Felipe Campelo

University of Bristol | UB · School of Engineering Mathematics and Technology

We introduce a phylogeny-aware framework for predicting linear B-cell epitope (LBCE)-containing regions within proteins. Our approach leverages evolutionary information by using a taxonomic scaffold to build models trained on hierarchically structured data. The resulting models present performance equivalent or superior to generalist methods, despi...

Computational predictors of immunogenic peptides, or epitopes, are traditionally built based on data from a broad range of pathogens without consideration for taxonomic information. While this approach may be reasonable if one aims to develop one-size-fits-all models, it may be counterproductive if the proteins for which the model is expected to ge...

The field of metaheuristics has a long history of finding inspiration in natural systems, starting from evolution strategies, genetic algorithms, and ant colony optimization in the second half of the 20th century. In the last decades, however, the field has experienced an explosion of metaphor-centered methods claiming to be inspired by increasingl...

Francisco Pereira Lobo, Giovanni Marques de Castro, and Felipe Campelo are part of an international team of collaborators that developed CALANGO, a comparative genomics tool to investigate quantitative genotype-phenotype relationships. Their Patterns article highlights how the tool integrates species-centric data to perform genome-wide search and d...

Living species vary significantly in phenotype and genomic content. Sophisticated statistical methods linking genes with phenotypes within a species have led to breakthroughs in complex genetic diseases and genetic breeding. Despite the abundance of genomic and phenotypic data available for thousands of species, finding genotype-phenotype associati...

Over recent decades, power distribution systems have been required to handle extreme events that are increasing in both frequency and intensity. In addition, there are novel technologies, planning strategies, and operational approaches. In this context, topological flexibility is a key aspect to allow distribution systems to accommodate all the sim...

Monkeypox is a disease caused by the Monkeypox virus (MPXV), a double-stranded DNA virus from genus Orthopoxvirus under family Poxviridae, that has recently emerged as a global health threat after decades of local outbreaks in Central and Western Africa. Effective epidemiological control against this disease requires the development of cheaper, fas...

Tissue testing used to assess the chemical contents in potato plants is considered laborious, time-consuming, destructive, and expensive. Ground-based sensors have been assessed to provide efficient information on nitrogen using leaf canopy reflectance. In potatoes, however, the main organ required for tissue testing is the petiole to estimate the...

During epidemics, data from different sources can provide information on varying aspects of the epidemic process. Serology-based epidemiologic surveys could be used to compose a consistent epidemic scenario. We assessed the seroprevalence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) IgG in serum samples collected from 7,837 blood...

Data availability in a wide variety of domains has boosted the use of Machine Learning techniques for knowledge discovery and classification. The performance of a technique in a given classification task is significantly impacted by specific characteristics of the dataset, which makes the problem of choosing the most adequate approach a challenging...

Background The identification of linear B-cell epitopes remains an important task in the development of vaccines, therapeutic antibodies and several diagnostic tests. Machine learning predictors are trained to flag potential epitope candidates for experimental validation and currently, most predictors are trained as generalist models using large, h...

Background The development of peptide-based diagnostic tests requires the identification of epitopes that are at the same time highly immunogenic and, ideally, unique to the pathogen of interest, to minimise the chances of cross-reactivity. Existing computational pipelines for the prediction of linear B-cell epitopes tend to focus exclusively on th...

The increasing availability of genomic, annotation, evolutionary and phenotypic data for species contrasts with the lack of studies that adequately integrate these heterogeneous data sources to produce biologically meaningful knowledge. Here, we present CALANGO, a phylogeny-aware comparative genomics tool that uncovers functional molecular converge...

Motivation: In silico identification of linear B-cell epitopes represents an important step in the development of diagnostic tests and vaccine candidates, by providing potential high-probability targets for experimental investigation. Current predictive tools were developed under a generalist approach, training models with heterogeneous data sets...

A new selection operator for genetic algorithms dedicated to combinatorial optimization, the Diversity Driven selection operator, is proposed. The proposed operator treats the population diversity as a second objective, in a multiobjectivization framework. The Diversity Driven operator is parameterless, and features low computational complexity. Nu...

We demonstrate improved performance in the classification of bioelectric data for use in systems such as robotic prosthesis control, by data fusion using low-cost electromyography (EMG) and electroencephalography (EEG) devices. Prosthetic limbs are typically controlled through EMG, and whilst there is a wealth of research into the use of EEG as par...

We demonstrate improved performance in the classification of bioelectric data for use in systems such as robotic prosthesis control, by data fusion using low-cost electromyography (EMG) and electroencephalography (EEG) devices. Prosthetic limbs are typically controlled through EMG, and whilst there is a wealth of research into the use of EEG as par...

This work presents a statistically principled method for estimating the required number of instances in the experimental comparison of multiple algorithms on a given problem class of interest. This approach generalises earlier results by allowing researchers to design experiments based on the desired best, worst, mean or median-case statistical pow...

We propose the cone epsilon-dominance approach to improve convergence and diversity in multiobjective evolutionary algorithms (MOEAs). A cone-eps-MOEA is presented and compared with MOEAs based on the standard Pareto relation (NSGA-II, NSGA-II*, SPEA2, and a clustered NSGA-II) and on the epsilon-dominance (eps-MOEA). The comparison is performed bot...

Multiobjective evolutionary algorithms based on decomposition (MOEA/D) represent a widely used class of population-based metaheuristics for the solution of multicriteria optimization problems. We introduce the MOEADr package, which offers many of these variants as instantiations of a component-oriented framework. This approach contributes for easie...

Recent studies on resource allocation suggest that some subproblems are more important than others in the context of the MOEA/D, and that focusing on the most relevant ones can consistently improve the performance of that algorithm. These studies share the common characteristic of updating only a fraction of the population at any given iteration of...

This work presents an image classification approach to EEG brainwave classification. The proposed method is based on the representation of temporal and statistical features as a 2D image, which is then classified using a deep Convolutional Neural Network. A three-class mental state problem is investigated, in which subjects experience either relaxa...

Tuning parameters is an important step for the application of metaheuristics to specific problem classes. In this work we present a tuning framework based on the sequential optimisation of perturbed regression models. Besides providing algorithm configurations with good expected performance, the proposed methodology can also provide insights on the...

This work presents an image classification approach to EEG brainwave classification. The proposed method is based on the representation of temporal and statistical features as a 2D image, which is then classified using a deep Convolutional Neural Network. A three-class mental state problem is investigated, in which subjects experience either relaxa...

This work presents a statistically principled method for estimating the required number of instances in the experimental comparison of multiple algorithms on a given problem class of interest. This approach generalises earlier results by allowing researchers to design experiments based on the desired best, worst, mean or median-case statistical pow...

Experimental comparisons of performance represent an important aspect of research on optimization algorithms. In this work we present a methodology for defining the required sample sizes for designing experiments with desired statistical properties for the comparison of two methods on a given problem class. The proposed approach allows the experime...

After the occurrence of faults in a radial distribution system, the load restoration problem consists in implementing a sequence of switch opening and closing operations such that the resulting network configuration restores services to the most loads in the shortest possible time. We formulate this optimization problem in terms of two complementar...

When a fault occurs in a power distribution network, energy utilities have limited time to define and run a restoration plan. While this problem is widely studied in the literature, existing works consider neither the work in parallel of multiple maintenance teams, nor the time taken by the teams to move between locations. In this paper, we address...

Tuning parameters is an important step for the application of metaheuristics to problem classes of interest. In this work we present a tuning framework based on the sequential optimization of perturbed regression models. Besides providing algorithm configurations with good expected performance, the proposed methodology can also provide insights on...

Purpose This paper aims to present a SPICE model to represent antennas in receiving mode. The model can be used to evaluate the performance of the antenna when it is coupled to several different nonlinear electric circuits. The proposed methodology is particularly suitable for rectenna applications, as it allows the analysis of different configurat...

Experimental comparisons of performance represent an important aspect of research on optimization algorithms. In this work we present a methodology for defining the required sample sizes for designing experiments with desired statistical properties for the comparison of two methods on a given problem class. The proposed approach allows the experime...

Multiobjective Evolutionary Algorithms based on Decomposition (MOEA/D) represent a widely used class of population-based metaheuristics for the solution of multicriteria optimization problems. We introduce the MOEADr package, which offers many of these variants as instantiations of a component-oriented framework. This approach contributes for easie...

This work introduces a heuristic for mixed integer programming (MIP) problems with binary variables, based on information obtained from differences between feasible solutions as well as solutions from the linear relaxation. This information is used to build a neighborhood that is explored as a sub‐MIP problem. The proposed heuristic is evaluated us...

This paper addresses the problem of planning and allocation of trucks in open-pit mines in terms of three conflicting objectives, and adapts three algorithms for its solution: NSGA-II, SPEA2, and a variant of the Pareto Iterated Local Search using Reduced Variable Neighborhood Search as its local exploration mechanism. Results on four different min...

We propose a technique for incorporating robustness as part of the search process of evolutionary multiobjective optimization algorithms. The proposed approach calculates the sensitivity of candidate solutions by solving a linear programming subproblem, defined by regression models fitted using points in the neighborhood of each candidate solution....

This paper discusses the use of self-organizing maps (SOM) for decision-making in multiobjec- tive design problems. Estimates of the Pareto-optimal solutions for a given problem are mapped onto a two- dimensional grid, where the distance between solutions is a measure of their similarity in the parameter space. By comparing the clustered points and...

This paper presents a systematic investigation of the effects of sixteen recombination operators for real-coded spaces on the performance of Differential Evolution. A unified description of the operators in terms of mathematical operations of vectors is presented, and a standardized implementation is provided in the form of an R package. The object...

Evolutionary multiobjective optimization is employed for designing the geometric configurations of winglets adapted to a base wing. Seven decision variables are employed for the winglet parameterization, and the wing-winglet transition region is modeled using Bezier surfaces. A case study is presented to illustrate the application of this technique...

Strategic asset management of transformer fleets in electrical power systems is a critical aspect for distribution utilities. In this study, an integrated framework for multicriteria asset management is presented. A multiobjective optimisation model is deployed, simultaneously minimising the maintenance costs and the predicted cost of unexpected fa...

This work presents theoretical results on the development of a statistical convergence criterion for evolutionary algorithms. An analytical formula is derived for the probability of success in isotropic Gaussian mutation operators over spherical functions, and statistical criteria are proposed for evaluating, with predefined confidence levels, the...

This paper presents a technique that incorporates preference information within the framework of multi-objective evolutionary algorithms for the solution of many-objective optimization problems. The proposed approach employs a single reference point to express the preferences of a decision maker, and adaptively biases the search procedure toward th...

This work presents a comparison of results obtained by different methods for the Multiobjective Open-Pit Mining Operational Planning Problem, which consists of dynamically and efficiently allocating a fleet of trucks with the goal of maximizing the production while reducing the number of trucks in operation, subject to a set of constraints defined...

This paper presents a fast shape optimization method for antennas using proper orthogonal decomposition (POD)-based model order reduction (MOR). In this method, the finite element region is subdivided into design and ambient regions. The former includes antennas, whose shapes are optimized, whereas the latter includes air and perfect matched layer....

This paper presents parameter and topology optimizations of wideband antennas for microwave energy harvesters based on finite difference time-domain computations. The antenna shapes are optimized to reduce return losses in a specific frequency band using micro-genetic algorithm. The shape parameters of a two-arm planar spiral antenna are optimized....

This work presents a differential evolution algorithm for combinatorial optimization, in which a set-based representation and operators define subproblems that are used to explore the search space. The proposed method is tested on the capacitated centered clustering problem.

The Island Model (IM) is a well known multi-population ap-proach for Evolutionary Algorithms (EAs). One of the crit-ical parameters for defining a suitable IM is the migration topology. Basically it determines the Migratory Flows (MF) between the islands of the model which are able to improve the rate and pace of convergence observed in the EAs cou...

Purpose – The purpose of this paper is to apply an Ant colony optimization approach for the solution of the topological design of interior permanent magnet (IPM) machines. Design/methodology/approach – The IPM motor design domain is discretized into a suitable equivalent graph representation and an Ant System (AS) algorithm is employed to achieve...

We present an adaption on the formulation for the vehicle routing problem with fixed delivery and optional collections, in which the simultaneous minimization of route costs and of collection demands not fulfilled is considered. We also propose a multiobjective version of the iterated local search (MOILS). The performance of the MOILS is compared w...

Differential evolution (DE) was originally designed to solve continuous optimization problems, but recent works have been investigating this algorithm for tackling combinatorial optimization (CO), particularly in permutation-based combinatorial problems. However, most DE approaches for combinatorial optimization are not general approaches to CO, be...

Finding Nash equilibria has been one of the early objectives of research in game theory, and still represents a challenge to this day. We introduce a multiobjective formulation for computing Pareto-optimal sets of mixed Nash equilibria in normal form games. Computing these sets can be notably useful in decision making, because it focuses the analys...

We examine the performance of four discrete differential evolution (DE) algorithms for the solution of capacitated vehicle routing problems (CVRPs). Twenty seven test instances are employed in the experimental analysis, with comparisons of final solution quality and time to convergence. The results indicate that two approaches presented significant...

This work explores the influence of three different dominance criteria, namely the Pareto-, epsilon-, and cone epsilon-dominance, on the performance of multiobjective evolutionary algorithms. The approaches are incorporated into two different algorithms, which are then applied to the solution of twelve benchmark problems from the ZDT and DTLZ famil...

In this paper, a new approach to the topology configuration problem in the Island Model (IM) is proposed. The mechanism proposed works with a pool of candidates for migration and the choice of immigrants is performed using the usual selection techniques of evolutionary algorithms. Computational tests on IM versions of the Differential Evolution sho...

Este capítulo apresenta uma abordagem multiobjetivo para o problema de roteamento de veículos com coleta seletiva, cujos objetivos são a minimização dos custos das rotas e das demandas de coletas não atendidas. Propõe-se uma estrutura de dados que melhor se ajusta ao problema, estruturas de vizinhanças que exploram ambos objetivos do problema e um...

This paper presents the optimization of a meander line antenna finite-element model by means of an adaptive genetic algorithm (GA). To search for optimal antenna configurations, the present method employs a GA with an adaptive method that adjusts the characteristics of its selection, crossover, and mutation operators in order to maintain a diverse...

In a Two-Level Reverse Distribution Network, products are returned from customers to manufacturers through collection and refurbishing sites. The costs of the reverse chain often overtake the costs of the forward chain by many times. With some known algorithms for the problem as reference, we propose a hybrid memetic algorithm that uses linear prog...

Reverse Distribution Networks are designed to plan the distribution of products from customers to manufacturers. In this paper, we study the problem with two-levels,with products transported from origination points to collection sites before being sent to a refurbishing site. The optimization of reverse distribution networks can reduce the costs of...

The Island Model (IM) is an important multi-population approach for improving the performance of Evolutionary Algorithms (EAs) when solving complex problems. One of the critical parameters for defining a suitable IM is the migration topology, which determines the migratory flows between sub-populations of the model. Despite the importance of this p...

Purpose The purpose of this paper is to present a graph representation of the design space that is suitable for the ant colony optimization (ACO) method in topology optimization (TO) problems. Design/methodology/approach The ACO is employed to obtain optimal routes in an equivalent graph representation of the discretized design space, with each ro...

In this paper, we analyze four dominance criteria in terms of their ability to adequately order sets of points in multi- and many-objective optimization problems. The use of relaxed and alternative dominance relationships has been an important tool for improving the performance of multiobjective evolutionary optimization algorithms, and their order...

Relaxed forms of Pareto dominance have been shown to be the most effective way in which evolutionary algorithms can progress towards the Pareto-optimal front with a widely spread distribution of solutions. A popular concept is the ε-dominance technique, which has been employed as an archive update strategy in some multiobjective evolutionary algori...

This paper presents parameter and topology optimization of inductor shapes using evolutionary algorithms. The goal of the optimization is to reduce the size of inductors satisfying the specifications on inductance values under weak and strong bias-current conditions. The inductance values are computed from the finite-element (FE) method taking magn...

We propose in this paper a new strategy for self-adaptation in multiobjective evolutionary algorithms, which is based on information obtained from the implicit distribution created by a chaotic differential mutation operator. This technique is used to develop a self-adaptive evolutionary algorithm for multiobjective optimisation, and its efficiency...

In this paper, we introduce an approach for the design of electromagnetic devices based on the use of estimation of distribution algorithms (EDAs), coupled with approximation-based local search around the most promising solutions. The main idea is to combine the power of EDAs in the solution of hard optimization problems with the faster convergence...

Topology optimization (TO) is a promising field for the design of industrial devices, since it can allow computational tools to develop creative solutions independently of initial topologies. However, the generation of smooth solutions, i.e., solutions that can be physically implemented, remains a challenge for most TO techniques available. In this...

A new hybrid methodology for the design of engineering devices is presented in this paper. This technique employs a topology optimization (TO) algorithm in order to obtain an initial design for a given device under consideration, followed by a parameterization routine which transforms the TO solution into a parametric model. Finally, this model is...

The m-AINet is a modified version of the artificial immune network algorithm for single-objective and multimodal optimization (opt-AINet), with constraint-handling capability and improvements aiming to reduce the computational effort required by the original algorithm. In this paper we extend this algorithm for multiobjective problems by using the...

This work analyzes the Real-coded Clonal Selection Algorithm (RCSA) for mono objective optimization in electro-magnetics. This algorithm presents a set of features enabling global search as well as the local improvement of the candidate solutions. An analysis of the sensitivity of the algorithm to its basic parameters shows that it is possible to s...

We utilize optimization algorithms inspired by the immune system for treating the mixed H2/H∞ control problem. Both precisely known systems and uncertain systems with polytopic uncertainties are investigated. For the latter, a novel methodology is proposed to compute the worst case norms within the polytope of matrices. This methodology consists in...

Purpose The paper introduces an evolutionary algorithm based on the artificial immune systems paradigm for topology optimization (TO) in 3D. Design/methodology/approach The 3D TO algorithm is described, and experimentally validated on an electromagnetic design problem. Findings The proposed method is capable of finding an optimal configuration fo...

This paper addresses the problem of electric distribution network expansion under condition of uncertainty in the evolution of node loads in a time horizon. An immune-based evolutionary optimization algorithm is developed here, in order to find not only the optimal network, but also a set of suboptimal ones, for a given most probable scenario. A Mo...

Evolutionary algorithms can benefit from their association with local search operators, giving rise to hybrid or memetic algorithms. The cost of the local search may be prohibitive, particularly when dealing with computationally expensive functions. We propose the use of local approximations in the local search phase of memetic algorithms for optim...