SOP: Parallel surrogate global optimization with Pareto center selection for computationally expensive single objective problems

This paper presents a parallel surrogate-based global optimization method for computationally expensive objective functions that is more effective for larger numbers of processors. To reach this goal, we integrated concepts from multi-objective optimization and tabu search into, single objective, surrogate optimization. Our proposed derivative-free algorithm, called SOP, uses non-dominated sorting of points for which the expensive function has been previously evaluated. The two objectives are the expensive function value of the point and the minimum distance of the point to previously evaluated points. Based on the results of non-dominated sorting, P points from the sorted fronts are selected as centers from which many candidate points are generated by random perturbations. Based on surrogate approximation, the best candidate point is subsequently selected for expensive evaluation for each of the P centers, with simultaneous computation on P processors. Centers that previously did not generate good solutions are tabu with a given tenure. We show almost sure convergence of this algorithm under some conditions. The performance of SOP is compared with two RBF based methods. The test results show that SOP is an efficient method that can reduce time required to find a good near optimal solution. In a number of cases the efficiency of SOP is so good that SOP with 8 processors found an accurate answer in less wall-clock time than the other algorithms did with 32 processors.

Quantifying uncertainty on Pareto fronts with Gaussian process conditional simulations

Multi-objective optimization algorithms aim at finding Pareto-optimal solutions. Recovering Pareto fronts or Pareto sets from a limited number of function evaluations are challenging problems. A popular approach in the case of expensive-to-evaluate functions is to appeal to metamodels. Kriging has been shown efficient as a base for sequential multi-objective optimization, notably through infill sampling criteria balancing exploitation and exploration such as the Expected Hypervolume Improvement. Here we consider Kriging metamodels not only for selecting new points, but as a tool for estimating the whole Pareto front and quantifying how much uncertainty remains on it at any stage of Kriging-based multi-objective optimization algorithms. Our approach relies on the Gaussian process interpretation of Kriging, and bases upon conditional simulations. Using concepts from random set theory, we propose to adapt the Vorob’ev expectation and deviation to capture the variability of the set of non-dominated points. Numerical experiments illustrate the potential of the proposed workflow, and it is shown on examples how Gaussian process simulations and the estimated Vorob’ev deviation can be used to monitor the ability of Kriging-based multi-objective optimization algorithms to accurately learn the Pareto front.

A multifactorial analysis of obesity as CVD risk factor: use of neural network based methods in a nutrigenetics context

Obesity is a multifactorial trait, which comprises an independent risk factor for cardiovascular disease (CVD). The aim of the current work is to study the complex etiology beneath obesity and identify genetic variations and/or factors related to nutrition that contribute to its variability. To this end, a set of more than 2300 white subjects who participated in a nutrigenetics study was used. For each subject a total of 63 factors describing genetic variants related to CVD (24 in total), gender, and nutrition (38 in total), e.g. average daily intake in calories and cholesterol, were measured. Each subject was categorized according to body mass index (BMI) as normal (BMI ≤ 25) or overweight (BMI > 25). Two artificial neural network (ANN) based methods were designed and used towards the analysis of the available data. These corresponded to i) a multi-layer feed-forward ANN combined with a parameter decreasing method (PDM-ANN), and ii) a multi-layer feed-forward ANN trained by a hybrid method (GA-ANN) which combines genetic algorithms and the popular back-propagation training algorithm.

Simulating the evolution of a clonal trait in plants with sexual and vegetative reproduction

Aims Phenotypic optimality models neglect genetics. However, especially when heterozygous genotypes ire fittest, evolving allele, genotype and phenotype frequencies may not correspond to predicted optima. This was not previously addressed for organisms with complex life histories. Methods Therefore, we modelled the evolution of a fitness-relevant trait of clonal plants, stolon internode length. We explored the likely case of air asymmetric unimodal fitness profile with three model types. In constant selection models (CSMs), which are gametic, but not spatially explicit, evolving allele frequencies in the one-locus and five-loci cases did not correspond to optimum stolon internode length predicted by the spatially explicit, but not gametic, phenotypic model. This deviation was due to the asymmetry of the fitness profile. Gametic, spatially explicit individual-based (SEIB) modeling allowed us relaxing the CSM assumptions of constant selection with exclusively sexual reproduction. Important findings For entirely vegetative or sexual reproduction, predictions. of the gametic SEIB model were close to the ones of spatially explicit CSMs gametic phenotypic models, hut for mixed modes of reproduction they appoximated those of gametic, not spatially explicit CSMs. Thus, in contrast to gametic SEIB models, phenotypic models and, especially for few loci, also CSMs can be very misleading. We conclude that the evolution of trails governed by few quantitative trait loci appears hardly predictable by simple models, that genetic algorithms aiming at technical optimization may actually, miss the optimum and that selection may lead to loci with smaller effects, in derived compared with ancestral lines.

Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks

Quantitative characterisation of carotid atherosclerosis and classification into symptomatic or asymptomatic is crucial in planning optimal treatment of atheromatous plaque. The computer-aided diagnosis (CAD) system described in this paper can analyse ultrasound (US) images of carotid artery and classify them into symptomatic or asymptomatic based on their echogenicity characteristics. The CAD system consists of three modules: a) the feature extraction module, where first-order statistical (FOS) features and Laws' texture energy can be estimated, b) the dimensionality reduction module, where the number of features can be reduced using analysis of variance (ANOVA), and c) the classifier module consisting of a neural network (NN) trained by a novel hybrid method based on genetic algorithms (GAs) along with the back propagation algorithm. The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance. The performance is measured by the accuracy, sensitivity, specificity and the area under the receiver-operating characteristic (ROC) curve. The CAD design and development is based on images from 54 symptomatic and 54 asymptomatic plaques. This study demonstrates the ability of a CAD system based on US image analysis and a hybrid trained NN to identify atheromatous plaques at high risk of stroke.

A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease." The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.

Multi-Model Data Fusion to Improve an Early Warning System for Hypo-/Hyperglycemic Events

Correct predictions of future blood glucose levels in individuals with Type 1 Diabetes (T1D) can be used to provide early warning of upcoming hypo-/hyperglycemic events and thus to improve the patient's safety. To increase prediction accuracy and efficiency, various approaches have been proposed which combine multiple predictors to produce superior results compared to single predictors. Three methods for model fusion are presented and comparatively assessed. Data from 23 T1D subjects under sensor-augmented pump (SAP) therapy were used in two adaptive data-driven models (an autoregressive model with output correction - cARX, and a recurrent neural network - RNN). Data fusion techniques based on i) Dempster-Shafer Evidential Theory (DST), ii) Genetic Algorithms (GA), and iii) Genetic Programming (GP) were used to merge the complimentary performances of the prediction models. The fused output is used in a warning algorithm to issue alarms of upcoming hypo-/hyperglycemic events. The fusion schemes showed improved performance with lower root mean square errors, lower time lags, and higher correlation. In the warning algorithm, median daily false alarms (DFA) of 0.25%, and 100% correct alarms (CA) were obtained for both event types. The detection times (DT) before occurrence of events were 13.0 and 12.1 min respectively for hypo-/hyperglycemic events. Compared to the cARX and RNN models, and a linear fusion of the two, the proposed fusion schemes represents a significant improvement.

Gradient-domain Path Tracing

We introduce gradient-domain rendering for Monte Carlo image synthesis.While previous gradient-domain Metropolis Light Transport sought to distribute more samples in areas of high gradients, we show, in contrast, that estimating image gradients is also possible using standard (non-Metropolis) Monte Carlo algorithms, and furthermore, that even without changing the sample distribution, this often leads to significant error reduction. This broadens the applicability of gradient rendering considerably. To gain insight into the conditions under which gradient-domain sampling is beneficial, we present a frequency analysis that compares Monte Carlo sampling of gradients followed by Poisson reconstruction to traditional Monte Carlo sampling. Finally, we describe Gradient-Domain Path Tracing (G-PT), a relatively simple modification of the standard path tracing algorithm that can yield far superior results.

Methods for assessment of keel bone damage in poultry

Keel bone damage (KBD) is a critical issue facing the laying hen industry today as a result of the likely pain leading to compromised welfare and the potential for reduced productivity. Recent reports suggest that damage, while highly variable and likely dependent on a host of factors, extends to all systems (including battery cages, furnished cages, and non-cage systems), genetic lines, and management styles. Despite the extent of the problem, the research community remains uncertain as to the causes and influencing factors of KBD. Although progress has been made investigating these factors, the overall effort is hindered by several issues related to the assessment of KBD, including quality and variation in the methods used between research groups. These issues prevent effective comparison of studies, as well as difficulties in identifying the presence of damage leading to poor accuracy and reliability. The current manuscript seeks to resolve these issues by offering precise definitions for types of KBD, reviewing methods for assessment, and providing recommendations that can improve the accuracy and reliability of those assessments.

Causes of keel bone damage and their solutions in laying hens

Keel bone damage (KBD) is a critical issue facing the contemporary laying hen industry due to the likely pain leading to compromised welfare and reduced productivity. Recent reports suggest that KBD, while highly variable and likely dependent on a host of factors, extends to all housing systems (including traditional battery cages, furnished cages and non-cage systems), genetic lines, and management styles. Despite the extent of the problem, the research community remains uncertain as to the causes and influencing factors of KBD. To combat these issues, the current review was produced following discussions from the 1st International Keel Bone Damage Workshop held in Switzerland in April 2014. This exercise sought to assess current knowledge, foster novel collaborations, propose unique methodologies and highlight the key areas where innovative research is needed. The following paper is based on the content of those discussions and presents nine recommendations for future research efforts.

Vitamin D time profile based on the contribution of non-genetic and genetic factors in HIV-infected individuals of European ancestry

BACKGROUND Vitamin D deficiency is prevalent in HIV-infected individuals and vitamin D supplementation is proposed according to standard care. This study aimed at characterizing the kinetics of 25(OH)D in a cohort of HIV-infected individuals of European ancestry to better define the influence of genetic and non-genetic factors on 25(OH)D levels. These data were used for the optimization of vitamin D supplementation in order to reach therapeutic targets. METHODS 1,397 25(OH)D plasma levels and relevant clinical information were collected in 664 participants during medical routine follow up visits. They were genotyped for 7 SNPs in 4 genes known to be associated with 25(OH)D levels. 25(OH)D concentrations were analyzed using a population pharmacokinetic approach. The percentage of individuals with 25(OH)D concentrations within the recommended range of 20-40ng/ml during 12 months of follow up and several dosage regimens were evaluated by simulation. RESULTS A one-compartment model with linear absorption and elimination was used to describe 25(OH)D pharmacokinetics, while integrating endogenous baseline plasma concentrations. Covariate analyses confirmed the effect of seasonality, body mass index, smoking habits, the analytical method, darunavir/r and the genetic variant in GC (rs2282679) on 25(OH)D concentrations. 11% of the interindividual variability in 25(OH)D levels was explained by seasonality and other non-genetic covariates and 1% by genetics. The optimal supplementation for severe vitamin D deficient patients was 300000 IU two times per year. CONCLUSIONS This analysis allowed identifying factors associated with 25(OH)D plasma levels in HIV-infected individuals. Improvement of dosage regimen and timing of vitamin D supplementation is proposed based on those results.