-Chu Huang

Quantum NN vs. NN in signal recognition

In this paper, the signal recognition by using quantum neural network (QNN) is studied and simulated. The signals with fuzziness distributed in the boundary of two different types of signals could be effectively recognized due to the structure of QNNs hidden units. To demonstrate the capability of QNN in recognition, the signals in a two-dimension (NC2) non-convex system is simulated. All the experiments are also performed by using the traditional neural network (NN) for a comparison.

The indoor positioning technique based on neural networks

This paper presents an indoor positioning technique based on neural networks (NN). The received signal strengths (RSS) sensed by Zigbee wireless sensor network were used to estimate the position of object. From the simulation results shown, the NN technique proposed still has the high accuracy even the signal strengths sensed are unstable. Besides, from the experimental results shown, it is concluded that the positioning accuracy could be improved if the number of wireless sensors is added more. In this research, the polar coordinate system of objects position was also studied. It is found that the accuracy of positioning by polar form is better than by rectangular form.

Fast learning neural network with modified neurons

In this paper, a neural model with modified neurons is developed. Compare with traditional neural network, such a neural model not only has a fast learning, but also can significantly improve the accuracy while it is used in real applications. To demonstrate the learning efficiency of neural model we developed, a nonlinear system identification problem is studied and simulated. All simulations are performed by using constant learning rates (0.1/spl sim/0.9). From the simulation results, the neural model we developed obviously has excellent performances as desired.

System Identification of TP Film Evaporation by Using Nearly Equivalent NN Model

This paper presents a technique, called “nearly equivalent neural network (NN) model” in the application of nonlinear system identification. This technique is expected to adequately to catch the behavior of the nonlinear system. To demonstrate the new technique proposed, the evaporation system of TP decoration film was analyzed. The complex relationship between the film’s transmittance and its possible influencing factors was identified. For the comparison, the same simulations were also performed by using the conventional neural network with the standard steepest descent error back-propagation (BP) learning algorithm.

Power Signal Forecasting by Neural Model with Different Layer Structures

In this paper, the non-stationary power load forecasting by using neural model with different layer structures is presented. In the neural forecasting model we developed, the neuron types used in different layers are different. Each layer is composed of the same kind of neurons. A reliable and accurate neural forecasting model for the non-stationary power loads is trying to be found in this study. To demonstrate the superiority of the model we created, all simulations are executed by using the conventional neural model with same neurons as a comparison. From the results shown, it is clearly found that the neural model we constructed do have better nonlinear mapping and forecasting capabilities in comparison with the conventional neural model

The data mining for TP film's transmittance by using neural network

This paper presents a new computation method based on the weights of the well-trained neural network (NN) for the data mining of touch panel (TP) films transmittance. By using the method developed, the influence degree of each input variable to the transmittance could be obtained and then the useful influencing inputs could also be determined. In this research, the data of the transmittance of TP film with Cr and Cr2O3 coating are studied. The possible influencing factors including the coating target composition, the layers of coating material, the films thickness, the position of panel placed and the rotation speed of evaporators holder are collected and analyzed. The relationship between films transmittance and these possible influencing factors is expected to be obtained.

The Neural Network Estimator for Mechanical Property of Rolled Steel Bar

In this paper, the neural network estimator for mechanical property of rolled steel bar was proposed. Based on the learning capability of neural network, the nonlinear, complex relationships among the steel bar, the billet materials and the control parameters of production are expected to be automatically developed. Such a neural network estimator can help the technician to make a precise judgment for setting the related control parameters of rolling process. Not only the quality of steel bars can meet the standard asked for, but also can reduce the running cost caused by failure production.

The transmittance estimations of TP film with Cr and Cr 2 O 3 coating

This paper presents the transmittance estimations for touch panel (TP) film with Cr and Cr2O3 coating by using neural network (NN) model. The NN model with quasi-Newton learning method was used to obtain the mapping between TP transmittance and its all possible influencing factors. This study tries to develop an artificial intelligent (AI) evaporation decision mechanism which can help the technician to set the related control parameters before the films evaporation process is taken. The transmittance is one of important determination factors used for checking whether the quality of TP is qualified or not. Thus, a smart decision mechanism not only can help technician to improve the work efficiency, but also can reduce the running cost of the company due to the defective products.

Quality Identification of the Riveting Process by QNN Model

In this paper, an automatic quality inspection system for the riveting process by using quantum neural network (QNN) was proposed. This inspection system not only can monitor the real time riveting process, but also can give the assistance on the riveting quality verification. For demonstrating the superiority of the inspection system we developed, the data provided by the experiment did by Chinese Air Force Institute of Technology was simulated. The method of riveting quality index (RQI) was also performed as a comparison.

Short Term Power Load Forecasting by Using Neural Models

This paper presents the power load forecasting by using neural models for Toronto area, Canada. Different neural models were used to carry out the forecasting works. One-day-ahead daily total load and peak load forecasts were implemented by using different neural models in order to find the more accurate forecasting results. The load data and temperatures provided by Independent Electricity System Operator (IESO) from January, year 2003 to January, year 2008 were studied and simulated. In our studies, mean absolute percentage error (MAPE) is used as the measurement of models performances.