model selection in two-class SVMs with a RBF kernel. The model selection method and related tuning algorithm are both presented. Experimental results from application to a selection of benchmark datasets for SVMs show that this method can produce an optimized classification in less time and with higher accuracy than a classical grid search. Comparison with a Particle Swarm Optimization (PSO) based alternative is also included.

Differential evolution combined with clonal selection for dynamic economic dispatch

Dynamic economic load dispatch (DELD) is one of the most important steps in power system operation. Various optimisation algorithms for solving the problem have been developed; however, due to the non-convex characteristics and large dimensionality of the problem, it is necessary to explore new methods to further improve the dispatch results and minimise the costs. This article proposes a hybrid differential evolution (DE) algorithm, namely clonal selection-based differential evolution (CSDE), to solve the problem. CSDE is an artificial intelligence technique that can be applied to complex optimisation problems which are for example nonlinear, large scale, non-convex and discontinuous. This hybrid algorithm combines the clonal selection algorithm (CSA) as the local search technique to update the best individual in the population, which enhances the diversity of the solutions and prevents premature convergence in DE. Furthermore, we investigate four mutation operations which are used in CSA as the hyper-mutation operations. Finally, an efficient solution repair method is designed for DELD to satisfy the complicated equality and inequality constraints of the power system to guarantee the feasibility of the solutions. Two benchmark power systems are used to evaluate the performance of the proposed method. The experimental results show that the proposed CSDE/best/1 approach significantly outperforms nine other variants of CSDE and DE, as well as most other published methods, in terms of the quality of the solution and the convergence characteristics.

A biogeography-based optimization algorithm with mutation strategies for model parameter estimation of solar and fuel cells

Mathematical models are useful tools for simulation, evaluation, optimal operation and control of solar cells and proton exchange membrane fuel cells (PEMFCs). To identify the model parameters of these two type of cells efficiently, a biogeography-based optimization algorithm with mutation strategies (BBO-M) is proposed. The BBO-M uses the structure of biogeography-based optimization algorithm (BBO), and both the mutation motivated from the differential evolution (DE) algorithm and the chaos theory are incorporated into the BBO structure for improving the global searching capability of the algorithm. Numerical experiments have been conducted on ten benchmark functions with 50 dimensions, and the results show that BBO-M can produce solutions of high quality and has fast convergence rate. Then, the proposed BBO-M is applied to the model parameter estimation of the two type of cells. The experimental results clearly demonstrate the power of the proposed BBO-M in estimating model parameters of both solar and fuel cells.

Low-cost Process monitoring for polymer extrusion

Polymer extrusion is regarded as an energy-intensive production process, and the real-time monitoring of both energy consumption and melt quality has become necessary to meet new carbon regulations and survive in the highly competitive plastics market. The use of a power meter is a simple and easy way to monitor energy, but the cost can sometimes be high. On the other hand, viscosity is regarded as one of the key indicators of melt quality in the polymer extrusion process. Unfortunately, viscosity cannot be measured directly using current sensory technology. The employment of on-line, in-line or off-line rheometers is sometimes useful, but these instruments either involve signal delay or cause flow restrictions to the extrusion process, which is obviously not suitable for real-time monitoring and control in practice. In this paper, simple and accurate real-time energy monitoring methods are developed. This is achieved by looking inside the controller, and using control variables to calculate the power consumption. For viscosity monitoring, a ‘soft-sensor’ approach based on an RBF neural network model is developed. The model is obtained through a two-stage selection and differential evolution, enabling compact and accurate solutions for viscosity monitoring. The proposed monitoring methods were tested and validated on a Killion KTS-100 extruder, and the experimental results show high accuracy compared with traditional monitoring approaches.

Characterization of the Kepler-101 planetary system with HARPS-N. A hot super-Neptune with an Earth-sized low-mass companion

We characterize the planetary system Kepler-101 by performing a combined differential evolution Markov chain Monte Carlo analysisof Kepler data and forty radial velocities obtained with the HARPS-N spectrograph. This system was previously validated and iscomposed of a hot super-Neptune, Kepler-101b, and an Earth-sized planet, Kepler-101c. These two planets orbit the slightly evolvedand metal-rich G-type star in 3.49 and 6.03 days, respectively. With mass Mp = 51.1+5.1−4.7 M⊕, radius Rp = 5.77+0.85−0.79 R⊕, and density ρp = 1.45+0.83 −0.48 g cm−3, Kepler-101b is the first fully characterized super-Neptune, and its density suggests that heavy elements makeup a significant fraction of its interior; more than 60% of its total mass. Kepler-101c has a radius of 1.25+0.19−0.17 R⊕, which implies theabsence of any H/He envelope, but its mass could not be determined because of the relative faintness of the parent star for highly precise radial-velocity measurements (Kp = 13.8) and the limited number of radial velocities. The 1σ upper limit, Mp < 3.8 M⊕, excludes a pure iron composition with a probability of 68.3%. The architecture of the planetary system Kepler-101 − containing aclose-in giant planet and an outer Earth-sized planet with a period ratio slightly larger than the 3:2 resonance − is certainly of interest for scenarios of planet formation and evolution. This system does not follow the previously reported trend that the larger planet has the longer period in the majority of Kepler systems of planet pairs with at least one Neptune-sized or larger planet.

Parsing parallel evolution:Ecological divergence and differential gene expression in the adaptive radiations of thick-lipped Midas cichlid fishes from Nicaragua

The study of parallel evolution facilitates the discovery of common rules of diversification. Here, we examine the repeated evolution of thick lips in Midas cichlid fishes (the Amphilophus citrinellus species complex) - from two Great Lakes and two crater lakes in Nicaragua - to assess whether similar changes in ecology, phenotypic trophic traits and gene expression accompany parallel trait evolution. Using next-generation sequencing technology, we characterize transcriptome-wide differential gene expression in the lips of wild-caught sympatric thick- and thin-lipped cichlids from all four instances of repeated thick-lip evolution. Six genes (apolipoprotein D, myelin-associated glycoprotein precursor, four-and-a-half LIM domain protein 2, calpain-9, GTPase IMAP family member 8-like and one hypothetical protein) are significantly underexpressed in the thick-lipped morph across all four lakes. However, other aspects of lips' gene expression in sympatric morphs differ in a lake-specific pattern, including the magnitude of differentially expressed genes (97-510). Generally, fewer genes are differentially expressed among morphs in the younger crater lakes than in those from the older Great Lakes. Body shape, lower pharyngeal jaw size and shape, and stable isotopes (dC and dN) differ between all sympatric morphs, with the greatest differentiation in the Great Lake Nicaragua. Some ecological traits evolve in parallel (those related to foraging ecology; e.g. lip size, body and head shape) but others, somewhat surprisingly, do not (those related to diet and food processing; e.g. jaw size and shape, stable isotopes). Taken together, this case of parallelism among thick- and thin-lipped cichlids shows a mosaic pattern of parallel and nonparallel evolution. © 2012 Blackwell Publishing Ltd.

Distribution-based adaptive bounding genetic algorithm for continuous optimisation problems

A new search-space-updating technique for genetic algorithms is proposed for continuous optimisation problems. Other than gradually reducing the search space during the evolution process with a fixed reduction rate set ‘a priori’, the upper and the lower boundaries for each variable in the objective function are dynamically adjusted based on its distribution statistics. To test the effectiveness, the technique is applied to a number of benchmark optimisation problems in comparison with three other techniques, namely the genetic algorithms with parameter space size adjustment (GAPSSA) technique [A.B. Djurišic, Elite genetic algorithms with adaptive mutations for solving continuous optimization problems – application to modeling of the optical constants of solids, Optics Communications 151 (1998) 147–159], successive zooming genetic algorithm (SZGA) [Y. Kwon, S. Kwon, S. Jin, J. Kim, Convergence enhanced genetic algorithm with successive zooming method for solving continuous optimization problems, Computers and Structures 81 (2003) 1715–1725] and a simple GA. The tests show that for well-posed problems, existing search space updating techniques perform well in terms of convergence speed and solution precision however, for some ill-posed problems these techniques are statistically inferior to a simple GA. All the tests show that the proposed new search space update technique is statistically superior to its counterparts.

Differential osmoregulatory capabilities of common spiny mice (Acomys cahirinus) from adjacent microhabitats

The osmoregulatory function of common spiny mice Acomys cahirinus living on opposite slopes of the lower Nahal Oren ('Evolution Canyon') on mount Carmel, Israel, was investigated by increasing the salinity of the water source whilst maintaining a high-protein diet. The southern-facing slope (SFS) of this canyon differs from the northern-facing slope (NFS) as it receives considerably more solar radiation and consequently forms a more xeric, sparsely vegetated habitat. During the summer, mice living on the two opposite slopes significantly differed in their urine osmolality, which also increased significantly as dietary salinity increased. Offspring of wild-captured mice, born in captivity, and examined during the winter, continued to show a difference in osmoregulatory function depending on the slope of origin. However, they differed from wild-captured mice, as they did not respond to the increase in dietary salinity by increasing the concentration of their urine, but rather by increasing the volume of urine produced. This study shows that A. cahirinus occupying different microhabitats may exhibit differences in their ability to concentrate urine and thus in their ability to withstand xeric conditions. We suggest that they may also differ genetically, as offspring from the NFS and SFS retain physiological differences, but further studies will be needed to confirm this hypothesis.

Noise resilience and entanglement evolution in two nonequivalent classes of quantum algorithms

The speedup provided by quantum algorithms with respect to their classical counterparts is at the origin of scientific interest in quantum computation. However, the fundamental reasons for such a speedup are not yet completely understood and deserve further attention. In this context, the classical simulation of quantum algorithms is a useful tool that can help us in gaining insight. Starting from the study of general conditions for classical simulation, we highlight several important differences between two nonequivalent classes of quantum algorithms. We investigate their performance under realistic conditions by quantitatively studying their resilience with respect to static noise. This latter refers to errors affecting the initial preparation of the register used to run an algorithm. We also compare the evolution of the entanglement involved in the different computational processes.

Segmentation of optic disc in retinal images using an improved gradient vector flow algorithm

Image segmentation plays an important role in the analysis of retinal images as the extraction of the optic disk provides important cues for accurate diagnosis of various retinopathic diseases. In recent years, gradient vector flow (GVF) based algorithms have been used successfully to successfully segment a variety of medical imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods can lead to less accurate segmentation results in certain cases. In this paper, we propose the use of a new mean shift-based GVF segmentation algorithm that drives the internal/external energies towards the correct direction. The proposed method incorporates a mean shift operation within the standard GVF cost function to arrive at a more accurate segmentation. Experimental results on a large dataset of retinal images demonstrate that the presented method optimally detects the border of the optic disc.

Potential roles for differential body size and microhabitat complexity in mediating biotic interactions within invasive freshwater amphipod assemblages

Cannibalism and intraguild predation (IGP) are common amongst freshwater amphipod crustacean aswsemblages, particularly between individuals of different body size, with IGP of smaller by larger species. The decline of Gammarus tigrinus Populations in mainland Europe has been accompanied by the arrival of the Ponto-Caspian invader Dikerogammarus villosus and previous studies have implicated IGP of G. tigrinus by the larger D. villosus as the principal driving force in this replacement. We examined how factors such as microhabitat and body size may mediate both cannibalism within G. tigrinus populations and IGP by D. villosus and thus contribute to field patterns of coexistence and exclusion. A field Survey of an invaded Dutch fake indicated that G. tigrinus and D. villosus differed in distribution. with D. villosus being the numerically dominant amphipod (80-96 %) on the rocky boulder Substrate of the shoreline and G. tigrinus being the dominant amphipod (100 %) in the crushed shell/sand matrix immediately adjacent to this. Laboratory microcosm experiments indicated that G. tigrinus cannibalism, particularly of smaller by larger size classes, may be common. In addition, although D. villosus predation of all G. tigrinus size classes was extreme, the smallest size classes Suffered the highest predation. Indeed, when exposed to D. villosus, predation of larger G. tigrinus was lowest when smaller G. tigrinus were also present. Increasing microhabitat complexity from a simple bare substrate littered with Dreissena polymorpha zebra mussels to a Crushed shell/sand matrix significantly reduced both cannibalism and IGP. Our Study emphasizes the need to consider both life history stages and habitat template, when considering the impacts of biotic interactions and it also emphasizes that complex, interacting factors may be mediating the range expansion of D. villosus.

Interactions between invasive and native crustaceans: differential functional responses of intraguild predators towards juvenile hetero-specifics

Intraguild predation (IGP) between invasive and native species can lead to species exclusions or co-existence, dependent on the direction and strength of the interaction. Recently, derivation of 'functional responses' has been identified as a means of comparing the community impacts of invasive and native species. Here, we employ a novel use of this functional response methodology to evaluate any IGP asymmetries between the invasive Ponto-Caspian amphipod Echinogammarus ischnus and the North American native Gammarus fasciatus. The direction and magnitude of intraguild predation of adult males on hetero-specific adult females has previously been shown to reverse across a water conductivity gradient. This partially explains field patterns, but does not predict the co-existence of the two species observed in many habitats and locations. Here, we compared intraguild predation by both species on each other's juveniles in high- and low- conductivity water. G. fasciatus has a higher type II functional response towards E. ischnus juveniles compared to the reciprocal interaction. Conductivity did not influence the predation rate on juveniles of either E. ischnus or G. fasciatus. Thus, the male/female IGP advantage to the native G. fasciatus in low conductivity water is compounded by a juvenile IGP asymmetry, which also counteracts the male/female IGP advantage to E. ischnus in high conductivity waters, helping to explain field patterns of exclusion and co-existence. Thus, complex asymmetries in mutual IGP associated with inherent species differences, environmental modulation, and life-history effects can help us understand and predict the population and community level outcomes of species invasions.