To objectively evaluate the parenchymal echo pattern of cirrhotic liver and chronic hepatitis, the authors applied an image analyzing system (IAS) using a neural network. Autopsy specimens in a water ...tank (n=13) were used to examine the relationship between the diameter of the regenerative nodule and the coarse score (CS) calculated by IAS. CS was significantly correlated with the diameter of the regenerative nodule (p<0.0001, r=0.966). CS is considered to be useful for evaluating the coarseness of the parenchymal echo pattern.
This paper presents exact analysis of class DE amplifier for any conditions including outside optimum conditions. We give an analytical expression of waveform equations and initial values of current ...and voltage in the steady state. By using these analytical equations, switching voltage, output voltage and power conversion efficiency of class DE amplifier can be derived with few efforts. In this paper, we denote the steady state behaviors outside optimum conditions which occur by the variations of operating frequency and switch on duty ratio. The theoretical results show a quantitative agreement with the experimental ones, which denotes the validity of analytical equations
It is well known that sliding mode control (SMC) is capable of tackling systems with uncertainties. However, the discontinuous control signal causes the significant problem of chattering. ...Furthermore, thorough knowledge of the plant dynamics may be unknown or difficult to obtain, which makes it difficult to calculate the control law. A synergistic combination of neural network (NN) and SMC methodology is proposed. The network weights are adjusted using a modified online error backpropagation algorithm. Moreover, a new and simple approach is utilized to construct corrective controls of SMC to overcome the chattering problem. As a result, chattering is eliminated and the error performance of SMC is also improved. Experimental studies carried out on a magnetic levitation system are presented.
The paper presents a new free-running-oscillation resonant DC/DC converter with a class E oscillator, along with its design procedure and experimental results. The proposed converter is composed of a ...class E oscillator and a class E rectifier. This circuit is a free-running-oscillation system and has no gate-drive circuit to drive the MOSFET. The proposed converter has the ability to achieve high power conversion efficiency under high frequency operation because of class E switching at both oscillator and rectifier. Experimentally measured power conversion efficiency is 78.9% for 1.55 W output power at an operating frequency 2.00 MHz.
We propose a new detector of random-valued impulse noise in images using level detection. In our method, we use directional windows in order to search a level region in the images. One window, whose ...variation is lowest, is selected as a flat window from multi directional windows. In a flat window, random-valued impulse noise may move to both ends of the order statistics. Therefore, noise detection in the selected window is easy. Consequently, the proposed method reduces undetected noise pixels without increasing mis-detections. Extensive simulations indicate that the proposed method performs significantly better than conventional methods.
The effects of the water extract of
Sinomeni Caulis et Rhizoma
(SCR-WE) and its major constituents, sinomenine (SIN) and magnoflorine (MAG), on moderate hemolysis induced by lysophosphatidylcholine ...(LPC) were investigated in rat erythrocytes and compared with the anti-hemolytic effects of lidocaine (LID) and propranolol (PRO) as reference drugs. LPC caused hemolysis at concentrations above the critical micelle concentration (CMC), and the concentration of LPC producing moderate hemolysis (60 %) was approximately 10 μM. SCR-WE at 1 ng/mL–100 μg/mL significantly inhibited the hemolysis induced by LPC. SIN and MAG attenuated LPC-induced hemolysis in a concentration-dependent manner from very low to high concentrations (1 nM–100 μM and 10 nM–100 μM, respectively). In contrast, the inhibiting effects of LID and PRO on LPC-induced hemolysis were observed at higher concentrations (1–100 μM) but not at lower concentrations (1–100 nM). Neither SIN nor MAG affected micelle formation of LPC, nor, at concentrations of 1 nM–1 μM, did they attenuate the hemolysis induced by osmotic imbalance (hypotonic hemolysis). Similarly, SCR-WE also did not modify micelle formation or hypotonic hemolysis, except at the highest concentration. These results suggest that SIN and MAG potently protect the erythrocyte membrane from LPC-induced damage and contribute to the beneficial action of SCR-WE. The protective effects of SIN and MAG are mediated by some mechanism other than prevention of micelle formation or protection of the erythrocyte membrane against osmotic imbalance.
The face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. In this paper, we present a method for face recognition based on parallel ...neural networks. Neural networks (NNs) have been widely used in various fields. However, the computing efficiency decreases rapidly if the scale of the NN increases. In this paper, a new method of face recognition based on fuzzy clustering and parallel NNs is proposed. The face patterns are divided into several small-scale neural networks based on fuzzy clustering and they are combined to obtain the recognition result. In particular, the proposed method achieved a 98.75% recognition accuracy for 240 patterns of 20 registrants and a 99.58% rejection rate for 240 patterns of 20 nonregistrants. Experimental results show that the performance of our new face-recognition method is better than those of the backpropagation NN (BPNN) system, the hard c-means (HCM) and parallel NNs system, and the pattern-matching system
This paper investigates the use of neural networks (NNs) in conventional model reference adaptive control (MRAC) to control a nonlinear magnetic levitation system. In the conventional MRAC scheme, ...the controller is designed to realize plant output convergence to a reference model output based on a plant which is linear. This scheme is effectively for controlling linear plants with unknown parameters. However, using MRAC to control the nonlinear magnetic levitation system in real time is a difficult control problem. In this paper, we incorporate a NN in MRAC to overcome the problem. The control input is given by the sum of the output of the adaptive controller and the output of the NN. The NN is used to compensate the nonlinearity of the plant that is not taken into consideration in the conventional MRAC. From experiment results, it has been shown that the plant output can converge to the reference model output after using NN in MRAC.
We propose a robust approach for blind source separation when observations are contaminated with Gaussian noise and nonlinear distortion. A radial basis function network (RBFN) is employed to ...estimate the inverse of the nonlinear mixing matrix. We utilize an novel cost function which consists of mutual information and higher-order cumulants of signals. Compared with moments, higher-order cumulants can provide a clearer form and more information of signals. Thus, the proposed method has not only the capacity of recovering the nonlinearly mixed signals, but also removing high-level Gaussian noise from transmitted signals. Through simulation and analysis of artificially synthesized signals, we illustrate the efficacy of this approach.