Luís Rato

Universidade de Évora | uevora · Department of Informatics

Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of transcribing audio recordings into text, i.e., transforming speech into the respective sequence of words. This paper presents a deep learning ASR system optimization and evaluation for the European Portuguese language. We present a pipeline composed of several s...

Over the years, due to the enrichment of paired-label datasets, supervised machine learning has become a prime component of any problem-solving. Examples include building classifiers for applications such as image/speech recognition, traffic prediction, product recommendation, virtual personal assistant (VPA), online fraud detection and many more....

Numerical simulations of a billet heating furnace with direct flame impingement operating in a metallurgical plant were carried out and the results compared to measurements obtained in an industrial environment. The transport equations for mass, momentum, energy and mass of chemical species in reactive flow were computed with the use of ANSYS FLUEN...

Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge...

Apparent diffusion coefficient (ADC) of magnetic resonance imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using diffusion-weighted imaging (DWI). This study focuses on developing a robust machine learning (ML) model to predict the aggressive...

A abrangência e a diversificação dos sistemas de ensino superior determinaram uma maior atenção por parte da sociedade e a uma maior preocupação com a qualidade dos programas oferecidos aos estudantes e, em consequência, ao aumento das avaliações públicas e das comparações internacionais das instituições de ensino superior com projeção frequente na...

'Persian walnut' ( Juglans regia L.) is one of the most consumed nut species in the world, and N, K, and Ca nutrition are critical for its growth and quality. Mineral nutrition management in fruit crops over large areas is a challenging task only possible with a remote sensing data approach and using rapid analytical methods to correlate remotely s...

Apparent Diffusion Coefficient (ADC) is one of the most common magnetic resonance imaging (MRI) techniques that are frequently used in the brain tumor diagnosis process. This study is based on extracting statistical texture features from MRI-ADC images of human brain tumors to observe correlations of feature values between malignant and benign brai...

Background: Apparent Diffusion Coefficient (ADC) of Magnetic Resonance Imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using Diffusion-weighted imaging (DWI). This study focuses on developing a robust Machine Learning (ML) model to predict th...

Background: Apparent Diffusion Coefficient (ADC) of Magnetic Resonance Imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using Diffusion-weighted imaging (DWI). This study focuses on developing a robust Machine Learning (ML) model to predict th...

Diffusion Weighted (DW) imaging is a Magnetic Resonance Imaging (MRI) technique that is widely used in modern clinical neuroimaging practices. This study was focused on developing a robust machine-learning (ML) model to differentiate benign and malignant brain tumours by analysing patients’ demographics, high-order moments, and statistical texture...

p>All the data was obtained from the National Hospital of Sri Lanka (NHSL) and the Teaching Hospital Anuradhapura under the supervision of the Ethical Review Board of NHSL and the Faculty of Medicine, University of peradeniya. </p

p>All the data was obtained from the National Hospital of Sri Lanka (NHSL) and the Teaching Hospital Anuradhapura under the supervision of the Ethical Review Board of NHSL and the Faculty of Medicine, University of peradeniya. </p

Background Diffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifyin...

The digital world is very dynamic. The ability to timely identify possible vendor migration trends or customer loss risks is very important in cloud-based services. This work describes a churn risk prediction system and how it can be applied to guide cloud service providers for recommending adjustments in the service subscription level, both to pro...

Over the years, due to the enrichment of paired-label datasets, supervised machine learning has become an important part of any problem-solving process. Active Learning gains importance when, given a large amount of freely available data, there’s a lack of expert’s manual labels. This paper proposes an active learning algorithm for selective choice...

This paper focuses on the mapping problem for mobile robots in dynamic environments where the state of every point in space may change, over time, between free or occupied. The dynamical behaviour of a single point is modelled by a Markov chain, which has to be learned from the data collected by the robot. Spatial correlation is based on Gaussian r...

Background: Diffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifyi...

Background: Diffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifyi...

In this phenomenographic qualitative research, the aim is to learn about the conceptions of university professors about the university. The study was carried out with 20 university professors: 10 from the School of Social Sciences and 10 from the School of Science and Technology of University of Évora with an average age of 54 years and over 20 yea...

With the raising of environmental concerns regarding pollution, interest in monitoring air quality is increasing. However, air pollution data is mostly originated from a limited number of government-owned sensors, which can only capture a small fraction of reality. Improving air quality coverage in-volves reducing the cost of sensors and making dat...

Industrial furnaces consume a large amount of energy and their operating points have a major influence on the quality of the final product. Designing a tool that analyzes the combustion process, fluid mechanics and heat transfer and assists the work done during energy audits is then of the most importance.

For mammogram image analysis, feature extraction is the most crucial step when machine learning techniques are applied. In this paper, we propose RMID (Radon-based Multi-resolution Image Descriptor), a novel image descriptor for mammogram mass classification, which perform efficiently without any clinical information. For the present experimental f...

Air pollution is a rising concern, demanding for low cost air quality monitoring systems. In this paper, we describe the back-end of an air quality monitoring system, developed in the context of the NanoSen-AQM project, a project with the goal of creating a real-time system that allows for a cost-effective, distributed and ubiquitous air quality mo...

This work is part of the ongoing efforts under the Audit Furnace project to develop a reduced-order model (ROM) that allows for fast analysis of combustion, fluid flow and heat transfer processes that occur inside industrial furnaces. The following approach was used: (i) division of the furnace in a limited number of zones and equipment; (ii) ident...

microRNAs (miRNAs) are short, non-coding, endogenous RNA molecule that regulates messenger RNAs (mRNAs) at the post-transcriptional level. The discovery of this regulatory relationship between miRNAs and mRNAs is an important research direction. In this regard, our method proposed an integrated approach to identify the mRNA targets of dysregulated...

Industrial furnaces consume large amounts of energy and their operating points have a major influence on the quality of the final product. Designing a tool that analyzes the combustion process, fluid mechanics and heat transfer and assists the energy audit work is then of the most importance. This work proposes a hybrid composite model for such a t...

Industrial furnaces consume a large amount of energy and their operating points have a major influence on the quality of the final product. Designing a tool that analyzes the combustion process, fluid mechanics and heat transfer and assists the work done during energy audits is then of the most importance. This work proposes a hybrid model for such...

This work presents the method developed in the scope of the "Audit Furnace" project to support the manufacturing industry in understanding the energy efficiencies of its furnaces and to identify strategies for the continuous improvement of its processes. A digital representation to support the development, calibration, and training of a physical-ba...

The precision agriculture approach can be used in grazing management. The underlying principle is the same, understanding the variability of a system components, in this case pasture and animals, in order to adapt supply to demand. And there is no more variable agricultural system than grazing systems. Preserving the dynamic balance among pasture a...

Grazing in extensive beef farming systems is often manage in an empirical way based on past experience and on the visual appreciation of animal behavior and forage potential. Records of entrances and exits of the animals in the paddocks in a regular basis are rare. However, knowing the occupation period and the animal density, when coupled with bio...

Imaging biomarkers are becoming important in both research and clinical studies. This study is focused on developing measures of tumour mean, fractal dimension, homogeneity, energy, skewness and kurtosis that reflect the values of the pharmacokinetic (PK) parameters within the breast tumours, evaluate those using clinical data, and investigate thei...

Background Recent advancement in bioinformatics offers the ability to identify informative genes from high dimensional gene expression data. Selection of informative genes from these large datasets has emerged as an issue of major concern among researchers. Objective Gene functionality and regulatory mechanisms can be understood through the analys...

Neste trabalho apresenta-se uma metodologia desenvolvida no âmbito do projeto "Audit Furnace" para apoiar a indústria transformadora na compreensão das eficiências encontradas nos seus fornos bem como na identificação de estratégias de melhoria contínua dos seus processos. Aliando auditorias feitas a várias unidades industriais com a modelação de m...

This paper describes a novel fast algorithm for automatic segmentation of islets of Langerhans and β-cell region from pancreas histological images for automatic identification of glucose intolerance. Here, LUV colour space and connected component analysis are used on 134 images among which 56 are of normal and rest 78 are of prediabetic type. The p...

In contemporary societies, higher education institutions face the impact of globalization, which is mainly demanding in imposing and shaping ethical practices. While higher education systems and dynamics cannot be understood apart from this broader context, its primary focus seems to remain as equal as ever: the creation of knowledge-based societie...

The precision agriculture approach can be used in grazing management. The underlying principle is the same, understanding the variability of a system components, in this case pasture and animals, in order to adapt supply to demand. And there is no more variable agricultural system than grazing systems. Preserving the dynamic balance among pasture a...

Background Identification of differentially expressed genes, i.e., genes whose transcript abundance level differs across different biological or physiological conditions, was indeed a challenging task. However, the inception of transcriptome sequencing (RNA-seq) technology revolutionized the simultaneous measurement of the transcript abundance leve...

Presentation of a smartphone App for grazing management

This paper focuses on dynamic environments for mobile robots and proposes a new mapping method combining hidden Markov models (HMMs) and Markov random fields (MRFs). Grid cells are used to represent the dynamic environment. The state change of every grid cell is modelled by an HMM with an unknown transition matrix. MRFs are applied to consider the...

MicroRNAs (miRNAs) are a class of 22-nucleotide endogenous noncoding RNAs, and plays an important role in regulating target gene expression via repressing translation or promoting messenger RNAs (mRNA) degradation. Numerous researchers have found that miRNAs have serious effects on cancer. Therefore, study of mRNAs and miRNAs together through the i...

This paper focuses on mapping problem with known robot pose in static environments and proposes a Gaussian random field-based log odds occupancy mapping (GRF-LOOM). In this method, occupancy probability is regarded as an unknown parameter and the dependence between parameters are considered. Given measurements and the dependence, the parameters of...

Microarray technology has been developed and applied in different biological context, especially for the purpose of monitoring the expression levels of thousands of genes simultaneously. In this regard, analysis of such data requires sophisticated computational tools. Hence, we confined ourselves to propose a tool for the analysis of microarray dat...

Conservation and restoration of architectural heritage requires knowledge of the conservation state of its constituent materials in order to provide recommendations concerning the intervention plan, and the materials and the techniques to be used. Information on physical, chemical and mechanical characterization of materials, when available, is usu...

Subtle structural differences can be observed in the islets of Langerhans region of microscopic image of pancreas cell of the rats having normal glucose tolerance and the rats having pre-diabetic (glucose intolerant) situations. This paper proposes a way to automatically segment the islets of Langerhans region from the histological image of rat’s p...

Robot mapping is the basic work for robot navigation and path planning. Static map is also important to deal with dynamic environment. Occupancy grid maps are used to represent the environment. This paper focuses on the dependence between grid cells. We assume that if one point of the map is free, then the neighbors are likely to be free. This know...

Resumo—Os serviços baseados na Internet têm registado um crescimento contínuo e acelerado nos últimos anos, dependendo o seu sucesso, em larga medida, da qualidade de serviço (QoS) prestada. A sociedade moderna tornou-se fortemente dependente da Internet e dos vários serviços nela disponibilizados. Neste artigo é apresentado um sistema original de...

Nos últimos anos a Universidade de Évora (UEvora) tem vindo a efetuar uma aposta estratégica no desenvolvimento de um sistema de informação que integre a monitorização e melhoria continuada das componentes académicas e de investigação com as componentes de garantia de qualidade e de gestão. Neste sentido, a UEvora tem desenvolvido, desde 1993, mode...

This paper reports a work in progress, the training of a Support Vector Machine model to detect faults in an experimental water supply canal. The work took place at the experimental canal of Núcleo de Hidráulica e Controlo de Canais at the Universidade de Évora. The main objective is to identify faults in the water depth sensors and to detect unaut...

The brain tissue classification from magnetic resonance images provides valuableinsight in neurological research study. A significant number ofcomputational methods havebeen developed for pixel classification of magnetic resonancebrain images. Here, we haveshown a comparative study of various machine learning methods for this. The results ofthe cla...

The observation of histological sections of pancreas under microscope enables the evaluation of structural differences in pancreatic cells, between rats with normal glucose tolerance and rats with glucose intolerance (pre-diabetic)condition. However, the subtle changes in islets of Langerhans structures resulting from pre-diabetic condition, and th...

The problem of reconfiguration of the control sys- tem to mitigate the effects of actuator faults in a water delivery canal is addressed in this paper. When a fault in an actuator is detected and isolated, the controller is reconfigured by changing the set of manipulated and process variables and using a different controller, associated to a differ...

This paper addresses the problem of the development of a distributed linear quadratic Gaussian (LQG) controller for a water delivery canal. The control structure proposed relies on a set of LQG control agents interconnected through a communication network. Each of these local control agents controls a canal reach made of a pool and the correspondin...

In this paper, an ensemble classifier, namely RotaSVM, is proposed that uses recently developed rotational feature selection approach and Support Vector Machine classifier cohesively. The RotaSVM generates the number of predefined outputs of Support Vector Machines. For each Support Vector Machine, the training data is generated by splitting the fe...

The knowledge of vegetation land cover over time is essential for an appropriate grazing management in any free range animal production system. Ground vegetation has traditionally been monitored using visual methods that produce estimates of percentage covered/bared soil, green/senescent vegetation and also grasses/forbs occurrences. Visual methods...

The crucial points in machine learning research are that how to develop new classification methods with strong mathematic background and/or to improve the performance of existing methods. Over the past few decades, researches have been working on these issues. Here, we emphasis the second point by improving the performance of well-known supervised...

This work addresses the problem of designing fault tolerant controllers for a water delivery canal that tackle actuator faults. The type of faults considered consists in blocking one of the gates. The detection of the fault is made by comparing the gate position command with the actual (measured) gate position. Both centralized and distributed cont...

This work addresses the problem of tuning the parameters of a distributed model predictive control algorithm (DMPC) applied to the control of water level in a water delivery canal. The D-SIORHC algorithm considered is based on distributed MPC control agents that incorporate stability constraints. Coordination of the different controllers is achieve...

In this work, a novel distributed MPC algorithm, denoted D-SIORHC, is applied to upstream local control of a pilot water delivery canal. The D-SIORHC algorithm is based on MPC control agents that incorporate stability constraints and communicate only with their adjacent neighbors in order to achieve a coordinated action. Experimental results that s...

This work addresses the design of distributed LQG controllers for water delivery canals that include feedforward from local farmer water consumptions. The proposed architecture consists of a network of local control agents, each connected to one of the canal pools and sharing information with their neighbors in order to act in a coordinated way. In...

This article addresses the problem of controlling pool levels in a water delivery canal using a novel cooperative distributed MPC control algorithm that incorporates stability constraints. According to a distributed control strategy, a local control agent is associated to all canal gates (actuators). In order to achieve cooperative action, each con...

RESUMO: O artigo apresenta um canal automático, particularmente vocacionado para o estudo, experimentação e a demonstração de sistemas de controlo automático para canais e dos respectivos algoritmos. Faz-se uma apresentação sumária do controlo automático de canais e do sistema SCADA, instalado para a supervisão e controlo do canal automático. O art...

This article deals with a histological problem by using image processing and feature extraction in images of renal tissues of rats and their classification through various methods such as: Bayesian inference, decision trees and support vector machines.