Abstract
Fuzzy modelling has been widely applied as a powerful methodology for the identification of nonlinear systems from process measurements. Most applications use flat sets of fuzzy rules, which are hardly interpretable black-box approaches. Hierarchical modelling is a promising tool to deal with real world complex systems. A large-scale model can be easily readable if it is partitioned into several independent smaller models to represent functional relations of the processes involved in the system. This article deals with the application of a new fuzzy modelling technique that automatically organizes the sets of fuzzy IF-THEN rules in a Hierarchical Collaborative Structure. This organizational structure makes the fuzzy model interpretable as in the case of the physical model. This new methodology was tested to split the inside greenhouse air temperature and humidity flat fuzzy models into fuzzy sub-models. which have alike counterpart on the physical sub-models.

Abstract
This paper presents a hybrid genetic algorithm, also known as Memetic Algorithm (MA), applied to the design of combinational logic circuits. In view of the fact that hybrid algorithms have shown to be very effective in solving many hard combinatorial optimization problems, the proposed MA combines a Genetic Algorithm (GA) for digital circuit design with the gate type local search (GTLS). The combination of a global and a local search is a strategy adopted by recent hybrid optimization approaches. The main idea is to apply a local refinement to an Evolutionary Algorithm (EA) in order to improve the fitness of the individuals in the population. The results show an improvement of the final fitness function followed by a reduction of the average number of generations required to reach the solutions and its standard deviation, for all the tested circuits.

Abstract
This paper proposes a genetic algorithm for designing combinational logic circuits and studies four different/case examples: the 2-to-1 multiplexer, the one-bit full adder, the four-bit parity checker and the two-bit multiplier. The objective of this work is to generate a functional circuit with the minimum number of logic gates. It is also studied the scalability problem that emerges from the exponential growth of the truth table when the circuits complexity increases. Furthermore, it is as well investigated the population size and the processing time for achieving a solution in order to establish a compromise between the two parameters.

Abstract
The MatPLC is an international project to develop a program similar to a PLC (Programmable Logic Controller) for POSIX operating systems. It is an open source application consisting of a core, generic modules, and tools for creating custom modules. Since many control and monitoring systems are distributed in nature, they require that the application be running on an embedded system capable of withstanding harsh environments. This paper describes the porting of the MatPLC code base to a commercial embedded system running on a PowerPC CPU. Time measurements were taken to determine whether the resulting code would be suitable for control applications.

Abstract
This paper presents a large amount of data on the composition of quince fruit with regard to phenolic compounds, organic acids, and free amino acids. Subsequently, principal component analysis (PCA) is carried out to characterize this fruit. The main purposes of this study were (i) the clarification of the interactions among three factors-quince fruit part, geographical origin of the fruits, and harvesting year-and the phenolic, organic acid, and free amino acid profiles; (ii) the classification of the possible differences; and (iii) the possible correlation among the contents of phenolics, organic acids, and free amino acids in quince fruit. With these aims, quince pulp and peel from nine geographical origins of Portugal, harvested in three consecutive years, for a total of 48 samples, were studied. PCA was performed to assess the relationship among the different components of quince fruit phenolics, organic acids, and free amino acids. Phenolics determination was the most interesting. The difference between pulp and peel phenolic profiles was more apparent during PCA. Two PCs accounted for 81.29% of the total variability, PC1 (74.14%) and PC2 (7.15%). PC1 described the difference between the contents of caffeoylquinic acids (3-O-, 4-O-, and 5-O-caffeoylquinic acids and 3,5-O-dicaffeoylquinic acid) and flavonoids (quercetin 3-galactoside, rutin, kaempferol glycoside, kaempferol 3-glucoside, kaempferol 3-rutinoside, quercetin glycosides acylated with p-coumaric acid, and kaempferol glycosides acylated with p-coumaric acid). PC2 related the content of 4-O-caffeoylquinic acid with the contents of 5-O-caffeoylquinic and 3,5-O-dicaffeoylquinic acids. PCA of phenolic compounds enables a clear distinction between the two parts of the fruit. The data presented herein may serve as a database for the detection of adulteration in quince derivatives.

Abstract
This study shows the results of Vitis vinifera pollen season in the atmosphere of the Braga region (Portugal) for the last 5 years (1999-2003). The fluctuations in the airborne pollen concentration, the synchronic rhythms in the annual pollen trends and their relationship to the main meteorological parameters were investigated. The vineyard pollen season extends from late May to early July, presenting always a bimodal pattern. During the studied period several pollen types such as Poaceae, Castanea, Olea, Urticaceae, Quercus, Plantago, Rumex, Asteraceae, Pinaceae, Ericaceae and Eucalyptus were also observed. Airborne pollen concentration is highly influenced by mean temperature, rain, number of days with rain and wind direction.