Marco S. Reis

Hospital Risoleta Tolentino Neves

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Tiago J. Rato

University of Coimbra

Pedro Saraiva

Instituto Superior de Gestão

Ricardo Rendall

Dow Chemical (United States)

Leo H. Chiang

Dow Chemical (United States)

Ana C. Pereira

Universidade da Madeira

Iván Castillo

Dow Chemical (United States)

Tocio Sediyama

Universidade Federal de Viçosa

José C. Marques

Universidade da Madeira

Eugeniu Strelet

University of Coimbra

Joel Sansana

University of Coimbra

Cooperative Institutions

University of Coimbra

Universidade Federal de Viçosa

Serviço Nacional de Aprendizagem Industrial

University of Lisbon

Dow Chemical (United States)

University of Aveiro

Universidade Federal da Bahia

Universidade do Porto

Centre National de la Recherche Scientifique

Universidade de São Paulo

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Machine Learning Techniques Disclose the Combined Effect of Fermentation Conditions on Yeast Mixed-Culture Dynamics and Wine Quality

Microorganisms (2022)

Catarina Barbosa Elsa Ramalhosa Isabel Vasconcelos Marco S. Reis Ana Mendes‐Ferreira

The use of yeast starter cultures consisting of a blend of Saccharomyces cerevisiae and non-Saccharomyces yeasts has increased in recent years as a mean to address consumers' demands for diversified wines. However, this strategy is currently limited by the lack of a comprehensive knowledge regarding the factors that determine the balance between the yeast-yeast interactions and their responses triggered in complex environments. Our previous studies demonstrated that the strain Hanseniaspora guilliermondii UTAD222 has potential to be used as an adjunct of S. cerevisiae in the wine industry due to its positive impact on the fruity and floral character of wines. To rationalize the use of this yeast consortium, this study aims to understand the influence of production factors such as sugar and nitrogen levels, fermentation temperature, and the level of co-inoculation of H. guilliermondii UTAD222 in shaping fermentation and wine composition. For that purpose, a Central Composite experimental Design was applied to investigate the combined effects of the four factors on fermentation parameters and metabolites produced. The patterns of variation of the response variables were analyzed using machine learning methods, to describe their clustered behavior and model the evolution of each cluster depending on the experimental conditions. The innovative data analysis methodology adopted goes beyond the traditional univariate approach, being able to incorporate the modularity, heterogeneity, and hierarchy inherent to metabolic systems. In this line, this study provides preliminary data and insights, enabling the development of innovative strategies to increase the aromatic and fermentative potential of H. guilliermondii UTAD222 by modulating temperature and the availability of nitrogen and/or sugars in the medium. Furthermore, the strategy followed gathered knowledge to guide the rational development of mixed blends that can be used to obtain a particular wine style, as a function of fermentation conditions.

Winemaking

Modularity

Starter

10.3390/microorganisms10010107

Cite

Citations (8)

Metástase espinhal de glioblastoma cerebral: relato de caso e revisão da literatura

Arquivos Brasileiros de Neurocirurgia Brazilian Neurosurgery (2018)

Marcelo Filho Andrey Silva Marco S. Reis

Introdução: O Glioblastoma é a neoplasia primária mais comum no sistema nervoso central. Metástase sintomática para a medula espinhal é um evento raro, no entanto, há um aumento de casos relatados nos últimos anos. Acredita-se que cerca de 25% dos pacientes desenvolvam metástase assintomática durante a evolução da doença, com base em estudos de necropsias. O primeiro caso foi relatado em 1931. Até 1978 havia apenas 14 casos bem descritos na literatura. Em 1990 uma série de 600 pacientes portadores de GBM mostrou uma incidência de 2% de disseminação liquórica.

10.1055/s-0038-1672872

Cite

Citations (0)

Efeito do condicionamento osmótico na embebição e na germinação de sementes de cenoura (Daucus carota L.)

Revista Brasileira de Sementes (1999)

Luciano Esteves Peluzio R.F. Silva Marco S. Reis Paulo Roberto Cecon D.C.F.S. Dias

Daucus carota

10.17801/0101-3122/rbs.v21n2p161-169

Cite

Citations (5)

Cached Machine Learning - A Local Caching System to Reduce Cloud-Communication Dependency During Inference Phase

Sérgio Branco J. Carvalho Marco S. Reis Jorge Cabral

<p>The continuous research on TinyML has increased the number of Machine Learning (ML) models capable of running their inference phase in a Resource-Scarce Embedded System (RSES). Therefore, part of the intelligence services run now in the devices at the end of the network. However, many ML models are too complex to run in such tiny devices, and a Cloud system is necessary to implement the network's intelligence inference layer. Every communication between a RSES and the Cloud is expensive in terms of power consumption, money, and time. The following work tries to answer how to reduce the number of times a RSES communicates with the Cloud system while achieving the same ML inference rate, and without reducing the model's accuracy. The results show how by building a cache system that allows the RSES to store previous samples and their predictions, the RSES can use this information to avoid Cloud communication. The solution has proven to work and to accomplish a communication reduction between the cloud system and the RSES by 30%.</p>

10.36227/techrxiv.21405120

Cite

Citations (0)

Advantage of Using Decorrelated Residuals in Dynamic Principal Component Analysis for Monitoring Large-Scale Systems

Industrial & Engineering Chemistry Research (2013)

Tiago J. Rato Marco S. Reis

A new methodology is proposed for monitoring multi- and megavariate systems whose variables present significant levels of autocorrelation. The new monitoring statistics are derived after the preliminary generation of decorrelated residuals in a dynamic principal component analysis (DPCA) model. The proposed methodology leads to monitoring statistics with low levels of serial dependency, a feature that is not shared by the original DPCA formulation and that seriously hindered its dissemination in practice, leading to the use of other, more complex, monitoring approaches. The performance of the proposed method is compared with those of a variety of current monitoring methodologies for large-scale systems, under different dynamical scenarios and for different types of process upsets and fault magnitudes. The results obtained clearly indicate that the statistics based on decorrelated residuals from DPCA (DPCA-DR) consistently present superior performances regarding detection ability and decorrelation power and are also robust and efficient to compute.

Decorrelation

Component (thermodynamics)

Feature (linguistics)

10.1021/ie3035306

Cite

Citations (58)

Multiscale statistical process control with multiresolution data

AIChE Journal (2006)

Marco S. Reis Pedro Saraiva

Abstract An approach is presented for conducting multiscale statistical process control that adequately integrates data at different resolutions (multiresolution data), called MR‐MSSPC. Its general structure is based on Bakshi's MSSPC framework designed to handle data at a single resolution. Significant modifications were introduced in order to process multiresolution information. The main MR‐MSSPC features are presented and illustrated through three examples. Issues related to real world implementations and with the interpretation of the multiscale covariance structure are addressed in a fourth example, where a CSTR system under feedback control is simulated. Our approach proved to be able to provide a clearer definition of the regions where significant events occur and a more sensitive response when the process is brought back to normal operation, when it is compared with previous approaches based on single resolution data. © 2006 American Institute of Chemical Engineers AIChE J, 2006

Statistical Process Control

Multiresolution analysis

Implementation

10.1002/aic.10805

Cite

Citations (42)

Different Modeling Approaches for a Heterogeneous Liquid−Liquid Reaction Process

Industrial & Engineering Chemistry Research (2005)

Paulo A. Quadros Marco S. Reis Cristina M. S. G. Baptista

Multivariate linear regression (MLR) techniques were used to develop empirical models which are able to predict the formation of the main product and byproducts of the adiabatic benzene nitration process, as a function of the main operating conditions. Experiments carried out in a pilot plant enabled us to reproduce the operating conditions of the industrial process, providing experimental data in the intermediate and fast reaction regimes. The nitrobenzene (MNB) formation was modeled according to the film and Danckwerts mechanistic models, and the results were compared with a MLR model, showing that both approaches are suitable for describing this reaction. Nevertheless, the results stress an improved performance of the MLR model when compared to the mechanistic models, despite its structural simplicity. The statistical models developed for the nitrophenols (NPs), namely for the dinitrophenol and trinitrophenol (DNP and TNP, respectively), describe accurately the formation of these byproducts, overcoming the lack of data on kinetic and physical-chemical properties required by the mechanistic approach. The MLR models can be used for process optimization regarding conversion, productivity, and selectivity. By making use of these models, it was possible to estimate the operating conditions (temperature, 81 °C; FB/FN ratio, 1.5; residence time, 1.9 min; nitric acid concentration, 2.6%; sulfuric acid concentration, 64%; interfacial area, 46.7 × 103m2·m-3) that enable the attainment of a 99.99% MNB yield, with a total NP concentration<215 ppm.

Nitrobenzene

10.1021/ie050205m

Cite

Citations (11)

From Heated Discussions to Enlightened Debates – Bringing the Bayesian Perspective to the Archaeological Arena

SSRN Electronic Journal (2022)

Joel dos Santos Marco S. Reis Afonso Garradas Leão

Archaeological arguments usually fall in the “to be or not to be” discussions, where several suppositions are raised, not being possible to prove that some hypotheses are more plausible than others. Using a Bayesian perspective this paper presents a mathematical probabilistic approach that calculates the degree of likelihood for each of the hypotheses suggested for a specific discussion, calculating the probability for each one and quantitatively comparing each one with all others. This method will be applied even in situations where there is a huge lack of comparative data. To exemplify our proposal, a case study regarding a 2019 excavation will be used, since this specific place was appointed as a possible prostitution house, a hypothesis that was contradicted by other investigators. Our work, using the proposed methodology, will calculate the probability of several hypotheses.

10.2139/ssrn.4129678

Cite

Citations (0)

An integrated multiscale and multivariate image analysis framework for process monitoring of colour random textures: MSMIA

Chemometrics and Intelligent Laboratory Systems (2015)

Marco S. Reis

Texture (cosmology)

Line (geometry)

10.1016/j.chemolab.2015.01.008

Cite

Citations (7)

Development of a fast and reliable method for long- and short-term wine age prediction

Talanta (2011)

Ana C. Pereira Marco S. Reis Pedro Saraiva José C. Marques

10.1016/j.talanta.2011.09.016

Cite

Citations (23)