Chih-Yung 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.

Isolated ocular motor nerve palsy in dural carotid-cavernous sinus fistula.

The incidence of dural carotid‐cavernous sinus fistula (DCCF) presenting as isolated ocular motor nerve palsies without congestive ocular features is unknown. We reviewed the DCCF patients in our hospital during the last 10 years to elucidate the clinical and neuroradiological features of DCCF with isolated ocular motor nerve palsy. Eleven amongst the 33 DCCF patients presented isolated ocular motor nerve palsy. All the 11 patients underwent brain CT/CT angiography (CTA) and/or MRI/MR angiography (MRA), before the digital subtraction angiography (DSA). The compromised nerves were the oculomotor nerve in eight (72.7%), abducens nerve in two (18.2%) and trochlear nerve in one (9.1%). Brain CT and/or CTA were conducted in four patients but all unremarkable. MRI and/or MRA were performed in nine patients and six of them showed compatible findings of DCCF. The diagnoses of DCCFs were confirmed by DSA and all were posterior‐draining type. The outcome was good, with a total recovery rate of 54.5% within 12 months. Thirty‐three percent (11 of 33) of our DCCF patients presented with isolated ocular motor nerve palsy, which is not uncommon. MRI and MRA are of value in the initial evaluation, but DSA is necessary for the accurate diagnosis and treatment planning.

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.

Rebound intracranial hypertension after treatment of spontaneous intracranial hypotension

Spontaneous intracranial hypotension (SIH) is characterized by orthostatic headache and the cause is usually cerebrospinal fluid leaks in spine level. Most patients with SIH have a benign course. Epidural blood patch (EBP) is the treatment of choice when initial conservative managements are ineffective. We reported a patient with SIH diagnosed by using magnetic resonance imaging and radionuclide cisternography. Acute rebound intracranial hypertension developed after EBP and was successfully treated with intravenous osmotic agent.

A new variable topology for evolutionary hardware design

In this paper, a novel variable topology for evolutionary hardware design is proposed. The slicing structure and routing graph are integrated into the design of evolutionary hardware. With off-line gate-level samples, simulation results clearly demonstrate the validity of this new approach performed as superior as existing methods in the logic circuit optimization. Compare with the random circuit matrix method, our approach uses less code length for evolutionary hardware description. The method we proposed could be taken as an alternative way for possible evolutionary hardware applications in the future.

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).

A six-antenna station based indoor positioning system

This study develops an intelligent wireless indoor positioning system (IPS), which includes new beam antenna design and modified probabilistic neural network based positioning algorithm. The six directional antennas can obtain the angle between an object and the station. Then, a modified probabilistic neural network is applied to estimate the accurate position of the object with the signal strength. The developed IPS architecture has the average error of less than 0.8 meters in the eight square meter indoor scene. This indoor positioning scheme is not only has high positioning accuracy, but also can be an effective solution to solve the difficult issue of positioning station deployment.

Automatic White Balancing by Using NN Module

This paper presents an automatic white balancing (AWB) technique achieved by a hybrid neural module. The neural module is composed of self-organizing map (SOM) neural network, quantum neural network (QNN), and von Kries chromatic adaptation. By this module, the illuminated effect of an image can be greatly eliminated and improved. To demonstrate the efficiency of the module proposed, the experiments executed by SOM and probabilistic neural network (PNN) are used to be a comparison. From the experimental results shown, the effect of illuminant has been improved effectively as compared with the works we done before.

A New Variable Topology Genetic Coding for Evolutionary Hardware

Recently, the approaches that were all developed with random circuit matrix as evolutionary framework have been widely used for evolutionary hardware and evolutionary hardware design. In this paper, a novel variable topology genetic coding including a new logic circuit representation and corresponding evolutionary algorithm for evolutionary hardware design is proposed. In comparison with random circuit matrix based studies, the proposed approach is able to reduce searching space for evolutionary computation, obtain better flexibility for logic circuit encoding, and increase exploration possibility for more complex evolutionary hardware. Simulation results demonstrate the validity and performance of the proposed method.

The intelligent control of ITO bar's resistance for touch panel

The paper presents an intelligent control mechanism for the ITO bars resistance of touch panel (TP). The artificial neural network is used to catch the complex relationship between bars resistance and its relevant manufacturing parameters during the printing and etching processes. An effective and accurate manufacturing mechanism of ITO bar is expected to be developed. This mechanism can be taken as a tool which is able to help the engineer to precisely control the manufacturing process of ITO bar such that the ideal touch panel with desired film thickness and resistance can be produced. Not only the rate of excellent product could be greatly improved, but also the business cost could be effectively saved.