Yu-Ju Chen

A passive auto-focus camera control system

This paper presents a passive auto-focus camera control system which can easily achieve the function of auto-focus with no necessary of any active component (e.g., infrared or ultrasonic sensor) in comparison with the conventional active focus system. To implement the technique we developed, the hardware system including the adjustable lens with CMOS sensor and servo motor, an 8051 image capture micro-controller, a field programmable gate array (FPGA) sharpness measurement circuit, a pulse width modulation (PWM) controller, and a personal digital assistant (PDA) image displayer was constructed. The discrete wavelet transformation (DWT), the morphology edge enhancement sharpness measurement algorithms, and the self-organizing map (SOM) neural network were used in developing the control mechanism of the system. Compared with other passive auto-focus methods, the method we proposed has the advantages of lower computational complexity and easier hardware implementation.

Artificial intelligent analyzer for mechanical properties of rolled steel bar by using neural networks

In this paper, an artificial intelligent (AI) analyzer for mechanical properties of rolled steel bar by using neural networks was proposed. Based on the learning capability of neural network, the nonlinear and complex relationships among the steel bars properties, the billet compositions and the control parameters of manufacture could be automatically developed. Such an AI analyzer could help the technician to precisely set the related control parameters on the bar rolling process. Not only the quality of steel bar could be improved, the production cost of the bar could also be greatly reduced.

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.

A modified probability neural network indoor positioning technique

This paper presents an indoor positioning technique using a modified probabilistic neural network (MPNN) scheme. It measures the received signal strength (RSS) between an object and stations, and then transforms the RSS into distances. A MPNN engine determines coordinate of the object with the input distances. The experiments are conducted in a realistic ZigBee sensor network. The proposed approach performs significantly better than triangulation technique when the RSS data are unstable. It can be efficiently applied to applications of location based service (LBS).

The Estimations of Mechanical Property of Rolled Steel Bar by Using Quantum Neural Network

In this paper, the estimations of mechanical property of rolled steel bar by using quantum neural network (QNN) were 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 could be automatically developed. Such an artificial intelligent (AI) estimator then can help the operation technician to set the related control parameters of rolling process. Not only the quality of steel bars could be improved, but also the cost of bar’s production could be greatly reduced.

An AI system for the decision to control parameters of TP film printing

In this paper, an artificial intelligent mechanism for the decision of control parameters of touch panel film printing was developed. This mechanism is capable of providing the accurate information for the control parameters of the film printing, so that the technician could make a good setting work for the real-line manufacturing operation of touch panel film. Thus, this system not only can help the technician to improve the efficiency on the work of film printing, but also can reduce the cost caused by the defective products for the company. In our study, this intelligent system was constructed by using quantum neural network. It can automatically display the proper value of each control parameter needed for the film printing when the thickness of film is determined.

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.

Transmittance Estimation of TP Decoration Film by QNN

In this paper, the transmittance estimation of touch panel decoration film by using quantum neural network (QNN) is proposed. This model is able to catch the complex relationship between the film’s transmittance and its possible influencing factors. An artificial intelligent (AI) mechanism for the decision of control parameters of film evaporation is expected to be developed. Based on this AI mechanism, the technician could make a good setting work for the real-line evaporation process. Thus, this system not only can help the technician to improve the efficiency of the touch panel, but also can reduce the cost caused by the defective products for the company.

The estimations of ammonia concentration by using neural network SH-SAW sensors

Research highlights? This paper presents the estimations of ammonia concentration by using neural network (NN) models. ? The shear horizontal surface acoustic wave (SH-SAW) devices coated with L-glutamic acid hydrochloride and polyaniline (PANI) film, respectively, were applied as the ammonia sensors. ? The signal sensed by SH-SAW sensors were implemented by using different NN models for the estimation of ammonia concentration. ? A reliable and superior neural network SAW identifier is expected to be found for effectively overcoming the interference of humidity in ammonia detection.Display Omitted This paper presents the estimations of ammonia concentration by using neural network (NN) models. The shear horizontal surface acoustic wave (SH-SAW) devices coated with L-glutamic acid hydrochloride and polyaniline (PANI) film, respectively, were applied as the ammonia sensors. The data sensed by SH-SAW sensors were implemented by using different NN models. A reliable and superior neural network SAW identifier is expected to be found for effectively overcoming the interference of humidity in ammonia detection.

The Transmittance Estimation of Touch Panel Decoration Film by Neural Network

In this paper, a transmittance estimator of touch panel decoration film by using neural network is presented. In the evaporation process, the coating material and the related control parameters are all important influencing factors in obtaining the desired transmittance. The relationship among the transmittance and these factors are very complex and nonlinear. It’s very hard to use the certain mathematical model to describe such relationship. In this research, the neural network was employed to catch the relationship among transmittance and its possible influencing factors. In other words, an efficiently and precisely automatic evaporation parameters decision system for touch panel decoration film is expected to be developed. Through the estimation system developed, the quality of transmittance of touch panel film could meet the customer’s requirement.