Genetic Algorithm Selection Research Articles

Eccentricity Optimization of NGB System by using Multi-Objective Genetic Algorithm

In this study, a new method for designing a particular braced system by using multi-objective genetic algorithm is proposed. This type of braced system, which is called non-geometric braced system are mostly used in seismic areas and it allows architects to have more openings in the panels. Non-straight diagonal member of this system introduces eccentricity and it is connected to the corner of the frame by a third member. In designing this system, designers often use trial and error method to locate the connection point of the brace elements by considering various parameters which affect the design such as opening and frame dimensions, cross section areas of brace elements and the location of brace element connection. Hence, finding the best connection point with maximum stiffness and minimum weight of brace elements with conventional methods is not trivial. In this study, a multi-object genetic algorithm is proposed in determining the best selection for connection point and also the brace elements' cross section area proportions which is the key rule in determining the stiffness of the system. Boundary equations are set by introducing feasible area to avoid improper individuals followed by utilization of some operators such as selection, mutation, crossover and elite genetic algorithm. Based on the plain aggregate approaches for transforming the objective vector in scalar, some modifications are proposed to assist designers in making decision on prioritizing between the frame stiffness and brace frame weight in their design.

A QoS Driven Web Service Composition Method Based on ESGA (Elitist Selection Genetic Algorithm) with an Improved Initial Population Selection Strategy

With more and more web services being applied, the quality of service (QoS) becomes an important criterion in a service selection. We propose a UDDI process with QoS extension to support quality requests. Service providers can send functional and QoS information to the UDDI registry. As a component of the UDDI registry, the QoS calculator calculates the QoS value of each service to decide the optimal service and send the information back to the UDDI registry. After receiving the requestor's feedback, the QoS calculator re-calculates QoS of the service. In a service composition, component services and the composed service should satisfy local and global restrictions respectively. The QoS of component services aggregate to QoS of the composed service according to an aggregation rule. The QoS parameters may conflict with each other, so this problem is actually a multi-objective optimization. A service selection can be seen as a path formation and each node of the path is a service class. A genetic algorithm can be used to solve complicated global optimization problems. It is proved that a simplex genetic algorithm cannot converge to optimal global solution but the elitist selection genetic algorithm (ESGA) can. So we use ESGA to solve this problem. We use integer encoding as the encoding rule. A composed service can be seen as a chromosome and a gene is an integer that represents a service number in its service class. We use an initial population selection strategy instead of the random initial population creation method. In the strategy, if the fitness of a new composed service is worse than the average fitness of the selected composed services, it should be abandoned, otherwise it should be kept. We coordinate these objectives by assigning a weight to each parameter and the fitness function is the weighted sum of QoS parameters. In the stage of genetic operation, the penalty function is subtracted from the fitness of the composed service if it does not satisfy the restrictions. We use the roulette wheel selection method, single point crossover operator, and uniform mutation operator as genetic operators. It is shown that this method has better performance than the method using ESGA through an experiment.

The anti-fibrillogenic activity of tetracyclines on PrP 106–126: a 3D-QSAR study

There is evidence that Tetracyclines are potentially useful drugs to treat prion disease, the fatal neurodegenerative disease in which cellular prion proteins change in conformation to become a disease-specific species (PrP(Sc)). Based on an in vitro anti-fibrillogenesis test, and using the peptide PrP106-126 in the presence of tetracycline and 14 derivatives, we carried out a three-dimensional quantitative structure-activity relationship (3D-QSAR) study to investigate the stereoelectronic features required for anti-fibrillogenic activity. A preliminary variable reduction technique was used to search for grid points where statistical indexes of interaction potential distributions present local maximum (or minimum) values. Variable selection genetic algorithms were then used to search for the best 3D-QSAR models. A 6-variable model showed the best predictability of the anti-fibrillogenic activity that highlighted the best tetracycline substitution patterns: hydroxyl group presence in positions 5 and 6, electrodonor substituents on the aromatic D-ring, alkylamine substituent at the amidic group in position 2 and non-epi configuration of the NMe2 group.

Compensation for the mutual coupling effect in uniform circular arrays for 2D DOA estimations employing the maximum likelihood technique

An effective compensation method for the mutual coupling effect in uniform circular arrays (UCAs) employed for two-dimensional (2D) direction-of-arrival (DOA) estimations is introduced. A new 2D DOA searching algorithm using the maximum likelihood technique optimized by the emperor selective genetic algorithm (ML-EMSGA) is introduced for use with UCAs. This method circumvents the difficulty of dealing with coherent signals in 2D DOA estimations. ML-EMSGA is less computationally demanding than the maximum likelihood method (MLM) and statistically more efficient. Our study shows that ML-EMSGA can be effectively combined with the proposed compensation method, which is based on the introduction of a new mutual impedance, to give very accurate and robust 2D DOA estimation results. The structure of mutual impedance matrix for UCAs under the compensation method is fully explained. The theory of the ML-EMSGA for the UCAs is formulated. Computer simulation examples on several synthetic scenarios are presented to demonstrate the effectiveness of the mutual coupling compensation method and the superior performance of the ML-EMSGA for UCAs.

Noninvasive metabolomic profiling of embryo culture media using Raman and near-infrared spectroscopy correlates with reproductive potential of embryos in women undergoing in vitro fertilization

To determine if metabolomic profiling of embryo culture media correlates with reproductive potential of individual embryos. Prospective study. An academic and a private assisted reproduction program; a university research center. Women undergoing assisted reproduction treatment. Sixty-nine spent media samples from 30 patients with known outcome (0 or 100% sustained implantation rates) were individually collected after embryo transfer on day 3 and were evaluated using Raman and/or near-infrared spectroscopy. The spectra obtained from each instrument were separately analyzed using a wavelength selective genetic algorithm to determine regions predictive of pregnancy outcome. Viability indices reflective of reproductive potential were calculated for each sample. To avoid random correlations, a leave-one-out cross-validation was used. Sensitivity and specificity of predicting viability (described as implantation and delivery) were calculated. Metabolomic profile of culture media and embryo viability. Viability indices calculated by Raman or near-infrared spectroscopy were higher for embryos that implanted and resulted in a delivery, compared with those that failed to implant. Raman spectroscopy predicted viability of individual embryos with a sensitivity of 86% and a specificity of 76.5%; near-infrared provided a sensitivity of 75% and a specificity of 83.3%. Rapid, noninvasive metabolomic profiling of human embryo culture media using Raman or near-infrared spectroscopy combined with bioinformatics correlates with pregnancy outcome.

Non-invasive method for embryo selection in single embryo transfer (SET) using metabolomic profiling (MetPro) of oxidative metabolism (OM)

SET is an effective method to minimize risks of multiple pregnancies in IVF. Since morphology has limited predictive value, new selection tools are needed to ensure success rates are maintained. Previous studies have shown that non-invasive MetPro may be useful in predicting reproductive potential of embryos. The purpose of this study was to investigate the efficiency of MetPro of biomarkers of OM in patients undergoing SET compared to morphological selection. Prospective study. 274 patients scheduled for IVF with SET received standard gonadotropin stimulation protocols with agonist down-regulation. Embryos were cultured individually in 25 μl media drops (HTF, Cambrex, Belgium and 10% GPO) alongside embryo-free media drops as controls. Embryos were selected for transfer by strict morphological criteria. After transfer, spent media were immediately frozen (−196°C). Pregnancy was defined by positive fetal cardiac activity (FCA) at 12 weeks. 7 μl media samples were analysed by Near Infrared (NIR) spectroscopy; analysis time was <1 min. OM biomarkers of ROH, -SH, C = C, -CH, -OH, and -NH groups were identified yielding unique metabolomic profiles that were quantified using a wavelength selective genetic algorithm, proprietary bioinformatics and leave-one out cross-validation, in conjunction with logistical regression, to create a relative “embryo viability score” that correlated to pregnancy outcomes. The resulting metabolomics data were compared to morphological assesment and pregnancy outcomes. NIR spectral analysis of discarded culture media samples produced unique metabolomic profiles of OM that correlated to an embryo's reproductive potential as determined by FCA. Differences in metabolomic profiles between FCA+ and FCA− groups were statistically significant (>95% confidence interval); sensitivity and specificity was 87% and 93%, respectively. Greater than 86% of all embryos transferred were classified as Grade A or B embryos by strict morphological criteria while 27% resulted in an ongoing pregnancy. Conversely, significant numbers of poorer quality embryos (Grade C and D) actually resulted in FCA+ outcomes. MetPro of discarded embryo culture media by NIR was effective in distinguishing between viable and non-viable embryos in SET irrespective of embryo morphology. MetPro targeting biomarkers of OM may provide a strong addition for rapid, non-invasive selection of embryos with high reproductive potential in SET.

Application of genetic algorithm for selection of variables for the BLLS method applied to determination of pesticides and metabolites in wine

A variable selection methodology based on genetic algorithm (GA) was applied in a bilinear least squares model (BLLS) with second-order advantage, in three distinct situations, for determination by HPLC–DAD of the pesticides carbaryl (CBL), methyl thiophanate (TIO), simazin (SIM) and dimethoate (DMT) and the metabolite phthalimide (PTA) in wine. The chromatographic separation was carried out using an isocratic elution with 50:50 (v/v) acetonitrile:water as mobile phase. Preprocessing methods were performed for correcting the chromatographic time shifts, baseline variation and background. The optimization by GA provided a significant reduction of the errors, where for SIM and PTA a decrease of three times the value obtained using all variables, and an improvement in the distribution of them, reducing the observed bias in the results were observed. Comparing the RMSEP of the optimized model with the uncertainty estimates of the reference values it is observed that GA can be a very useful tool in second-order models.

Physicochemical descriptors to discriminate protein–protein interactions in permanent and transient complexes selected by means of machine learning algorithms

Analyzing protein-protein interactions at the atomic level is critical for our understanding of the principles governing the interactions involved in protein-protein recognition. For this purpose, descriptors explaining the nature of different protein-protein complexes are desirable. In this work, the authors introduced Epic Protein Interface Classification as a framework handling the preparation, processing, and analysis of protein-protein complexes for classification with machine learning algorithms. We applied four different machine learning algorithms: Support Vector Machines, C4.5 Decision Trees, K Nearest Neighbors, and Naïve Bayes algorithm in combination with three feature selection methods, Filter (Relief F), Wrapper, and Genetic Algorithms, to extract discriminating features from the protein-protein complexes. To compare protein-protein complexes to each other, the authors represented the physicochemical characteristics of their interfaces in four different ways, using two different atomic contact vectors, DrugScore pair potential vectors and SFCscore descriptor vectors. We classified two different datasets: (A) 172 protein-protein complexes comprising 96 monomers, forming contacts enforced by the crystallographic packing environment (crystal contacts), and 76 biologically functional homodimer complexes; (B) 345 protein-protein complexes containing 147 permanent complexes and 198 transient complexes. We were able to classify up to 94.8% of the packing enforced/functional and up to 93.6% of the permanent/transient complexes correctly. Furthermore, we were able to extract relevant features from the different protein-protein complexes and introduce an approach for scoring the importance of the extracted features.

Genetic Algorithms for Optimal Reservoir Dispatching

The fundamental guidelines for genetic algorithm to optimal reservoir dispatching have been introduced. It is concluded that with three basic generators selection, crossover and mutation genetic algorithm could search the optimum solution or near-optimal solution to a complex water resources problem. Alternative formulation schemes of a GA are considered. The real-value coding is proved significantly faster than binary coding, and can produce better results. Sensitivity of crossover probability and mutation probability are also analyzed in this paper. Results from genetic algorithm with real-value coding are compared with those from other optimal methods. The results demonstrate that a genetic algorithm can be satisfactorily used in optimal reservoir problems, and it has potential in application to complex river systems.

Monitoring complex media fermentations with near‐infrared spectroscopy: Comparison of different variable selection methods

Near-infrared spectroscopy (NIRS) is known to be a suitable technique for rapid fermentation monitoring. Industrial fermentation media are complex, both chemically (ill-defined composition) and physically (multiphase sample matrix), which poses an additional challenge to the development of robust NIRS calibration models. We investigated the use of NIRS for at-line monitoring of the concentration of clavulanic acid during an industrial fermentation. An industrial strain of Streptomyces clavuligerus was cultivated at 200-L scale for the production of clavulanic acid. Partial least squares (PLS) regression was used to develop calibration models between spectral and analytical data. In this work, two different variable selection methods, genetic algorithms (GA) and PLS-bootstrap, were studied and compared with models built using all the spectral variables. Calibration models for clavulanic acid concentration performed well both on internal and external validation. The two variable selection methods improved the predictive ability of the models up to 20%, relative to the calibration model built using the whole spectra.

Sharp asymptotic results for simplified mutation-selection algorithms

We study the asymptotic behavior of a mutation--selection genetic algorithm on the integers with finite population of size $p\ge 1$. The mutation is defined by the steps of a simple random walk and the fitness function is linear. We prove that the normalized population satisfies an invariance principle, that a large-deviations principle holds and that the relative positions converge in law. After $n$ steps, the population is asymptotically around $\sqrt{n}$ times the position at time $1$ of a Bessel process of dimension $2p-1$.

Heterogeneous Selection Genetic Algorithms For Traveling Salesman Problems

This paper proposes a genetic algorithm, called the heterogeneous selection genetic algorithm (HSGA), integrating local and global strategies via family competition and edge similarity, for the traveling salesman problem (TSP). Local strategies include neighbor-join mutation and family competition, and global strategies consist of heterogeneous pairing selection and edge assembly crossover. Based on the mechanisms of preserving and adding edges, the search behaviors of neighbor-join mutation and edge assembly crossover are studied. The proposed method has been implemented and applied to 17 well-lmown TSPs whose numbers of cities range from 101 to 13,509. Experimental results indicate that this approach, although somewhat slower, performs very robustly and is very competitive with other approaches in the best surveys. This approach is able to find the optimum, and the average solution quality is within 0.00048 above the optima of each test problem.

Using weather indices to predict survival of winter wheat in a cool temperate environment.

Seven years of winter survival data for winter wheat ( Triticum aestivum L.) were collected on a loam soil located on the Central Experimental Farm at Ottawa, Ontario (45 degrees 23'N, 75 degrees 43'W). The site was low-lying and subject to frequent winter flooding and ice-sheet formation. Two cultivars, a soft white and a hard red winter wheat, were planted in September. Crop establishment was measured in late fall and the percentage survival was measured in April of the following year. Meteorological data, which were available from the nearby weather site, were used to develop a large set of monthly weather indices that were felt to be important for winter survival. The objective of the study was to use genetic selection algorithms and artificial neural networks to select a subset of critical weather factors and topographic features and to model winter survival. The six weather indices selected were the total rain depth for December (mm), the total rain depth for February (mm), the number of days of the month with snow on the ground for January, the extreme minimum observed daily air temperature for March ( degrees C), the number of days of the month with snow on the ground for March, and the number of days of April with a daily maximum air temperature greater than 0 degrees C. It was found 89% of the variation in winter survival could be explained by these six weather indices, the cultivar, elevation and plot location.

Variable selection in classification of environmental soil samples for partial least square and neural network models

Two variable selection methods were evaluated by comparing their predictions with respect to differentiating among environmental soil samples. The focus of this work is to determine which input variables are most relevant for prediction of soil sources using discriminant partial least square (D-PLS) and back-propagation artificial neural network (BP-ANN) models. The methods investigated were stepwise variable selection method and genetic algorithms (GAs). Microbial community DNA was extracted from 48 environmental soil samples derived from different field crops and soil sources. After amplification of bacterial ribosomal RNA genes by polymerase chain reaction (PCR), the products were separated by gel electrophoresis. Characteristic complex band patterns were obtained, indicating high bacterial diversity. Two hundred and twenty-three DNA band patterns produced in the gels of the soil samples were used in the analysis, after removal of included DNA standard markers. Based on the brightness of the bands, densitometric curves of the selected DNA band pattern were extracted from the gel images. The curves were smoothed using Savitsky–Golay method and scaled to the DNA standard markers. The prediction results based on the two variable selection methods for PLS and ANN models are presented and compared. Both methods gave good results before any variable selection methods, with the ANN being better than D-PLS. The prediction performance of both methods specially the D-PLS were improved by applying the stepwise variable selection and the GA variable selection method. The study also shows that GA variable selection had a significant improvement of the predictive ability than the stepwise variable selection method.

A real-coded genetic algorithm applied to optimum design of a low solidity vaned diffuser for diffuser pump

A numerical procedure for hydrodynamic redesign of the conventional vaned diffuser into the low solidity vaned diffuser by means of a real-coded genetic algorithm with Boltzmann, Tournament and Roulette Wheel selection is presented. In the first part, an investigation on the relative efficiency of the different real-coded genetic algorithm is carried out on a typical mathematical test function. The real-coded genetic algorithm with Boltzmann selection shows the best optimization performance compared to the Tournament and Roulette Wheel selection. In the second part, an approach to redesign the vaned diffuser profile is introduced. Goal of the optimum design is to search the highest static pressure recovery coefficient and low solidity vaned diffuser. The result of the low solidity vaned diffuser optimum design confirms that the efficiency and optimization performance of the real-coded Boltzmann selection genetic algorithm outperforms the other selection methods. A comparison between the designed low solidity vaned diffuser and original vaned diffuser shows that the diffuser pump with the redesigned low solidity vaned diffuser has the higher static pressure recovery and improved total hydrodynamic performance. In addition, the smaller outlet diameter of designed vaned diffuser tends to a more compact size of diffuser pump compared to the original diffuser pump. The obtained results also demonstrate the real-coded Boltzmann selection genetic algorithm is a promising optimization algorithm for centrifugal pumps design.

A combined use of global and local approaches in 3D-QSAR

A new methodology for 3D-QSAR studies, based on the combined use of global and local approaches, is proposed. Information on the whole molecular electrostatic potential distribution is obtained from a global approach and used to build global models, based on the grid weighted holistic invariant molecular (G-WHIM) descriptors, as well as to define an alignment criterion for developing local models. Moreover, a new technique based on local correlation indexes is proposed to perform the variable reduction. Both the global and the local models are obtained by a variable selection genetic algorithms technique. The methodology is applied to a benchmark steroid data set. The molecular electrostatic potential and the experimental binding affinity constants for the corticosteroid-binding globulin are used as variables. The QSAR models obtained compared with those obtained by the CoMFA method show higher predictive ability and give insight into the local molecular features that determine high binding affinity.

Facilities layout design by genetic algorithms

Genetic algorithms (GAs) are a class of adaptive search techniques which have gained popularity in optimisation. In particular they have successfully been applied to NP hard problems such as those resulted in mathematical modelling of facilities design problems. The typical steps required to implement GAs are: encoding of feasible solutions into chromosomes using a representation method, evaluation of fitness function, setting of GAs parameters, selection strategy, genetic operators, and criteria to terminate the process. This paper reports on finding of a research in design of a GA solving the quadratic assignment formulation of equal and unequal-sized facilities layout problems. Comparison is made with solutions of several test problems reported in the literature.

Analysis of Selection Algorithms: A Markov Chain Approach

A Markov chain framework is developed for analyzing a wide variety of selection techniques used in genetic algorithms (GAs) and evolution strategies (ESs). Specifically, we consider linear ranking selection, probabilistic binary tournament selection, deterministic s-ary (s = 3,4, …) tournament selection, fitness-proportionate selection, selection in Whitley's GENITOR, selection in (μ, λ)-ES, selection in (μ + λ)-ES, (μ, λ)-linear ranking selection in GAs, (μ + λ)-linear ranking selection in GAs, and selection in Eshelman's CHC algorithm. The analysis enables us to compare and contrast the various selection algorithms with respect to several performance measures based on the probability of takeover. Our analysis is exact—we do not make any assumptions or approximations. Finite population sizes are considered. Our approach is perfectly general, and following the methods of this paper, it is possible to analyze any selection strategy in evolutionary algorithms.