Pin-Hsuan Weng

  • Citations Per Year
Learn More
In this paper, an alternative fast learning algorithm for supervised neural network was proposed. Both linear multi-regression and back-propagation learning methods were used alternately in the network’s training process. This new learning way is expected to improve the learning efficiency and accuracy of neural network in the real applications. To(More)
In this paper, an intelligent fault diagnostic tool for oil-fired power plant with turbine generator by using the modified neural network was proposed. This tool is able to monitor the running condition of power plant immediately. It also can reveal the fault situation if the power plant had some troubles. Therefore, such a well designed mechanism can be(More)
The coupling-of-modes (COM) theory has been widely used in simulation of surface acoustic wave devices. The accuracy of simulation strongly depends on accurate COM parameters of the piezoelectric substrate. The COM parameters of most single crystal piezoelectric substrates can be obtained in literatures. However, for thin film and multilayer substrate, the(More)
In this paper, a hybrid supervised learning algorithm for neural network was proposed. The problem of local minimum learning usually occurred in the real application of neural network is tried to be solved or reduced. In order to improve the efficiency and stability of conventional error back-propagation learning algorithm, a hybrid learning method(More)
The aim of this research is to predict the luminous intensity and wavelength of light-emitting diode (LED) chip by using neural network technique. The data simulated was measured by electrical luminescence (EL) technique. The well trained neural model could be used to predict the optoelectronic attributes of LED chip in advance. The predicted results are(More)
  • 1