Percorrer por autor "Bernardino, Eugénia"
A mostrar 1 - 10 de 12
Resultados por página
Opções de ordenação
- Bio&Med Search – A Platform to Help Health Professionals about PharmacogeneticsPublication . Rocha, Andreia; Vilhena, Joana; Bernardino, Anabela; Bernardino, Eugénia; Gonçalves, Alexandrino; Ascenso, Rita M.T.Bio&Med Search is an online platform that allows to get data from different databases; it permits the collection of information about genetic research, namely genetic variants and drug side effects associated with genetic variability. Based on the concept of pharmacogenetics people respond differently to medicines according to their genes’ variants. Nowadays, health professionals should be more and more aware of the origin of several drug severe side effects. This proposed web platform will allow the improvement and better prescription practices by health professionals, from physicians to pharmaceuticals. With Bio&Med Search, it will be possible to access scientific information and data about genetic variants associated to certain diseases and drugs, to better suggest and adjust the patient’s medication according to its diagnostic and chemical composition of drugs and may suggest genetic tests. In this way, the error of prescription of drugs decreases and the quality of life of the patient may be improved, avoiding already described side effects. It will be possible to compare studies and literature associated to each drug, chemical composition, gene, gene variants and diseases.
- CROSS-PLATFORM DEVELOPMENT FOR E-COMMERCEPublication . Vieira, Leandro; Bernardino, Anabela; Bernardino, EugéniaElectronic commerce is generally seen as a competitor for physical stores, however, this paper proposes a solution where they work side-by-side to improve the in-store customer experience. An application directed for store retailers was created with the cross-platform framework React Native, making it available for Android, iOS, and the web. Using thebe of their interest, and place orders, providing the customer with a unique and faster shopping experience.
- Exploring SQL injection vulnerabilities using artificial bee colonyPublication . Baptista, Kevin; Bernardino, Anabela; Bernardino, EugéniaOver the last couple of decades, there has been an enormous growth in technologies and services available on the internet. This growth must take security into account, although due to the increase in complexity of systems this is not an easy task. Nowadays, hardly any organization may say with certainty that their system is secure. The Open Web Application Security listed “Injection” as the most security risk for web applications in 2020. There are many automated tools to assist professionals in the field, in order to identify this vulnerability. However, keeping these tools up to date has proven to be a challenge. Therefore, there has been some interest in applying Artificial Intelligence (AI) in this field. In this paper, we propose an approach to detect SQL injection vulnerabilities in the source code, using Artificial Bee Colony (ABC).
- Genetic and local search algorithms applied to balanced communication networksPublication . Bernardino, Eugénia; Moreira Bernardino, Anabela; Sánchez-Pérez, Juan M.; Gómez-Pulido, Juan A.; Vega-Rodríguez, Miguel A.In this paper we describe the application of different heuristics to optimise large communication networks. We use Iterated Local Search (ILS), Tabu Search (TS), Simulated Annealing (SA) and Genetic Algorithm (GA) to minimise the link cost to form balanced communication networks. This paper makes a comparison among the effectiveness of ILS, TS, SA and GA on solving large communication networks. Simulation results verify the effectiveness of these algorithms.
- A hybrid ant colony optimization algorithm for solving the terminal assignment problemPublication . Bernardino, Eugénia; Bernardino, Anabela; Sánchez-Pérez, Juan Manuel; Gómez-Pulido, Juan Antonio; Vega-Rodríguez, Miguel AngelThe past two decades have witnessed tremendous research activities in optimization methods for communication networks. One important problem in communication networks is the Terminal Assignment Problem. This problem involves determining minimum cost links to form a network by connecting a collection of terminals to a collection of concentrators. In this paper, we propose a Hybrid Ant Colony Optimization Algorithm to solve the Terminal Assignment Problem. We compare our results with the results obtained by the standard Genetic Algorithm, the Tabu Search Algorithm and the Hybrid Differential Evolution Algorithm, used in literature.
- A Hybrid Differential Evolution Algorithm for Solving the Terminal Assignment ProblemPublication . Bernardino, Eugénia; Bernardino, Anabela; Sánchez-Pérez, Juan Manuel; Gómez-Pulido, Juan Antonio; Vega-Rodríguez, Miguel AngelThe field of communication networks has witnessed tremendous growth in recent years resulting in a large variety of combinatorial optimization problems in the design and in the management of communication networks. One of these problems is the terminal assignment problem. The task here is to assign a given set of terminals to a given set of concentrators. In this paper, we propose a Hybrid Differential Evolution Algorithm to solve the terminal assignment problem. We compare our results with the results obtained by the classical Genetic Algorithm and the Tabu Search Algorithm, widely used in literature.
- Solving the non-split weighted ring arc-loading problem in a resilient packet ring using particle swarm optimizationPublication . Bernardino, Anabela; Bernardino, Eugénia; Sánchez-Pérez, Juan Manuel; Gómez-Pulido, Juan Antonio; Vega-Rodríguez, Miguel AngelMassive growth of the Internet traffic in last decades has motivated the design of high-speed optical networks. Resilient Packet Ring (RPR), also known as IEEE 802.17, is a standard designed for the optimized transport of data traffic over optical fiber ring networks. Its design is to provide the resilience found in SONET/SDH networks but instead of setting up circuit oriented connections, providing a packet based transmission. This is to increase the efficiency of Ethernet and IP services. In this paper, a weighted ring arc-loading problem (WRALP) is considered which arises in engineering and planning of the RPR systems (combinatorial optimization NP- complete problem). Specifically, for a given set of non-split and uni-directional point-to-point demands (weights), the objective is to find the routing for each demand (i.e., assignment of the demand to either clockwise or counter-clockwise ring) so that the maximum arc load is minimized. This paper suggests four variants of Particle Swarm Optimization (PSO), combined with a Local Search (LS) method to efficient non-split traffic loading on the RPR. Numerical simulation results show the effectiveness and efficiency of the proposed methods.
- Solving the Regenerator Location Problem using bioinspired algorithmsPublication . Pessoa, Rodrigo; Ferreira, Pedro Henrique; Bernardino, Anabela; Bernardino, Eugénia; Piedade, Maria Beatriz Guerra daNas redes óticas, a força de um sinal ótico deteriora-se à medida que fica mais longe da fonte, devido a deficiências de transmissão na fibra. Ou seja, a distância a que um sinal ótico pode ser enviado sem perder ou deteriorar a informação é limitada. É por isso necessário regenerar os sinais periodicamente, utilizando regeneradores. Dada uma rede ótica, o problema da localização de regeneradores procura que o subconjunto de regeneradores seja instalado a um custo mínimo, de modo a que cada par de nós possa comunicar entre si. Neste artigo são aplicados algoritmos baseadosna natureza para resolver este problema. Foram testadas 480instâncias diferentes para cada um dos algoritmos e os resultados comprovam a sua eficiência em termos de tempo e qualidade das soluções.
- Solving the Ring Loading Problem Using Genetic Algorithms with Intelligent Multiple OperatorsPublication . Bernardino, Anabela M.; Bernardino, Eugénia M.; Sánchez-Pérez, Juan M.; Gómez-Pulido, Juan A.; Vega-Rodríguez, Miguel A.; Moreira Bernardino, Anabela; Bernardino, EugéniaPlanning optical communication networks suggests a number of new optimization problems, most of them in the field of combinatorial optimization. We address here the Ring Loading Problem. The objective of the problem is to find a routing scheme such that the maximum weighted load on the ring is minimized. In this paper we consider two variants: (i) demands can be split into two parts, and then each part is sent in a different direction; (ii) each demand must be entirely routed in either of the two directions, clockwise or counterclockwise. In this paper, we propose a genetic algorithm employing multiple crossover and mutation operators. Two sets of available crossover and mutation operators are established initially. In each generation a crossover method is selected for recombination and a mutation method is selected for mutation based on the amount fitness improvements achieve over a number of previous operations (recombinations/mutations). We use tournament selection for this purpose. Simulation results with the different methods implemented are compared.
- Solving the Terminal Assignment Problem Using a Local Search Genetic AlgorithmPublication . Bernardino, Eugénia M.; Bernardino, Anabela M.; Sánchez-Pérez, Juan M.; Gómez-Pulido, Juan A.; Vega-Rodríguez, Miguel A.; Bernardino, Eugénia; Moreira Bernardino, AnabelaTerminal assignment is an important issue in telecommunication networks optimization. The task here is to assign a given collection of terminals to a given collection of concentrators. The main objective is to minimize the link cost to form a network. This optimization task is an NP-complete problem. The intractability of this problem is a motivation for the pursuits of a local search genetic algorithm that produces approximate, rather than exact, solutions. In this paper, we explore one of the most successful emerging ideas combining local search with population-based search. Simulation results verify the effectiveness of the proposed method. The results show that our algorithm provides good solutions in a better running time.