No abstract

No abstract

A neural network auto regressive with exogenous input (NNARX) model is used to predict the indoor temperature of a residential building. Firstly, the optimal regressor of a linear ARX model is identified by minimising Akaike's final prediction error (FPE). This regressor is then used as the input vector of a fully connected feedforward neural network with one hidden layer of ten units and one output unit. Results show that the NNARX model outperforms the linear model considerably: the sum of the squared error (SSE) is 15.0479 with the ARX model and 2.0632 with the NNARX model. The optimal network topology is subsequently determined by pruning the fully connected network according to the optimal brain surgeon (OBS) strategy. With this procedure near 73% of connections were removed and, as a result, the performance of the network has been improved: the SSE is equal to 0.9060.

No abstract

The Ant Colony Optimizat ion (ACO) algorith m is used as a multi-object ive optimization technique to size a most popular analog circuit, the CMOS operational amp lifier (Op-A mp). The work consist of finding the more convenient transistors sizes, including the channel widths and lengths, in o rder to meet or reach the specified requirements such as the voltage gain Av, the Co mmon Mode Rejection Ratio CM RR, the die area A, the power consumption P and the Slew Rate SR. SPICE simulat ions are used to strengthen and to validate the obtained sizing/performances.