Satoru Kishida

Learn More
We constructed systems with neural networks using one-dimensional numeric sequences from chest X-ray images for detection of abnormal areas and investigated the effect of pre-processing for input patterns on performance of the systems. We changed the number of data in one-dimensional numeric sequences, and applied differential filters to the sequences.(More)
We constructed neural network systems using one-dimensional numeric sequences from X-ray images of chest for detection of abnormal areas in the images and investigated the effect of number of input layer units on performance of the systems. In order to construct the neural networks with different number of input layer units, we changed the number of data in(More)
Although the presence of an oxygen reservoir (OR) is assumed in many models that explain resistive switching of resistive random access memory (ReRAM) with electrode/metal oxide (MO)/electrode structures, the location of OR is not clear. We have previously reported a method, which involved the use of an AFM cantilever, for preparing an extremely small ReRAM(More)
In order to remove high noise of the CT image reconstructed by a hard kernel efficiently and to minimize the number of images to be added, we constructed the system to fit the discrete data to a continuous function and developed the algorithm which calculate the MTF through a curve fitting technique with two steps. From the results, we found that the MTF(More)
This paper describes a technique of penalty weight adjustment for the Cooperative Genetic Algorithm applied to the nurse scheduling problem. In this algorithm, coefficient and thresholds for each penalty function are automatically optimized. Therefore, this technique provides a parameter free algorithm of nurse scheduling. The nurse scheduling is very(More)
We have constructed systems that detect abnormal areas of lung X-ray images from one-dimensional numeric sequences using neural networks. In these systems, the neural network consists of neurons that use trigonometric polynomials as activation functions, or TPUnit neural networks. The TPunit neural network has a high generalization ability in a smaller(More)