Implementação em hardware de uma Rede Neuronal com ummicroprocessador embebido em FPGA

O objectivo deste trabalho é a implementação em hardware de uma Rede Neuronal com um microprocessador embebido, podendo ser um recurso valioso em várias áreas científicas. A importância das implementações em hardware deve-se à flexibilidade, maior desempenho e baixo consumo de energia. Para esta implementação foi utilizado o dispositivo FPGA Virtex II Pro XC2VP30 com um MicroBlaze soft core, da Xilinx. O MicroBlaze tem vantagens como a simplicidade no design, sua reutilização e fácil integração com outras tecnologias. A primeira fase do trabalho consistiu num estudo sobre o FPGA, um sistema reconfigurável que possui características importantes como a capacidade de executar em paralelo tarefas complexas. Em seguida, desenvolveu-se o código de implementação de uma Rede Neuronal Artificial baseado numa linguagem de programação de alto nível. Na implementação da Rede Neuronal aplicou-se, na camada escondida, a função de activação tangente hiperbólica, que serve para fornecer a não linearidade à Rede Neuronal. A implementação é feita usando um tipo de Rede Neuronal que permite apenas ligações no sentido de saída, chamado Redes Neuronais sem realimentação (do Inglês Feedforward Neural Networks - FNN). Como as Redes Neuronais Artificiais são sistemas de processamento de informações, e as suas características são comuns às Redes Neuronais Biológicas, aplicaram-se testes na implementação em hardware e analisou-se a sua importância, a sua eficiência e o seu desempenho. E finalmente, diante dos resultados, fez-se uma análise de abordagem e metodologia adoptada e sua viabilidade.

Multivariate analysis for the classification and differentiation of Madeira wines according to main grape varieties

In order to differentiate and characterize Madeira wines according to main grape varieties, the volatile composition (higher alcohols, fatty acids, ethyl esters and carbonyl compounds) was determined for 36 monovarietal Madeira wine samples elaborated from Boal, Malvazia, Sercial and Verdelho white grape varieties. The study was carried out by headspace solid-phase microextraction technique (HS-SPME), in dynamic mode, coupled with gas chromatography–mass spectrometry (GC–MS). Corrected peak area data for 42 analytes from the above mentioned chemical groups was used for statistical purposes. Principal component analysis (PCA) was applied in order to determine the main sources of variability present in the data sets and to establish the relation between samples (objects) and volatile compounds (variables). The data obtained by GC–MS shows that the most important contributions to the differentiation of Boal wines are benzyl alcohol and (E)-hex-3-en-1-ol. Ethyl octadecanoate, (Z)-hex-3-en-1-ol and benzoic acid are the major contributions in Malvazia wines and 2-methylpropan-1-ol is associated to Sercial wines. Verdelho wines are most correlated with 5-(ethoxymethyl)-furfural, nonanone and cis-9-ethyldecenoate. A 96.4% of prediction ability was obtained by the application of stepwise linear discriminant analysis (SLDA) using the 19 variables that maximise the variance of the initial data set.

Effectiveness of different solid-phase microextraction fibres for differentiation of selected Madeira island fruits based on their volatile metabolite profile: identification of novel compounds

A headspace solid-phase microextraction (HS-SPME) procedure based on five commercialised fibres (85 μm polyacrylate – PA, 100 μm polydimethylsiloxane – PDMS, 65 μm polydimethylsiloxane/divinylbenzene – PDMS/DVB, 70 μm carbowax/divinylbenzene – CW/DVB and 85 μm carboxen/polydimethylsiloxane – CAR/PDMS) is presented for the characterization of the volatile metabolite profile of four selected Madeira island fruit species, lemon (Citrus limon), kiwi (Actinidia deliciosa), papaya (Carica papaya L.) and Chickasaw plum (Prunus angustifolia). The isolation of metabolites was followed by thermal desorption gas chromatography–quadrupole mass spectrometry (GC–qMS) methodology. The performance of the target fibres was evaluated and compared. The SPME fibre coated with CW/DVB afforded the highest extraction efficiency in kiwi and papaya pulps, while in lemon and plum the same was achieved with PMDS/DVB fibre. This procedure allowed for the identification of 80 compounds, 41 in kiwi, 24 in plums, 23 in papaya and 20 in lemon. Considering the best extraction conditions, the most abundant volatiles identified in kiwi were the intense aldehydes and ethyl esters such as (E)-2-hexenal and ethyl butyrate, while in Chicasaw plum predominate 2-hexenal, 2-methyl-4-pentenal, hexanal, (Z)-3-hexenol and cyclohexylene oxide. The major compounds identified in the papaya pulp were benzyl isothiocyanate, linalool oxide, furfural, hydroxypropanone, linalool and acetic acid. Finally, lemon was shown to be the most divergent of the four fruits, being its aroma profile composed almost exclusively by terpens, namely limonene, γ-terpinene, o-cymene and α-terpinolene. Thirty two volatiles were identified for the first time in the fruit or close related species analysed and 14 volatiles are reported as novel volatile metabolites in fruits. This includes 5 new compounds in kiwi (2-cyclohexene-1,4-dione, furyl hydroxymethyl ketone, 4-hydroxydihydro-2(3H)-furanone, 5-acetoxymethyl-2-furaldehyde and ethanedioic acid), 4 in plum (4-hydroxydihydro-2(3H)-furanone, 5-methyl-2-pyrazinylmethanol, cyclohexylene oxide and 1-methylcyclohexene), 4 in papaya (octaethyleneglycol, 1,2-cyclopentanedione, 3-methyl-1,2-cyclopentanedione and 2-furyl methyl ketone) and 2 in lemon (geranyl farnesate and safranal). It is noteworthy that among the 15 volatile metabolites identified in papaya, 3-methyl-1,2-cyclopentanedione was previously described as a novel PPARγ (peroxisome proliferator-activated receptor γ) agonist, having a potential to minimize inflammation.