Mauro Castelli

Universidade NOVA de Lisboa | NOVA · NOVA IMS

Geometric semantic genetic programming (GSGP) is a popular form of GP where the effect of crossover and mutation can be expressed as geometric operations on a semantic space. A recent study showed that GSGP can be hybridized with a standard gradient-based optimized, Adam, commonly used in training artificial neural networks.We expand upon that work...

Semantic segmentation consists of classifying each pixel of an image and constitutes an essential step towards scene recognition and understanding. Deep convolutional encoder–decoder neural networks now constitute state-of-the-art methods in the field of semantic segmentation. The problem of street scenes’ segmentation for automotive applications c...

Multiple Sclerosis (MS) is an autoimmune demyelinating disease characterised by changes in iron and myelin content. These biomarkers are detectable by Quantitative Susceptibility Mapping (QSM), an advanced Magnetic Resonance Imaging technique detecting magnetic properties. When analysed with radiomic techniques that exploit its intrinsic quantitati...

Some optimization problems are difficult to solve due to a considerable number of local optima, which may result in premature convergence of the optimization process. To address this problem, we propose a novel heuristic method for constructing a smooth surrogate model of the original function. The surrogate function is easier to optimize but maint...

The Competitive Intelligence (CI) construct must be scientifically defined, characterised, empirically validated, and accurately measured to grow in science and business. This study aims at elevating the accuracy of the empirical validation of the CI construct suggested and confirmed by Madureira, Popovic, & Castelli1,2 to serve as the scientific f...

This work aims to investigate the application of a Local Search (LS) enhanced Genetic Programming (GP) algorithm to the control scheme’s design task. Inclusive Genetic Programming (IGP) is chosen as the GP algorithm since it proved successful on the considered task. IGP is enhanced with the Operators Gradient Descent (OPGD) approach, which consists...

Geometric Semantic Geometric Programming (GSGP) is one of the most prominent Genetic Programming (GP) variants, thanks to its solid theoretical background, the excellent performance achieved, and the execution time significantly smaller than standard syntax-based GP. In recent years, a new mutation operator, Geometric Semantic Mutation with Local S...

Competitive Intelligence (CI) is vital for sustaining the performance of organisations in an increasingly volatile, uncertain, complex, and ambiguous (VUCA) world. However, the impact of CI on performance is proportional to its maturity level. The article aims to review and integrate the existing literature on Competitive Intelligence Maturity Mode...

Desde os anos 50 do século passado que o desempenho académico tem sido foco de interesse por parte de investigadores e decisores políticos. No entanto, apenas recentemente os métodos de ciência de dados começaram a ser aplicados de forma mais sistemática a este tema. Este trabalho utiliza os dados dos exames nacionais de matemática e português da p...

Evolutionary algorithms (EAs) are a family of optimization algorithms inspired by the Darwinian theory of evolution, and Genetic Algorithm (GA) is a popular technique among EAs. Similar to other EAs, common limitations of GAs have geometrical origins, like premature convergence, where the final population’s convex hull might not include the global...

BACKGROUND Medical imaging is an indispensable tool widely employed in the healthcare industry and medical field. With the emergence of deep learning, medical imaging analysis has entered a new era where disease diagnosis and therapy assessment can be faster and less prone to error. Although there has been a significant increase in scientific resea...

Full-reference image quality measures are a fundamental tool to approximate the human visual system in various applications for digital data management: from retrieval to compression to detection of unauthorized uses. Inspired by both the effectiveness and the simplicity of hand-crafted Structural Similarity Index Measure (SSIM), in this work, we p...

This study explores the contribution of various drivers of attainment in secondary education in Portugal. We propose a model explaining the influence of students, teachers, and parents' traits on high school achievement, measured by the self-reported Math and Portuguese final grades of 220 students. Using PLS-SEM, we show that previous achievement...

Neovascular age-related macular degeneration (nAMD) is one of the major causes of irreversible blindness and is characterized by accumulations of different lesions inside the retina. AMD biomarkers enable experts to grade the AMD and could be used for therapy prognosis and individualized treatment decisions. In particular, intra-retinal fluid (IRF)...

Determining the size of objects (static or moving) appearing in the aerial imagery can foster targets’ reconnaissance and support rapid decision-making during the flight. This paper presents a novel method, based on previous consolidated approaches, to measure the dimensions of any target appearing in an aerial image, either vertically (height), ho...

The top image shows a set of scales, which are intended to bring to mind the ideas of balance and fair experimentation which are the focus of our article on genetic programming benchmarks in this issue. Image by Elena Mozhvilo and made available under the Unsplash license on https://unsplash.com/photos/j06gLuKK0GM.

Consumer-level UAVs are often employed for surveillance, especially in urban areas. Within this context, human recognition via estimation of biometric traits, like body height, is of pivotal relevance. Previous studies confirmed that the pinhole model could be used for this purpose, but only if the accurate distance between the aerial camera and th...

Neovascular age-related macular degeneration (nAMD) is one of the major causes of irreversible blindness and is characterized by accumulations of different fluids inside the retina. An early detection and activity monitoring of predominately three types of fluids, namely intra-retinal fluid (IRF), sub-retinal fluid (SRF), and pigment epithelium det...

Geometric Semantic Genetic Programming (GSGP) is a popular form of GP where the effect of crossover and mutation can be expressed as geometric operations on a semantic space. A recent study showed that GSGP can be hybridized with a standard gradient-based optimized, Adam, commonly used in training artificial neural networks. We expand upon that wor...

Polyp detection through colonoscopy is a widely used method to prevent colorectal cancer. The automation of this process aided by artificial intelligence allows faster and improved detection of polyps that can be missed during a standard colonoscopy. In this work, we propose to implement various object detection algorithms for polyp detection. To i...

The manuscript presents a tool to estimate and predict data accuracy in hospitality by means of automated machine learning (AutoML). It uses a tree-based pipeline optimization tool (TPOT) as a methodological framework. The TPOT is an AutoML framework based on genetic programming, and it is particularly useful to generate classification models, for...

Academic achievement is of great interest to education researchers and practitioners. Several academic achievement determinants have been described in the literature, mostly identified by analyzing primary (sample) data with classic statistical methods. Despite their superiority, only recently have machine learning methods started to be applied sys...

This paper applies deep learning to the prediction of Portuguese high school grades. A deep multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is to demonstrate the adequacy of deep learning as a quantitative explanatory paradigm when compared with the classical econometrics approach. The results enc...

Given growing clinical needs, in recent years Artificial Intelligence (AI) techniques have increasingly been used to define the best approaches for survival assessment and prediction in patients with brain tumors. Advances in computational resources, and the collection of (mainly) public databases, have promoted this rapid development. This narrati...

Polyp detection through colonoscopy is a widely used method to prevent colorectal cancer. The automation of this process aided by artificial intelligence allows faster and improved detection of polyps that can be missed during a standard colonoscopy. In this work, we propose implementing different object detection algorithms for polyp detection. To...

Most real-world optimization problems are difficult to solve with traditional statistical techniques or with metaheuristics. The main difficulty is related to the existence of a considerable number of local optima, which may result in the premature convergence of the optimization process. To address this problem, we propose a novel heuristic method...

Geometric Semantic Genetic Programming (GSGP) is a state-of-the-art machine learning method based on evolutionary computation. GSGP performs search operations directly at the level of program semantics, which can be done more efficiently than operating at the syntax level like most GP systems. Efficient implementations of GSGP in C++ exploit this f...

Among the evolutionary methods, one that is quite prominent is genetic programming. In recent years, a variant called geometric semantic genetic programming (GSGP) was successfully applied to many real-world problems. Due to a peculiarity in its implementation, GSGP needs to store all its evolutionary history, i.e., all populations from the first o...

Among the evolutionary methods, one that is quite prominent is Genetic Programming, and, in recent years, a variant called Geometric Semantic Genetic Programming (GSGP) has shown to be successfully applicable to many real-world problems. Due to a peculiarity in its implementation, GSGP needs to store all the evolutionary history, i.e., all populati...

Understanding the determinants of academic achievement (AA) is crucial for virtually every stakeholder interested in personal development and individual and societal wellbeing. Extensive research in several areas, such as education, economics, or psychology, has addressed this topic, identifying a vast number of determinants that impact high school...

The growing production of digital content and its dissemination across the worldwide web require efficient and precise management. In this context, image quality assessment measures (IQAMs) play a pivotal role in guiding the development of numerous image processing systems for compression, enhancement, and restoration. The structural similarity ind...

This research focuses attention on over-indebtedness (i.e., recurrent incapability to repaying credits) and its risk factors, among Portuguese households in the context of the recent European sovereign debt crisis. Different theoretical accounts of consumers decision behavior and risk of becoming over-indebted vary (among other aspects) on the emph...

For a discipline to prosper in business and science, it must be thoroughly defined, characterized, and measured. Notably, the definition must reflect its praxis. This study aims to fill this void by empirically validating the Competitive Intelligence unified view and modular definition proposed by Madureira, Popovic, and Castelli (2021). The choice...

Risk analysis and scenario testing are two of the core activities carried out by economists at central banks. With the increasing adoption of machine learning to enhance decision-support systems, and the amount of collected data spiking, institutions provide countless use-cases for the application of these innovative technologies. Consequently, in...

The purpose of an effective liquidity risk assessment policy is to ensure that any given credit institution can meet its cash flow obligations, even factoring in the uncertainty caused by external factors. As part of the Supervisory Review and Evaluation Process (SREP), the European Central Bank (ECB) has determined this assessment should take into...

The study aimed to identify the core defining dimensions and descriptors of Competitive Intelligence (CI) to provide a unified view and approach. The authors used a mixed-methods approach to derive meta-inferences from the sequential integration of quantitative and qualitative methods. Five defining core dimensions and one hundred descriptors, twen...

Geometric semantic genetic programming (GSGP) is a recent variant of genetic programming. GSGP allows the landscape of any supervised regression problem to be transformed into a unimodal error surface, thus it has been applied only to this kind of problem. In a previous paper, we presented a novel variant of GSGP for binary classification problems...

Since ancient times there has been recognition of music's therapeutic powers, inherent in the properties of sound and its effects on human beings at a psychophysical level. Literature showed the development of therapeutic applications of music in numerous clinical settings. Music-listening itself can qualify as an effective therapeutic means within...

Cell counting is a frequent task in medical research studies. However, it is often performed manually; thus, it is time-consuming and prone to human error. Even so, cell counting automation can be challenging to achieve, especially when dealing with crowded scenes and overlapping cells, assuming different shapes and sizes. In this paper, we introdu...

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies tha...

Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be affected by low voxel statistics in regions of interest, increasing the samp...

Several contemporaneous image processing and computer vision systems rely upon the full-reference image quality assessment (IQA) measures. The single-scale structural similarity index (SS-SSIM) is one of the most popular measures, and it owes its success to the mathematical simplicity, low computational complexity, and implicit incorporation of Hum...

This study focuses on the machine learning bias when predicting teacher grades. The experimental phase consists of predicting the student grades of 11th and 12thgrade Portuguese high school grades and computing the bias and variance decomposition. In the base implementation, only the academic achievement critical factors are considered. In the seco...

In the crowded environment of bio-inspired population-based metaheuristics, the Salp Swarm Optimization (SSO) algorithm recently appeared and immediately gained a lot of momentum. Inspired by the peculiar spatial arrangement of salp colonies, which are displaced in long chains following a leader, this algorithm seems to provide an interesting optim...

This study assessed the short-term effects of conventional (i.e., human-composed) and algorithmic music on the relaxation level. It also investigated whether algorithmic compositions are perceived as music and are distinguishable from human-composed music. Three hundred twenty healthy volunteers were recruited and randomly allocated to two groups w...

Bone fractures are one of the main causes to visit the emergency room (ER); the primary method to detect bone fractures is using X-Ray images. X-Ray images require an experienced radiologist to classify them; however, an experienced radiologist is not always available in the ER. An accurate automatic X-Ray image classifier in the ER can help reduce...

Machine learning (ML) has revolutionised data analysis over the past decade. Like innumerous other industries heavily reliant on accurate information, banking supervision stands to benefit greatly from this technological advance. The objective of this review is to provide a comprehensive walk-through of how the most common ML techniques have been a...

In the past few decades, metaheuristics have demonstrated their suitability in addressing complex problems over different domains. This success drives the scientific community towards the definition of new and better-performing heuristics and results in an increased interest in this research field. Nevertheless, new studies have been focused on dev...

We investigate the use of Genetic Programming (GP) as a convolutional predictor for missing pixels in images. The training phase is performed by sweeping a sliding window over an image, where the pixels on the border represent the inputs of a GP tree. The output of the tree is taken as the predicted value for the central pixel. We consider two topo...

Bone fractures are among the main reasons for emergency room admittance and require a rapid response from doctors. Bone fractures can be severe and can lead to permanent disability if not treated correctly and rapidly. Using X-ray imaging in the emergency room to detect fractures is a challenging task that requires an experienced radiologist, a spe...

Geometric Semantic Genetic Programming (GSGP) is a state-of-the-art machine learning method based on evolutionary computation. GSGP performs search operations directly at the level of program semantics, which can be done more efficiently then operating at the syntax level like most GP systems. Efficient implementations of GSGP in C++ exploit this f...

In the crowded environment of bio-inspired population-based meta-heuristics, the Salp Swarm Optimization (SSO) algorithm recently appeared and immediately gained a lot of momentum. Inspired by the peculiar spatial arrangement of salp colonies, which are displaced in long chains following a leader, this algorithm seems to provide interesting optimiz...

Several interesting libraries for optimization have been proposed. Some focus on individual optimization algorithms, or limited sets of them, and others focus on limited sets of problems. Frequently, the implementation of one of them does not precisely follow the formal definition, and they are difficult to personalize and compare. This makes it di...

In machine learning, ensemble techniques are widely used to improve the performance of both classification and regression systems. They combine the models generated by different learning algorithms, typically trained on different data subsets or with different parameters, to obtain more accurate models. Ensemble strategies range from simple voting...

Ever since the worldwide demand for gambling services started to spread, its expansion has continued steadily. To wit, online gambling is a major industry in every European country, generating billions of Euros in revenue for commercial actors and governments alike. Despite such evidently beneficial effects, online gambling is ultimately a vast soc...

This article uses an anonymous 2014–15 school year dataset from the Directorate-General for Statistics of Education and Science (DGEEC) of the Portuguese Ministry of Education as a means to carry out a predictive power comparison between the classic multilinear regression model and a chosen set of machine learning algorithms. A multilinear regressi...

Regularization is frequently used in supervised machine learning to prevent models from overfitting. This paper tackles the problem of regularization in genetic programming. We apply, for the first time, soft target regularization, a method recently defined for artificial neural networks, to genetic programming. Also, we introduce a novel measure o...

The classification of the musculoskeletal images can be very challenging, mostly when it is being done in the emergency room, where a decision must be made rapidly. The computer vision domain has gained increasing attention in recent years, due to its achievements in image classification. The convolutional neural network (CNN) is one of the latest...

This paper focuses on how the height of a target can be swiftly estimated using images acquired by a digital camera installed into moving platforms, such as unmanned aerial vehicles (UAVs). A pinhole camera model after distortion compensation was considered for this purpose since it does not need extensive processing nor vanishing lines. The pinhol...

This research examines how artificial intelligence may contribute to better understanding and to overcome over-indebtedness in contexts of high poverty risk. This research uses Automated Machine Learning (AutoML) in a field database of 1654 over-indebted households to identify distinguishable clusters and to predict its risk factors. First, unsuper...

We exploit evolutionary computation to optimize the handcrafted Structural Similarity method (SSIM) through a datadriven approach. We estimate the best combination of luminance, contrast and structure components, as well as the sliding window size used for processing, with the objective of optimizing the similarity correlation with human-expressed...

Featured Application: Aims to execute novel optimisation algorithms such as whale optimisation and lion optimisation to find the optimal Virtual_Ms on cloud environment as well as executing our model in different applications. Abstract: Cloud computing has a significant role in healthcare services, especially in medical applications. In cloud compu...

The classification of histopathology images requires an experienced physician with years of experience to classify the histopathology images accurately. In this study, an algorithm was developed to assist physicians in classifying histopathology images; the algorithm receives the histopathology image as an input and produces the percentage of cance...

Predicting air quality is a complex task due to the dynamic nature, volatility, and high variability in time and space of pollutants and particulates. At the same time, being able to model, predict, and monitor air quality is becoming more and more relevant, especially in urban areas, due to the observed critical impact of air pollution on citizens...

Understanding academic achievement (AA) is one of the most global challenges, as there is evidence that it is deeply intertwined with economic development, employment, and countries' wellbeing. However, the research conducted on this topic grounds in traditional (statistical) methods employed in survey (sample) data. This paper presents a novel app...