Electrical load forecasting formulation by a fast neural network

The objective of this work is to develop a methodology for electric load forecasting based on a neural network. Here, backpropagation algorithm is used with an adaptive process that based on fuzzy logic and using a decaying exponential function to avoid instability in the convergence process. This methodology results in fast training, when compared to the conventional formulation of backpropagation algorithm. The results are presented using data from a Brazilian Electric Company, and shows a very good performance for the proposal objective.

High tech garbage can help engineering colleges to improve hands-on education

This paper presents a discussion on the potential use of high tech garbage, including electronic waste (e-waste), as a source of mechanisms, sensors and actuators, that can be adapted to improve the reality of microprocessor systems labs, at low cost. By means of some examples, it is shown that entire subsystems withdrawn of high tech equipments can be easily integrated into existing laboratory infrastructure. As examples, first a precision positioning mechanism is presented, which was taken from a discarded commercial ink jet printer and interfaced with a microprocessor board used in the laboratory classes. Secondly, a read/write head and its positioning mechanism has been withdrawn of a retired CD/DVD drive and again interfaced with the microprocessor board. Students who have been using these new experiments strongly approve their inclusion in the lab schedules. © 2011 IEEE.

Notes on competencies in engineering education

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)