Genetic programming and bacterial algorithm for neural networks and fuzzy systems design

In the field of control systems it is common to use techniques based on model adaptation to carry out control for plants for which mathematical analysis may be intricate. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this line, this paper gives a perspective on the quality of results given by two different biologically connected learning algorithms for the design of B-spline neural networks (BNN) and fuzzy systems (FS). One approach used is the Genetic Programming (GP) for BNN design and the other is the Bacterial Evolutionary Algorithm (BEA) applied for fuzzy rule extraction. Also, the facility to incorporate a multi-objective approach to the GP algorithm is outlined, enabling the designer to obtain models more adequate for their intended use.

Genetic and bacterial programming for B-Spline neural networks design

The design phase of B-spline neural networks is a highly computationally complex task. Existent heuristics have been found to be highly dependent on the initial conditions employed. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this paper, the Bacterial Programming approach is presented, which is based on the replication of the microbial evolution phenomenon. This technique produces an efficient topology search, obtaining additionally more consistent solutions.

Design of B-spline neural networks using a bacterial programming approach

The design phase of B-spline neural networks represents a very high computational task. For this purpose, heuristics have been developed, but have been shown to be dependent on the initial conditions employed. In this paper a new technique, Bacterial Programming, is proposed, whose principles are based on the replication of the microbial evolution phenomenon. The performance of this approach is illustrated and compared with existing alternatives.

Bacterial algorithm applied for fuzzy rule extraction

This paper presents a method of using the so-colled "bacterial algorithm" (4,5) for extracting a fuzzy rule base from a training set. The bewly proposed bacterial evolutionary algorithm (BEA) is shown. In our application one bacterium corresponds to a fuzzy rule system.

Dietary biodiesel-derived crude glycerol in gilthead seabream juveniles (Sparus aurata): effects on growth performance and metabolism

In the European Union the turn towards renewable energy sources has increased the production of biodiesel from rapeseed oil, leaving glycerol (also known as glycerin) as a valuable by-product. For every litre of biodiesel produced, approximately 79 g of crude glycerol are generated. As the biodiesel production grows, the quantity of crude glycerol generated will be considerable and its utilization will become an urgent topic. One possibility is the use of crude glycerol on animal feeds. Glycerol has been evaluated as a dietary energy source for several farm animals, including fish. A study was undertaken to assess the effect of dietary biodiesel-derived glycerol (from rapeseed oil) on the overall growth performance, digestive capacity and metabolic nutrient utilization in juvenile gilthead seabream fed a low fishmeal level diet. Two practical diets were formulated to be isonitrogenous (crude protein, 45.4% DM), isolipidic (18.5% DM) and isoenergetic (gross energy, 21.3 kJ/g DM). The control diet (CTRL) was formulated with intermediate levels of marine-derived proteins (19%). In the same basal formulation, 5% glycerol (GLY) was incorporated at the expenses of wheat. Each dietary treatment was tested in triplicate tanks over 63 days, with 20 gilthead seabream (Sparus aurata), with a mean initial body weight (IBW) of 27.9  0.12 g. At the end of the trial, fish fed the CTRL diet reached a final body weight of 84.3  2.2 g (more than 3-fold increase of initial body weight). Fish fed the GLY diet showed a significantly higher (P<0.05) growth, expressed in terms of final body weight and specific growth rate. Voluntary feed intake was similar between the two treatments, but both feed efficiency and protein efficiency ratio were significantly improved (P<0.05) in fish fed the GLY diet. Dietary glycerol had no effect (P>0.05) on the apparent digestibility of protein. In comparison to the control treatment, dietary glycerol significantly improved (P<0.05) protein and fat retention. Activities of digestive enzymes were significantly affected by the various dietary treatments. Fish fed the GLY diet showed an enhanced activity of alkaline phosphatase (ALP) and pepsin, while activities of lipase and leucine-alanine peptidase (LAP) were little affected by dietary glycerol. Fish show the ability to use crude glycerol as a dietary energy substrate.

A proteomic study of the effects of nutrient restriction in utero on postnatal metabolism

It is widely recognized that protein restriction in utero may cause metabolic and endocrine adaptations, which may be of benefit to the neonate on a short-term basis but may cause adverse long-term conditions such as obesity, Type 2 diabetes, metabolic syndrome, hypertension and cardiovascular diseases. Adequate foetal and early post natal nutrient and energy supply is therefore essential for adult animal health, performance and life span. In this project it was investigated the progressive adaptations of the hepatic proteome in male mink offspring exposed to either a low protein (FL) or an adequate protein (FA) diet in utero fed either on a low protein (LP) or on an adequate (AP) diet from weaning until sexual maturity. Specifically, the aim was to determine the metabolic adaptations at selected phases of the animal’s first annual cycle and establish the metabolic priorities occurring during those phases. The three different morphological stages studied during the first year of development included, end of bone growth at 4 months of age, maximal fat accretion at 6 months of age and sexual maturity at 12 months of age. A reference proteome of mink liver coming from these different animal groups were generated using 2D electrophoresis coupled to MALDI-TOF analysis and the way in which dietary treatment affect their proteome was established. Approximately 330 proteins were detected in the mink liver proteome. A total of 27 comparisons were carried out between all different animal groups which resulted in 20 differentially expressed proteins. An extensive survey was conducted towards the characterization of these proteins including their subcellular localization, the biological processes in which they are involved and their molecular functions. This characterization allowed the identification of proteins in various processes including the glycolysis and fatty acid metabolism. The detailed analysis of the different dietary treatment animal groups was indicative of differences in metabolism and also to changes associated with development in mink.

Study of the expression of different genes of long-chain polyunsaturated fatty acids (LC-PUFA) metabolism during the early paralarval development of the common octopus (Octopus vulgaris)

Dissertação de mestrado, Aquacultura e Pescas, Faculdade de Ciências e Tecnologias, Universidade do Algarve, 2015

Bacterial peroxide forming enzymes

Dissertação de mestrado, Engenharia Biológica, Faculdade de Ciências e Tecnologia, Universidade do Algarve; Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa, 2015