Repository logo
 
Loading...
Profile Picture
Person

Melicio, Fernando

Search Results

Now showing 1 - 10 of 12
  • A shuffled complex evolution algorithm for the examination timetabling problem
    Publication . Leite, Nuno; Melicio, Fernando; Rosa, Agostinho C.
    In this work two instances of the examination timetabling problem are studied and solved using memetic algorithms. The first is the uncapacitated single-epoch problem instance. In the second problem instance two examination epochs are considered, with different durations. The memetic algorithm, named Shuffled Complex Evolution Algorithm, uses a population organized into sets called complexes which evolve independently using a recombination and local search operators. Population diversity is preserved by means of the recombination operator and a special solution update mechanism. Experimental evaluation was carried out on the public uncapacitated Toronto benchmarks (single epoch) and on the ISEL-DEETC department examination benchmark (two epochs). Results show that the algorithm is competitive on the Toronto benchmarks, attaining a new lower bound on one benchmark. In the ISEL-DEETC benchmark, the algorithm attains a lower cost when compared with the manual solution.
  • In-plane displacement and strain image analysis
    Publication . Almeida, Graça; Melicio, Fernando; Biscaia, Hugo; Chastre, Carlos; Fonseca, José Manuel
    Measurements in civil engineering load tests usually require considerable time and complex procedures. Therefore, measurements are usually constrained by the number of sensors resulting in a restricted monitored area. Image processing analysis is an alternative way that enables the measurement of the complete area of interest with a simple and effective setup. In this article photo sequences taken during load displacement tests were captured by a digital camera and processed with image correlation algorithms. Three different image processing algorithms were used with real images taken from tests using specimens of PVC and Plexiglas. The data obtained from the image processing algorithms were also compared with the data from physical sensors. A complete displacement and strain map were obtained. Results show that the accuracy of the measurements obtained by photogrammetry is equivalent to that from the physical sensors but with much less equipment and fewer setup requirements. © 2015Computer-Aided Civil and Infrastructure Engineering.
  • A hybrid shuffled frog-leaping algorithm for the university examination timetabling problem
    Publication . Leite, Nuno; Melicio, Fernando; Rosa, Agostinho C.
    The problem of examination timetabling is studied in this work. We propose a hybrid solution heuristic based on the Shuffled Frog-Leaping Algorithm (SFLA) for minimising the conflicts in the students's exams. The hybrid algorithm, named Hybrid SFLA (HSFLA), improves a population of frogs (solutions) by iteratively optimising each memeplex, and then shuffling the memeplexes in order to distribute the best performing frogs by the memeplexes. In each iteration the frogs are improved based on three operators: crossover and mutation operators, and a local search operator based on the Simulated Annealing metaheuristic. For the mutation and local search, we use two well known neighbourhood structures. The performance of the proposed method is evaluated on the 13 instances of the Toronto datasets from the literature. Computational results show that the HSFLA is competitive with state-of-the-art methods, obtaining the best results on average in seven of the 13 instances.
  • The influence of noise in the neurofeedback training sessions in student athletes
    Publication . Domingos, Christophe; Caldeira, Higino da Silva; Miranda, Marco; Melicio, Fernando; Rosa, Agostinho; Pereira, José Gomes
    Considering that athletes constantly practice and compete in noisy environments, the aim was to investigate if performing neurofeedback training in these conditions would yield better results in performance than in silent ones. A total of forty-five student athletes aged from 18 to 35 years old and divided equally into three groups participated in the experiment (mean +/- SD for age: 22.02 +/- 3.05 years). The total neurofeedback session time for each subject was 300 min and were performed twice a week. The environment in which the neurofeedback sessions were conducted did not seem to have a significant impact on the training's success in terms of alpha relative amplitude changes (0.04 +/- 0.08 for silent room versus 0.07 +/- 0.28 for noisy room, p = 0.740). However, the group exposed to intermittent noise appears to have favourable results in all performance assessments (p = 0.005 for working memory and p = 0.003 for reaction time). The results of the study suggested that performing neurofeedback training in an environment with intermittent noise can be interesting to athletes. Nevertheless, it is imperative to perform a replicated crossover design.
  • Dynamic peripheral visual performance relates to alpha activity in soccer players
    Publication . Nan, Wenya; Migotina, Daria; Wan, Feng; Lou, Chin Ian; Rodrigues, João; Semedo, João; Vai, Mang I; Pereira, José Gomes; Melicio, Fernando; Rosa, Agostinho C. da
    Many studies have demonstrated the relationship between the alpha activity and the central visual ability, in which the visual ability is usually assessed through static stimuli. Besides static circumstance, however in the real environment there are often dynamic changes and the peripheral visual ability in a dynamic environment (i.e., dynamic peripheral visual ability) is important for all people. So far, no work has reported whether there is a relationship between the dynamic peripheral visual ability and the alpha activity. Thus, the objective of this study was to investigate their relationship. Sixty-two soccer players performed a newly designed peripheral vision task in which the visual stimuli were dynamic, while their EEG signals were recorded from Cz, O1, and O2 locations. The relationship between the dynamic peripheral visual performance and the alpha activity was examined by the percentage-bend correlation test. The results indicated no significant correlation between the dynamic peripheral visual performance and the alpha amplitudes in the eyes-open and eyes-closed resting condition. However, it was not the case for the alpha activity during the peripheral vision task: the dynamic peripheral visual performance showed significant positive inter-individual correlations with the amplitudes in the alpha band (8-12 Hz) and the individual alpha band (IAB) during the peripheral vision task. A potential application of this finding is to improve the dynamic peripheral visual performance by up-regulating alpha activity using neuromodulation techniques.
  • Extending IOPT nets with a module construct
    Publication . Ribeiro, José; Melicio, Fernando; Gomes, Luís
    Input-output place-transition nets (IOPT nets) is a Petri net based formalism targeted for the development of embedded systems controllers. It is an extension to common place-transition Petri nets, introducing constructs to model the communication between the controller and the environment and using an execution semantics assuring a deterministic behavior. However, IOPT nets and the supporting tools framework -the IOPT-Tools-do not have a mechanism to support model structuring. Since models are flat, all the graphical components and annotations are visualized in the same page. Systems with several dozens of nodes become very difficult to manage. In this paper a modular construct for IOPT nets is presented, helping to manage large-scale systems, and the reuse of model components across projects. The algebraic specification of the model is provided and an example illustrating the concept is presented.
  • Road lane detection for autonomous robot guidance
    Publication . Coutinho, César Valentino Ribeiro; Melicio, Fernando
    Computational Vision stands as the most comprehensive way of knowing the surrounding environment. Accordingly to that, this study aims to present a method to obtain from a common webcam, environment information to guide a mobile differential robot through a path similar to a roadway.
  • High-level Petri nets modules for embedded controllers design
    Publication . Ribeiro, José; Melicio, Fernando; Gomes, Luís
    Modular design is crucial to manage large-scale systems and to support the divide-and-conquer development approach. It allows hierarchical representations and, therefore, one can have a system overview, as well as observe component details. Petri nets are suitable to model concurrent systems, but lack on structuring mechanisms to support abstractions and the composition of sub-models, in particular when considering applications to embedded controllers design. In this paper we present a module construct, and an underlying high-level Petri net type, to model embedded controllers. Multiple interfaces can be declared in a module, thus, different instances of the same module can be used in different situations. The interface is a subset of the module nodes, through which the communication with the environment is made. Module places can be annotated with a generic type, overridden with a concrete type at instance level, and constants declared in a module may have a new value in each instance.
  • A fast simulated annealing algorithm for the examination timetabling problem
    Publication . Leite, Nuno; Melicio, Fernando; Rosa, Agostinho
    The timetabling problem involves the scheduling of a set of entities (e.g., lectures, exams, vehicles, or people) to a set of resources in a limited number of time slots, while satisfying a set of constraints. In this paper, a new variant of the simulated annealing (SA) algorithm, named FastSA, is proposed for solving the examination timetabling problem. In the FastSA's acceptance criterion, each exam selected for scheduling is only moved (and the associated move is evaluated) if that exam had any accepted moves in the immediately preceding temperature bin. Ten temperature bins were formed, ensuring that an equal number of evaluations is performed by the FastSA, in each bin. It was observed empirically that if an exam had zero accepted movements in the preceding temperature bin, it is likely to have few or zero accepted movements in the future, as it is becoming crystallised. Hence, the moves of all exams that are fixed along the way are not evaluated no more, yielding a lower number of evaluations compared to the reference algorithm, the standard SA. A saturation degree-based heuristic, coupled with Conflict-Based Statistics in order to avoid any exam assignment looping effect, is used to construct the initial solution. The proposed FastSA and the standard SA approaches were tested on the 2nd International Timetabling Competition (ITC 2007) benchmark set. Compared to the SA, the FastSA uses 17% less evaluations, on average, and a maximum of 41% less evaluations on one instance. In terms of solution cost, the FastSA is competitive with the SA algorithm attaining the best average fitness value in four out of twelve instances, while requiring less time to execute. In terms of average comparison with the state-of-the-art approaches, the FastSA improves on one out of twelve instances, and ranks third among the five best algorithms. The article's main impact comprises the points: (i) proposal of a new algorithm (FastSA) which is able to attain a reduced computation time (and number of evaluations computed) compared to the standard SA, (ii) demonstration of the FastSA capabilities on a NP-Complete timetabling problem, (iii) comparison with state-of-the-art approaches where the FastSA is able to improve the best known result on a benchmark instance. Due to the variety of problems solved by expert and intelligent systems using SA-based algorithms, we believe that the proposed approach will open new research paths with the creation of new algorithms that explore the space in a more efficient way.
  • An exploratory study of training intensity in EEG neurofeedback
    Publication . Esteves, Inês; Nan, Wenya; Alves, Cristiana P.; Calapez, Alexandre; Melicio, Fernando; Rosa, Agostinho
    Neurofeedback training has shown benefits in clinical treatment and behavioral performance enhancement. Despite the wide range of applications, no consensus has been reached about the optimal training schedule. In this work, an EEG neurofeedback practical experiment was conducted aimed at investigating the effects of training intensity on the enhancement of the amplitude in the individual upper alpha band. We designed INTENSIVE and SPARSE training modalities, which differed regarding three essential aspects of training intensity: the number of sessions, the duration of a session, and the interval between sessions. Nine participants in the INTENSIVE group completed 4 sessions with 37.5 minutes each during consecutive days, while nine participants in the SPARSE group performed 6 sessions of 25 minutes spread over approximately 3 weeks. As a result, regarding the short-term effects, the upper alpha band amplitude change within sessions did not significantly differ between the two groups. Nonetheless, only the INTENSIVE group showed a significant increase in the upper alpha band amplitude. However, for the sustained effects across sessions, none of the groups showed significant changes in the upper alpha band amplitude across the whole course of training. The findings suggest that the progression within session is favored by the intensive design. Therefore, based on these findings, it is proposed that training intensity influences EEG self-regulation within sessions. Further investigations are needed to isolate different aspects of training intensity and effectively confirm if one modality globally outperforms the other.