Artificial neural networks (ANN) are widely used to classify high non-linear systems by using a set of input/output data. Moreover, they are trained using several optimization methodologies and this paper presents a novel algorithm for training ANN through an earthquake optimization method. Usually, gradient optimization method is implemented for the training process, with perhaps the large number of iterations leading to slow convergence, and not always achieving the optimal solution. Since metaheuristic optimization methods deal with searching for weight values in a broad optimization space, the training computational effort is reduced and ensures an optimal solution. This work shows an efficient training process that is a suitable solution for detection of mobile phone usage while driving. The main advantage of training ANN using the Earthquake Algorithm (EA) lies in its versatility to search in a fine or aggressive way, which extends its field of application. Additionally, a basic example of a linear classification is illustrated using the proposal-training method, so the number of applications could be expanded to nano-sensors, such as reversible logic circuit synthesis in which a genetic algorithm had been implemented. The fine search is important for the studied logic gate emulation due to the small searching areas for the linear separation, also demonstrating the convergence capabilities of the algorithm. Experimental results validate the proposed method for smart mobile phone applications that also can be applied for optimization applications.
展开▼
