A fuzzy system is a rule-based system that uses human experts' knowledge to make a particular decision, while fuzzy modeling refers to the identification process of the fuzzy parameters. To generate the fuzzy parameters automatically, an optimization method is needed. One of the suitable methods provides the Firefly Algorithm (FA). FA is a natureinspired algorithm that uses fireflies' behavior to interpret data. This study explains in detail how fuzzy modeling works by using FA for detecting phishing. Phishing is an unsettled security problem that occurs in the world of internet connected computers. In order to experiment with the proposed method for the security threats, a database of phishing websites and SMS from different sources were used. As a result, the average accuracy for the phishing websites dataset achieved 98.86%, while the average value for the SMS dataset is 97.49%. In conclusion, both datasets show the best result in terms of the accuracy value for fuzzy modeling by using FA.

In this work, the optimization of biochemical systems production is performed by using a hybrid method of Newton competitive genetic algorithm is presented. The proposed method works by representing the biochemical systems as a generalized mass action model, where it leads to the process of solving a complex non-linear equations system. The optimization process becomes hard and difficult when it involves multi-objective problem. This is where two objectives, namely the maximize the biochemical systems production and minimize the total amount of chemical concentrations involves. To deal with the problem, this work proposed a hybrid method of the Newton method, genetic algorithm, and competitive co-evolutionary algorithm. The proposed method was experimentally applied on the benchmark biochemical systems and the experimental results showed that the proposed method achieved better results compared to the existing works.

No abstract

Metabolic engineering is attentive about the alteration properties of metabolic pathways with the point of improving the generation of a few metabolics of intrigue. An essential range of metabolic engineering, the development is quite useful in the parameter identification/estimation of kinetic parameters in the metabolic pathway. The development of metabolic kinetic model requires a detailed information of the initial concentration of enzymes, metabolites, co-metabolites, kinetic parameters and the cell condition. However, kinetic parameters play a significant role in building dynamic model. Kinetic parameters identification is usually used to reduce the errors in the simulation of the model or in the estimation of the model's enzymes and metabolites. Moreover, the inverse problem, irreversible problem and the large scale attributes are the main issues to be considered for optimizing and estimating large scale kinetic parameters. This paper highlights the challenges inherent in the identification/estimation of kinetic parameters and the methods applied in solving the problems in the kinetic metabolic model of E. Coli following comprehensive analyses and discussions.

The conventional Particle Swarm Optimization (PSO) still has weaknesses in finding optimal solutions especially in a dynamic environment. Therefore, in this paper we proposed a Global best Local Neighborhood in particle swarm optimization in order to solve the optimum solution in dynamic environment. Based on the experimental results of 50 datasets, show that GbLN-PSO has the ability to find the quality solution in dynamic environment.