A simple multimembered evolution strategy to solve constrained optimization problems

This work presents a simple multimembered evolution strategy to solve global nonlinear optimization problems. The approach does not require the use of a penalty function. Instead, it uses a simple diversity mechanism based on allowing infeasible solutions to remain in the population. This technique helps the algorithm to find the global optimum despite reaching reasonably fast the feasible region of the search space. A simple feasibility-based comparison mechanism is used to guide the process toward the feasible region of the search space. Also, the initial stepsize of the evolution strategy is reduced in order to perform a finer search and a combined (discrete/intermediate) panmictic recombination technique improves its exploitation capabilities. The approach was tested with a well-known benchmark. The results obtained are very competitive when comparing the proposed approach against other state-of-the art techniques and its computational cost (measured by the number of fitness function evaluations) is lower than the cost required by the other techniques compared.     

MRMOGA: a new parallel multi‐objective evolutionary algorithm based on the use of multiple resolutions

In this paper, we introduce MRMOGA (Multiple Resolution Multi‐Objective Genetic Algorithm), a new parallel multi‐objective evolutionary algorithm which is based on an injection island approach. This approach is characterized by adopting an encoding of solutions which uses a different resolution for each island. This approach allows us to divide the decision variable space into well‐defined overlapped regions to achieve an efficient use of multiple processors. Also, this approach guarantees that the processors only generate solutions within their assigned region. In order to assess the performance of our proposed approach, we compare it to a parallel version of an algorithm that is representative of the state‐of‐the‐art in the area, using standard test functions and performance measures reported in the specialized literature. Our results indicate that our proposed approach is a viable alternative to solve multi‐objective optimization problems in parallel, particularly when dealing with large search spaces. Copyright © 2006 John Wiley & Sons, Ltd.     

Relation between food habits and nutritional status of preschool children in a rural community

Food habits in regard to the nutritional status of preschool children and their socioeconomic situation were analyzed in this research. The study was carried out in Cuetzalan, State of Puebla; all families were studied and, besides the presence of a preschool child in the home, both father and mother should also be living in the same house. Forty children considered as well nourished and 40 malnourished in the opposite case, were selected, taking the limits of the Gómez classification. In order to define socioeconomic differences between the two groups, the sample population was divided into different levels, with the following results. The socioeconomic level of the well-nourished children did correlate with a good living standard of their families; in the other case, families with a low socioeconomic status, presented more nutritional problems. A questionnaire was applied to every mother selected. This included two items: a) In the first case, we tried to assess the mother's attitude towards food habits and children's illnesses. b) In the second case, the mother's knowledge concerning pregnancy, breast feeding, feeding of the child during the first year of life, taboos, beliefs and other aspects which could be related to nutrition. On the whole, the main objective of this study was attained, because significant differences were found between these two groups. Firstly, a good relationship between food habits and good nutritional status of the children was found. Secondly, mother with well-nourished children had better food habits and better socioeconomic status than mothers having children with poor health status, and therefore, of a lower socioeconomic status.     

Evidence for hydrogenase-4 catalyzed biohydrogen production in Escherichia coli

Biohydrogen production by Escherichia coli during fermentation of the mixture of glycerol, glucose and formate at different pH values was studied. Employing mutants lacking large subunits of different hydrogenases (Hyd), it was reported that, at pH 7.5, H₂ production was produced except in a hyaB hybC hycE triple mutant, thus suggesting compensatory H₂-producing functions of the Hyd enzymes. Activity of Hyd-4 was revealed in glucose assays at pH 7.5 in the triple mutant whereby 62% of the wild type level of H₂ production was derived from Hyd-4. In formate assays, it was shown, that, first, the hyaB hybC double mutant had a H₂ production ～3 fold higher than wild type, indicating that Hyd-1 and Hyd-2 oxidize H₂, and second, that at pH 5.5, Hyd-4 and Hyd-3 were responsible for H₂ production. These findings are significant when applying various carbon sources such as sugars, alcohol and organic acids for biohydrogen production.     

Experimental statistics of near-field intensity distributions at nanostructured surfaces

Scanning near‐field optical microscopy is a technique in which the resolution is primarily determined by the size of a probe and not by the wavelength of illumination as in classical (far‐field) microscopy. However, the relationship between a sample and its near‐field optical image is usually rather complex. Typical factors responsible, at least partially, for such a complexity are the conditions of illumination and detection, sample characteristics (e.g. roughness and dielectric constant) and optical properties of the probe. Theoretical and experimental works conducted to improve our understanding of the relation between the object and the image have been reported ( Greffet & Carminati, 1997 ). Recently, with the help of a photon scanning tunnelling microscope we have carried out an extensive study of the resultant near‐field intensity distributions due to the elastic (in the plane) scattering of surface plasmon polaritons (SPPs) at metal film surfaces. We have also directly observed (in similar experimental conditions) localized dipolar excitations in silver colloid fractals ( Bozhevolnyi et al., 1998 ). In both cases, the studied phenomena are intimately related to the regime of multiple light scattering, in which the interference effects are rather complicated and therefore a proper interpretation of them was far from being trivial. Thus, even though a certain understanding of many features inherent to the subwavelength light interference phenomena was gained ( Bozhevolnyi & Coello, 1998 ; Bozhevolnyi et al., 1998 ; Coello & Bozhevolnyi, 1999 ), it is clear from the outcome of the investigations that more systematic studies in this context are still needed. A different and more powerful approach may be a statistical study of the recorded near‐field intensity distributions. In this work, we report what we believe to be the first results on experimental statistics of near‐field optical images exhibiting localized optical excitations (related to the regime of multiple scattering of light). We investigated optical images obtained with SPPs excited at different light wavelengths and scattered at different film surfaces, and with different polarizations and wavelengths of light scattered by silver colloid fractal structures. We have found significant differences in statistics between near‐field intensity distributions taken at rough and smooth metal film surfaces and fractal structures. Finally, our predictions seem to be in agreement with theoretical studies reported by other authors ( Sanchez‐Gil & Garcia‐Ramos, 1998 ).     

Solving timetabling problems using a cultural algorithm

This paper addresses the solution of timetabling problems using cultural algorithms. The core idea is to extract problem domain information during the evolutionary search, and then combine it with some previously proposed operators, in order to improve performance. The proposed approach is validated using a benchmark of 20 instances, and its results are compared with respect to three other approaches: two evolutionary algorithms and simulated annealing, all of which have been previously adopted to solve timetabling problems.     

An evolutionary algorithm with a history mechanism for tuning a chess evaluation function

Here, we propose an evolutionary algorithm (i.e., evolutionary programming) for tuning the weights of a chess engine. Most of the previous work in this area has normally adopted co-evolution (i.e., tournaments among virtual players) to decide which players will pass to the following generation, depending on the outcome of each game. In contrast, our proposed method uses evolution to decide which virtual players will pass to the next generation based on the number of positions solved from a number of chess grandmaster games. Using a search depth of 1-ply, our method can solve 40.78% of the positions evaluated from chess grandmaster games (this value is higher than the one reported in the previous related work). Additionally, our method is capable of solving 53.08% of the positions using a historical mechanism that keeps a record of the “good” virtual players found during the evolutionary process. Our proposal has also been able to increase the competition level of our search engine, when playing against the program Chessmaster (grandmaster edition). Our chess engine reached a rating of 2404 points for the best virtual player with supervised learning, and a rating of 2442 points for the best virtual player with unsupervised learning. Finally, it is also worth mentioning that our results indicate that the piece material values obtained by our approach are similar to the values known from chess theory.     

Application of near infrared spectral fingerprinting and pattern recognition techniques for fast identification of Eleutherococcus senticosus

Eleutherococcus senticosus, a member of the Araliaceae family, has attracted the interest of many people due to its therapeutic properties. Consequent trading has impelled the development of analytical procedures for fast identification and counterfeit detection. For that purpose, a near-infrared spectroscopic procedure to obtain a fingerprint of E. senticosus has been developed using raw materials. The spectra were processed by using different pattern recognition procedures. General classification success rates of 84% and 92% were achieved by Soft Independent Modeling of Class Analogy (SIMCA) and Partial Least Squares Discriminant Analysis (PLS-DA), respectively. Tests on laboratory-made mixtures showed that it is possible to detect adulterations or counterfeits with about 5% foreign herbal material, depending on their closeness to the Araliaceae family. The sensitivity and specificity of constructed models were above 73%. The results suggest that NIR spectroscopy can be used to authenticate E. senticosus material.     

Evolutionary multi-objective optimization: some current research trends and topics that remain to be explored

This paper provides a short review of some of the main topics in which the current research in evolutionary multi-objective optimization is being focused. The topics discussed include new algorithms, efficiency, relaxed forms of dominance, scalability, and alternative metaheuristics. This discussion motivates some further topics which, from the author’s perspective, constitute good potential areas for future research, namely, constraint-handling techniques, incorporation of user’s preferences and parameter control. This information is expected to be useful for those interested in pursuing research in this area.     

An Artificial Immune System Heuristic for Generating Short Addition Chains

This paper deals with the optimal computation of finite field exponentiation, which is a well-studied problem with many important applications in the areas of error-correcting codes and cryptography. It has been shown that the optimal computation of finite field exponentiation is a problem which is closely related to finding a suitable addition chain with the shortest possible length. However, it is also known that obtaining the shortest addition chain for a given arbitrary exponent is an NP-hard problem. As a consequence, heuristics are an obvious choice to compute field exponentiation with a semi-optimal number of underlying arithmetic operations. In this paper, we propose the use of an artificial immune system to tackle this problem. Particularly, we study the problem of finding both the shortest addition chains for exponents e with moderate size (i.e., with a length of less than 20 bits), and for the huge exponents typically adopted in cryptographic applications, (i.e., in the range from 128 to 2048 bits).