Browsing by Author "Santos, Jorge M."
Now showing 1 - 7 of 7
Results Per Page
Sort Options
- Análise e comparação da utilização de métodos de Análise de Componentes Principais na descrição da relação entre a profundidade de um solo florestal e algumas das suas propriedades geoquímicasPublication . Meira Castro, Ana C.; Santos, Jorge M.; Meixedo, João Paulo; Góis, JoaquimNeste trabalho apresentam-se os resultados da analise e comparação da utilização da Análise de Componentes Principais Clássica (ACP) e a Análise de Componentes Principais Robusta (ACPR) na descrição da relação entre a profundidade de um solo florestal e as alterações em quatro propriedades geoquímicas fundamentais. Os resultados obtidos reconhecem que, neste tipo de dados e cala local, a utilização da ACPR deve ser utilizada em detrimento da ACP e que o procedimento de amostragem de solos pouco férteis, como é o caso dos solos florestais, pode ser aliviado em termos de detalhe em profundidade por uma amostragem a uma altura única de 18cm mas deve, contudo, ser efectuada estrategicamente, dado que a localização dos pontos de amostragem revela ter significativa influência nos resultados obtidos.
- High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer LearningPublication . Kandaswamy, C.; Silva, L. M.; Alexandre, L. A.; Santos, Jorge M.High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.
- On sampling collection procedure effectiveness for forest soil characterizationPublication . Meira Castro, Ana C.; Meixedo, João Paulo; Santos, Jorge M.; Góis, Joaquim; Bento-Gonçalves, António; Vieira, António; Lourenço, LucianoOne of the most important measures to prevent wild forest fires is the use of prescribed and controlled burning actions as it reduce the fuel mass availability. The impact of these management activities on soil physical and chemical properties varies according to the type of both soil and vegetation. Decisions in forest management plans are often based on the results obtained from soil-monitoring campaigns. Those campaigns are often man-labor intensive and expensive. In this paper we have successfully used the multivariate statistical technique Robust Principal Analysis Compounds (ROBPCA) to investigate on the sampling procedure effectiveness for two different methodologies, in order to reflect on the possibility of simplifying and reduce the sampling collection process and its auxiliary laboratory analysis work towards a cost-effective and competent forest soil characterization.
- Re-use assessment of thermoset composite wastes as aggregate and filler replacement for concrete-polymer composite materials: a case study regarding GFRP pultrusion wastesPublication . C. S. Ribeiro, Maria; Meira Castro, Ana C.; Silva, Francisco; Santos, Jorge M.; Meixedo, Joao Paulo; Fiúza, António; Dinis, M. L.; Alvim, Mário RuiGlass fibre-reinforced plastics (GFRP), nowadays commonly used in the construction, transportation and automobile sectors, have been considered inherently difficult to recycle due to both the cross-linked nature of thermoset resins, which cannot be remoulded, and the complex composition of the composite itself, which includes glass fibres, polymer matrix and different types of inorganic fillers. Hence, to date, most of the thermoset based GFRP waste is being incinerated or landfilled leading to negative environmental impacts and additional costs to producers and suppliers. With an increasing awareness of environmental matters and the subsequent desire to save resources, recycling would convert an expensive waste disposal into a profitable reusable material. In this study, the effect of the incorporation of mechanically recycled GFRP pultrusion wastes on flexural and compressive behaviour of polyester polymer mortars (PM) was assessed. For this purpose, different contents of GFRP recyclates (0%, 4%, 8% and 12%, w/w), with distinct size grades (coarse fibrous mixture and fine powdered mixture), were incorporated into polyester PM as sand aggregates and filler replacements. The effect of the incorporation of a silane coupling agent was also assessed. Experimental results revealed that GFRP waste filled polymer mortars show improved mechanical behaviour over unmodified polyester based mortars, thus indicating the feasibility of GFRP waste reuse as raw material in concrete-polymer composites.
- Sustainable waste recycling solution for the glass fibre reinforced polymer composite materials industryPublication . Meira Castro, Ana C.; Ribeiro, M. C. S.; Santos, Jorge M.; Meixedo, João Paulo; Silva, Francisco J. G.; Fiúza, António; Dinis, M. L.; Alvim, Mário RuiIn this paper the adequacy and the benefit of incorporating glass fibre reinforced polymer (GFRP) waste materials into polyester based mortars, as sand aggregates and filler replacements, are assessed. Different weight contents of mechanically recycled GFRP wastes with two particle size grades are included in the formulation of new materials. In all formulations, a polyester resin matrix was modified with a silane coupling agent in order to improve binder-aggregates interfaces. The added value of the recycling solution was assessed by means of both flexural and compressive strengths of GFRP admixed mortars with regard to those of the unmodified polymer mortars. Planning of experiments and data treatment were performed by means of full factorial design and through appropriate statistical tools based on analyses of variance (ANOVA). Results show that the partial replacement of sand aggregates by either type of GFRP recyclates improves the mechanical performance of resultant polymer mortars. In the case of trial formulations modified with the coarser waste mix, the best results are achieved with 8% waste weight content, while for fine waste based polymer mortars, 4% in weight of waste content leads to the higher increases on mechanical strengths. This study clearly identifies a promising waste management solution for GFRP waste materials by developing a cost-effective end-use application for the recyclates, thus contributing to a more sustainable fibre-reinforced polymer composites industry.
- Using neural networks and support vector regression to relate marchetti dilatometer test parameters and maximum shear modulusPublication . Cruz, Manuel; Santos, Jorge M.; Cruz, NunoIn the last two decades, small strain shear modulus became one of the most important geotechnical parameters to characterize soil stiffness. Finite element analysis have shown that in-situ stiffness of soils and rocks is much higher than what was previously thought and that stress-strain behaviour of these materials is non-linear in most cases with small strain levels, especially in the ground around retaining walls, foundations and tunnels, typically in the order of 10−2 to 10−4 of strain. Although the best approach to estimate shear modulus seems to be based in measuring seismic wave velocities, deriving the parameter through correlations with in-situ tests is usually considered very useful for design practice.The use of Neural Networks for modeling systems has been widespread, in particular within areas where the great amount of available data and the complexity of the systems keeps the problem very unfriendly to treat following traditional data analysis methodologies. In this work, the use of Neural Networks and Support Vector Regression is proposed to estimate small strain shear modulus for sedimentary soils from the basic or intermediate parameters derived from Marchetti Dilatometer Test. The results are discussed and compared with some of the most common available methodologies for this evaluation.
- Using neural networks and support vector regression to relate marchetti dilatometer test parameters and maximum shear modulusPublication . Cruz, Manuel; Santos, Jorge M.; Cruz, NunoIn the last two decades, small strain shear modulus became one of the most important geotechnical parameters to characterize soil stiffness. Finite element analysis have shown that in-situ stiffness of soils and rocks is much higher than what was previously thought and that stress-strain behaviour of these materials is non-linear in most cases with small strain levels, especially in the ground around retaining walls, foundations and tunnels, typically in the order of 10−2 to 10−4 of strain. Although the best approach to estimate shear modulus seems to be based in measuring seismic wave velocities, deriving the parameter through correlations with in-situ tests is usually considered very useful for design practice.The use of Neural Networks for modeling systems has been widespread, in particular within areas where the great amount of available data and the complexity of the systems keeps the problem very unfriendly to treat following traditional data analysis methodologies. In this work, the use of Neural Networks and Support Vector Regression is proposed to estimate small strain shear modulus for sedimentary soils from the basic or intermediate parameters derived from Marchetti Dilatometer Test. The results are discussed and compared with some of the most common available methodologies for this evaluation.