Rafael Stubs Parpinelli

• Dr
• Professor at Santa Catarina State University

Sulfur dioxide (\({{\textrm{SO}}_{2}}\)) is a pollutant primarily emitted through the combustion of fossil fuels and industrial activities, contributing significantly to environmental degradation and public health risks. Monitoring \({{\textrm{SO}}_{2}}\) deposition poses challenges due to spatial variability, technical complexities, and financial...

Accurately estimating atmospheric chloride deposition can offer important insights into metal corrosion. Corrosion of metals causes high associated costs in engineering work. Hence, there are standardized models to estimate the corrosivity of environments. One entry variable of such models is airborne salinity that comes from the sea, collected wit...

The design of new steel grades is a continuous pursuit in the metallurgical industry, aiming to develop lighter and stronger materials for diverse industries. This study explores the use of an ensemble of artificial neural networks, named EANN, to model the relationships between chemical composition, process parameters, and mechanical properties of...

Com o crescimento do número de aplicações no contexto da Internet Industrial (IIoT), surgem novos requisitos para atender as tarefas críticas com relação ao tempo de resposta. A Computação na Borda oferece uma alternativa em relação ao processamento dos dados na nuvem computacional, pois emprega recursos na borda da rede local, possibilitando o pro...

As aplicações têm requisitos diferentes em termos de largura de banda e atraso para entregar a qualidade de serviço esperada. Por esse e outros motivos, surgiram novos paradigmas como as redes definidas por software, que permitem o desenvolvimento de novas aplicações para programação dinâmica de dispositivos de roteamento na rede por meio de um dis...

In Evolutionary Algorithms, population diversity is a determinant factor for the quality of the final solutions. Due to diverse problem characteristics, many techniques face difficulties and converge prematurely in local optima. The maintenance of diversity allows the algorithm to explore the search space and efficiently achieve better results. Par...

The Protein Structure Prediction Problem is one of the most important and challenging open problems in Computer Science and Structural Bioinformatics. Accurately predicting protein conformations would significantly impact several fields, such as understanding proteinopathies and developing smart protein-based drugs. As such, this work has as its pr...

Computer vision-based parking lot management methods have been extensively researched upon owing to their flexibility and cost-effectiveness. To evaluate such methods authors often employ publicly available parking lot image datasets. In this study, we surveyed and compared robust publicly available image datasets specifically crafted to test compu...

Computer vision-based parking lot management methods have been extensively researched upon owing to their flexibility and cost-effectiveness. To evaluate such methods authors often employ publicly available parking lot image datasets. In this study, we surveyed and compared robust publicly available image datasets specifically crafted to test compu...

Cloud Computing popularization inspired the emergence of many new cloud service providers. The significant number of cloud providers available drives users to complex or even impractical choice of the most suitable one to satisfy his needs without automation. The Cloud Provider Selection (CPS) problem addresses that choice. Hence, this work present...

One of the most challenging problems in Bioinformatics is the finding of a protein conformation and it is known as the Protein Structure Prediction (PSP) problem. The main feature present in the AB off-lattice model is the use of polarity as the main driving force to guide the optimization process. The present work proposes an adaptive evolutionary...

Multimodal optimization can be divided into two main categories. The first focuses on finding only one global optimum, e.g., one peak, and the second focuses on finding multiple global optima, e.g., multiple peaks, and it is the focus of this work. The first category can be approached by single-solution and population-based metaheuristics, while in...

Face recognition (FR) applications have been intensively studied in the areas of Computer Vision specially with the wide use of bio-metrics as a method of security access. Hence, working on still images with multiple faces (SIMF) is still a challenge due to the diversity of features that may be present in the images and different conditions from wh...

Truss optimization is an important class of engineering problems, with better solutions allowing for reduced material use and reduced construction costs. Due to its complexity, meta-heuristic algorithms are often applied to this problem, since these algorithms require no prior knowledge of the search space, being built upon stochastic rules. The pr...

The development of steels requires multiples manufacturing steps and involves a high number of variables and non-linear processes. Although there are data-driven models used to predict such steels’ mechanical properties, their design often requires specialized Machine Learning knowledge, hampering the application of such models. In this paper, an A...

The use of fragment insertion in the protein structure prediction problem can be considered one of the most successful strategies to add problem-dependent information. The well known Rosetta suite provides two protocols for generating fragment libraries: Best and Quota. The first aims to maximize a given score function, while the second aims add fr...

The efficient management of resources after a disaster, must take place within a short time and efficiently. Therefore, resource scheduling protocol which shares resources among the victims, respecting time constraints, is decisive. In disaster scenarios, communication infrastructure is usually damaged and a commonly used solution for ensuring conn...

Financial news has been proven to be valuable source of information for the evaluation of stock market volatility. Most of the attention has been given to social media platforms, while news from vehicles such as newspapers are not as widely explored. Newspapers provide, although in a smaller volume, more reliable information than social media platf...

Proteins are base molecules present in live organisms. The study of their structures and functions is of considerable importance for many application fields, particularly for the pharmaceutical area. However, predict the structure of a protein is considered a complex problem. As optimizing methods for this problem have high execution time, a parall...

A estampagem de peça automotiva é o processo de criar algumas partes metálicas que são utilizadas para compor a estrutura de automóveis como, por exemplo, o capô de um carro. O problema se caracteriza como problema de otimização multiobjetivo porque, para cada peça, é possível encontrar uma combinação de variáveis que impactam diferentes critérios...

A função que uma proteína exerce está diretamente relacionada com a sua estrutura tridimensional. Porém, para a maior parte das proteínas atualmente sequenciadas ainda não se conhece sua forma estrutural nativa. Este artigo propõe a utilização do algoritmo de Evolução Diferencial (DE) desenvolvido na plataforma NVIDIA CUDA aplicado ao modelo 3D AB...

In the cold rolling of flat steel strips, electric energy consumption is one of the highest expenses. Predicting the power requirements according to the line and product conditions can significantly impact the energy cost and, thus, on the business’s profitability. This paper proposes predicting the power requirements of a tandem cold rolling mill...

Several works in GIScience propose approaches to identify general motion patterns through the analysis of objects’ trajectories. However, they are not suitable to identify functional relationships in scenarios where domain-dependent motion behaviors exist. In this work, we explore the identification of a particular pattern found in team-based invas...

Differential Evolution (DE) is a powerful and versatile algorithmfor numerical optimization, but one of its downsides is its numberof parameters that need to be tuned. Multiple techniques have beenproposed to self-adapt DE’s parameters, with L-SHADE being oneof the most well established in the literature. This work presentsthe A-SHADE algorithm, wh...

Face Recognition (FR) systems are still facing significant challenges when different image issues, such as variation of illumination, pose, expression, and occlusion, are present in captured images. In many situations, it is only possible to obtain One Sample Per Person (OSPP) for training, representing a challenging real-world condition. The propo...

The Protein Structure Prediction (PSP) problem is one of the most significant open problems in bioinformatics. In the AB off-lattice model, the protein sequence is labeled as ‘A’ or ‘B’ according to the amino acid classification of being hydrophobic or hydrophilic. It has been widely explored in the literature because polarity is one of the main dr...

The main difficulty encountered by population-based approaches in multimodal problems is their loss of diversity while converging to an optimum. Also, it is known that parameters play a big role in the performance of metaheuristics. Hence, in this paper two variations of the NCDE algorithm for multimodal optimization are proposed. The first version...

Vehicle routing problems require efficient computational solutions to reduce operational costs. Therefore, this paper presents a benchmark analysis of Max-Min Ant System (MMAS) combined with local search applied to the Asymmetric and Dynamic Travelling Salesman Problem with Moving Vehicle (ADTSPMV). Different from the well known ADTSP, in the movin...

Population-based search algorithms, such as the Differential Evolution approach, evolve a pool of candidate solutions during the optimization process and are suitable for massively parallel architectures promoted by the use of GPUs. Hence, this paper proposes a GPU-based self-adaptive Differential Evolution employing the jDE mechanism to control it...

The two major groups representing biologically inspired algorithms are Swarm Intelligence (SI) and Evolutionary Computation (EC). Both SI and EC share common features such as the use of stochastic components during the optimization process and various parameters for configuration. The setup of parameters in swarm and in evolutionary algorithms has...

Low-power and Lossy network (LLN) is commonly deployed in Internet of Things applications. It consists of a considerable amount of devices, also known as motes, with sensory capacity and wireless connectivity geographically spread in a wide area. Such devices face limitations in terms of energy, memory and processing. A common topology in LLN is a...

This paper presents the proposal of a mathematical model for ischemic stroke, which is implemented with multiagent systems, in a general purpose tool known as NetLogo. The objective of this simulator is to obtain a partial view of the stroke for didactic purposes and to motivate future works for the treatment of the disease. Given the importance of...

A popularização da Internet das Coisas resultou na implantação de diversos tipos de sensores em diferentes áreas, como monitoramento do ambiente, indústrias, energia, e outros. Esse grande volume de dispositivos que estão conectados à internet, gera quantidades massivas de dados a serem analisados. Muitos desses dados são ordenados pelo tempo, tais...

A wide range of approaches for 2D face recognition (FR) systems can be found in the literature due to its high applicability and issues that need more investigation yet which include occlusion, variations in scale, facial expression, and illumination. Over the last years, a growing number of improved 2D FR systems using Swarm Intelligence and Evolu...

Este artigo propõe uma abordagem para realizar agrupamento de dados utilizando o Algoritmo de Busca por Organismos Simbióticos (SOS) em uma arquitetura Hadoop MapReduce, chamado de MRCSOS. O algoritmo SOS é responsável pela exploração do espaço de busca enquanto a arquitetura Hadoop provê escalabilidade através do paralelismo. A principal contribui...

The Protein Structure Prediction problem is currently one of the most challenging open problems in Bioinformatics being a NP-Complete problem. In this work, a Multistage Simulated Annealing (MSA) employing different levels of detail for the potential energy function is applied using the Rosetta framework. The backbone and centroid coordinates model...

The success of cloud computing paradigm has leveraged the emergence of a large number of new companies providing cloud computing services. This fact has been making difficult, for consumers, to choose which cloud providers will be the most suitable to attend their computing needs, satisfying their desired quality of service. To qualify such provide...

The two major groups representing biologically inspired algorithms are Swarm Intelligence (SI) and Evolutionary Computation (EC). Both SI and EC share common features such as the use of stochastic components during the optimization process and various parameters for configuration. The setup of parameters in swarm and in evolutionary algorithms has...

The Protein Structure Prediction (PSP) is one of the most challenging problems in Bioinformatics. In computationally terms, the PSP is classified as a NP-complete problem. In this way, metaheuristics became very interesting to find good solutions in a plausible processing time. In this work we propose a distinct Differential Evolution approach that...

Este artigo apresenta um algoritmo gen´etico para escalonamento de recursos em descoberta de servic¸os em MANETs operando em cen´arios de emergˆencia. Os recursos a serem compartilhados s˜ao por exemplo, ambulˆancias ou carros de apoio. Com um modelo eficiente de escalonamento de recursos pretende-se maximizar o n´umero de atendimento as v´ıtimas n...

This paper presents a genetic algorithm for resource scheduling in service discovery to MANETs operating in emergency scenarios. The shared resources could be ambulances or support cars. Through an appropriate model for scheduling resources, we aim to attend the greatest number of victims in the affected area. Performance evaluation results on the...

The protein structure prediction is considered as one of the most important open problems in biology and bioinformatics due the huge amount of plausible shapes that a protein can assume. The objective of this paper is to apply the Differential Evolution (DE) algorithm employing two simple diversification strategies known as generation gap and Gauss...

Symbiotic relationships are one of several phenomena that can be observed in nature. These relationships consist of interactions between organisms and can lead to benefits or damages to those involved. In an optimization context, symbiotic relationships can be used to perform information exchange between populations of candidate solutions to a give...

Workshop em Bioinformática

Symbiotic relationships are one of several phenomena that can be observed in nature. These relationships consist of interactions between organisms and can lead to benefits or damages to those involved. In an optimization context, symbiotic relationships can be used to perform information exchange between populations of candidate solutions to a give...

In this work, a vision system has been developed using a frontal camera to monitor the driver, enabling to recognize the use of a cell phone while driving. It is estimated that 80% of car crashes and 65% of near collisions involved drivers who were inattentive in traffic for three seconds before the event. Five videos in real environments were gene...

The Protein Folding Problem (PFP) is considered one of the most important open challenges in Biology and Bioinformatics. This paper describes the application of a parallel ecology-inspired algorithm (pECO) to a hard problem related to the PFP: the protein structure reconstruction from Contact Maps. The fitness function proposed includes information...

The algorithms that are available in this release are: Artificial Bee Colony Algorithm, Particle Swarm Optimization, Differential Evolution, and Biogeographic-based Optimization. If you use this code, pls cite one of the following works: 1. PARPINELLI, R.S.; LOPES, H.S. Biological Plausibility in Optimization: An Ecosystemic View. International...

Realizar tarefas de mineração de dados, como agrupamento, pode ser complexo devido alta dimensionalidade e volume dos dados minerados. Esse artigo propõe uma abordagem de agrupamento de dados utilizando Algoritmo Inspirado em Organismos Simbióticos (SOS) projetado na arquitetura MapReduce e analisa a evolução da qualidade dos agrupa-mentos, usando...

Resumo. Este trabalho propõe uma abordagem para analisar a escalabilidade da arquitetura Hadoop MapReduce em problemas de agrupamento de dados. O algoritmo de otimizaçotimizaç˜otimização utilizado será o Algoritmo Inspirado em Organismos Simbióticos (SOS) e diferentes funçfunç˜funções de agrupamento serão empregadas. O objetivó e explorar de forma...

Realizar tarefas de mineração de dados, como agrupamento, pode ser complexo devido alta dimensionalidade e volume dos dados minerados. Esse artigo propõe uma abordagem de agrupamento de dados utilizando Algoritmo Inspirado em Organismos Simbióticos (SOS) projetado na arquitetura MapReduce e analisa a evolução da qualidade dos agrupamentos, usando a...

The literature shows a wide variety of pathfinding algorithms for navigation environments. These algorithms are widely used in games, robotics, GPS and many other applications. This paper aims to analyze how the classics algorithms Breadth-First Search, Search with Uniform Cost, A * and Weighted A * behave in an environment with various costs. It p...

"Mining of Massive Data Bases Using Hadoop MapReduce and Bio-inspired algorithms: A Systematic Review" Resumo: A Área de Mineração de Dados tem sido utilizada em diversas áreas de aplicação e visa extrair conhecimento através da análise de dados. Nas últimas décadas, inúmeras bases de dados estão tendenciando a possuir grande volume, alta velocida...

Model-Based Predictive Control techniques have been applied industrially since the 1970s, presenting favorable characteristics. Among them, it can be mentioned the treatment of process constraints and optimization considering the output error with respect to the reference and the used energy. Usually, formulations based on linear models of the plan...

A Natureza é uma fonte inesgotável de inspiração para o desenvolvimento de novas tecnologias. Entre os diferentes fenômenos naturais, as relações simbióticas inspirou recentemente o desenvolvimento de uma abordagem para otimização de problemas complexos. Chamada de Algoritmo de Busca por Organismos Simbióticos (\textit{Symbiotic Organisms Search},...

This paper presents a population-based approach to the Variable Neighbourhood Search algorithm, named PRVNS. The main contribution of the proposed algorithm, in addition to evolve a population of individuals, is that each individual adapts its neighborhood variations autonomously. This autonomous neighborhood control allows individuals to intensify...

Although widely used with satisfactory results, linear control systems may not be suitable for complex and nonlinear processes. Thus, nonlinear optimization algorithms are a possible solution for those systems. This paper presents a comparative study between the use of a predictive controller with optimization by Differential Evolution and the line...

In this paper the well-known 0-1 Multiple Knapsack Problem (MKP) is approached by an adaptive Binary Differential Evolution (aBDE) algorithm. The MKP is a NP-hard optimization problem and the aim is to maximize the total profit subjected to the total weight in each knapsack that must be less than or equal to a given limit. The aBDE self adjusts two...

Nature exhibits extremely diverse, dynamic, robust, complex and fascinating phenomena and, since long ago, it has been a great source of inspiration for solving hard and complex problems in computer science. Hence, the search for plausible biologically inspired ideas, models and computational paradigms always drew the interest of computer scientist...

It is estimated that 80% of crashes and 65% of near collisions involved drivers inattentive to traffic for three seconds before the event. This paper develops an algorithm for extracting characteristics allowing the cell phones identification used during driving a vehicle. Experiments were performed on sets of images with 100 positive images (with...

A natureza tem sido uma grande fonte de inspiração para o desenvolvimento de abordagens computacionais para otimização. Dois grandes grupos que representam esta classe de algoritmos biologicamente inspirados são a Inteligência de Enxame e a Computação Evolutiva. Tais algoritmos são chamados de metaheurísticas e são reconhecidos como abordagens efic...

This paper introduces an adaptive Binary Differential Evolution (aBDE) that self adjusts two parameters of the algorithm: perturbation and mutation rates. The well-known 0-1 Multiple Knapsack Problem (MKP) is addressed to validate the performance of the method. The MKP is a NP-hard optimization problem and the aim is to maximize the total profit su...

It is estimated that 80% of crashes and 65% of near collisions involved drivers inattentive to traffic for three seconds before the event. This paper develops an algorithm for extracting characteristics allowing the cell phones identification used during driving a vehicle. Experiments were performed on sets of images with 100 positive images (with...

This work presents a new evolutionary algorithm based on the standard harmony search strategy, called population-based harmony search PBHS. Also, this work provides a parallelisation method for the proposed PBHS by using graphical processing units GPU, allowing multiple function evaluations at the same time. Experiments were done using a benchmark...

This paper compares the performance of four swarm intelligence algorithms for the optimization of a hard bioinformatic problem: the protein structure prediction problem (PSP). The PSP envolved the protein folding that is the process by which polypeptide chains are transformed into compact structures that perform biological functions. In this work,...

Curve fitting is a classical problem in several areas, and the choice of parameters can drastically change the results obtained. Optimizing the parameters is a complex task, and there are many works in the literature applying nature inspired algorithms to solve this problem. A common observation in these works is that they minimize only the error o...

The Multiple Knapsack Problem (MKP) is a well-known NP-hard combinatorial optimisation problem [1] and its goal is to maximize the profit of items chosen to fulfil a set of knapsacks, subjected to constraints of capacity. The problem can be formulated as max(n i=1 (P i · X i)), subject to m j (W ij · X i) ≤ C j with X i ∈ {0, 1}. Where n is number...

Most swarm intelligence algorithms were devised for continuous optimization problems. However, they have been adapted for discrete optimization as well with applications in different domains. This survey aims at providing an updated review of research of swarm intelligence algorithms for discrete optimization problems, comprising combinatorial or b...

This paper applies an ecology-inspired algorithm (ECO) to solve a complex problem from bioinformatics. The ecological-inspired algorithm represents a new perspective to develop cooperative evolutionary algorithms. Different algorithms are applied to compose the computational ecosystem, both homogeneously and heterogeneously. The aim is to search lo...