No abstract

Artificial neural network (ANN) based prediction of the response of a microbend fiber optic sensor is presented. To the best of our knowledge no similar work has been previously reported in the literature. Parallel corrugated plates with three deformation cycles, 6 mm thickness of the spacer material and 16 mm mechanical periodicity between deformations were used in the microbend sensor. Multilayer Perceptron (MLP) with different training algorithms, Radial Basis Function (RBF) network and General Regression Neural Network (GRNN) are used as ANN models in this work. All of these models can predict the sensor responses with considerable errors. RBF has the best performance with the smallest mean square error (MSE) values of training and test results. Among the MLP algorithms and GRNN the Levenberg-Marquardt algorithm has good results. These models successfully predict the sensor responses, hence ANNs can be used as useful tool in the design of more robust fiber optic sensors.

No abstract

One way of improving the performance of a cellular network is to build a second tier (layer) called the macrocell on top of the existing single-tier called the microcell. Multi-tier cellular networks provide mobility solutions to both the high speed and low speed users. Since dropping an ongoing call when a mobile user moves from one cell to another is an undesirable event, several techniques have been previously proposed to solve this problem. In a cellular network, this problem can be solved by delaying the handoff call using a queue, until it's able to maintain a channel.In this paper, a new Markov model is developed for a two-tier cellular network having a FIFO queue in the macrocell, which takes into account the mobility and the queue time of users. Later, the analytical model of the cellular system is solved and its performance is calculated. The results are then compared with previously proposed models.

No abstract