上浦 尚武

In this study, we investigate model structures for neural ODEs to improve the data efficiency in learning the dynamics of control systems. We introduce two model structures and compare them with a typical baseline structure. The first structure considers the relationship between the coordinates and velocities of the control system, while the second structure adds linearity with respect to the control term to the first structure. Both of these structures can be easily implemented without requiring additional computation. In numerical experiments, we evaluate these structure on simulated simple pendulum and CartPole systems and show that incorporating these characteristics into the model structure leads to accurate learning with a smaller amount of training data compared to the baseline structure.

© 2018 IEEE. In this paper, we propose a new approach to classify ovarian follicles into two classes. A smoothing filter which is designed to consider speckle patterns under the resolution of the ultrasound devices is applied for filtering ovarian follicle images. Then, convolutional neural networks are used for extracting features from the filtered ovarian follicle images. Finally, both features extracted by CNNs from the filtered ovarian follicle images and numerical features defined by our previous works are used for classification. From experimental results, we show the effectiveness of our proposed method.

© 2018 IEEE. In this paper, an ultrasound-measurement-based method of detecting stenosises in fallopian tubal models is presented. The proposed method employs silicone rubber tubes and custom phantoms made of polymer gels as models of fallopian tubes. When the targets are the former (or latter), stenosis models are formed by lumps of polyester sewing threads (or polymer gels with high reflection intensity). The proposed method copes with detecting stenosis models as classification problems by applying support vector machines (SVMs for short). It prepare data for SVM learning and stenosis detection from waveforms in the range specified by two time points at which waves are probably reflected by inner upper and lower surfaces of tubal models. The data preparation is conducted by generating the frequency distribution of the number of regular short intervals into which this range is divided versus normalized values associated with amplitude of the waveforms in such intervals. When it is explored whether given data are prepared from a tube with the stenosis model, a discrimination model constructed by SVM learning works as a two-class classifier. Using the model as a multi-class classifier makes it possible to distinguish data of tubes with stenosis models from each other. It is revealed from experimental results that the proposed method has substantially high capability in detecting stenosis models.

© 2017 IEEE. In this paper, a method of calculating inner and outer diameters of fallopian tubes is presented, provided that silicone rubber tubes are models for fallopian tubes. It is based on the ultrasound measurement using a single probe of which the nominal frequency is 5 MHz, and assumes that ultrasound waves emanating from the probe are reflected at the top outer surface, surfaces between water and silicone rubber, and bottom outer surface of the tube. It obtains envelope curves associated with the reflected waves, by applying Hilbert transformation to the waves. It next estimates top four maximal values on the envelope curves to acquire time points when the wave reflections occur. The inner and outer diameters of the tubes are easily estimated by substituting the above time points in simple formulas. Experimental results reveal that the proposed method can achieve substantial accuracy in estimating inner and outer diameters of the target tubes.

In this paper, a method of estimating binding time is proposed for ophthalmological outpatients. Binding time equals the sum of transit time and waiting time at a hospital. It determines the number of outpatients virtually arriving and their arrival time intervals according to the gamma distribution and the exponential distribution. It then assigns examinations to outpatients virtually arriving, referring to their appointment types probabilistically determined. Ten examination rules are established to simulate the passage of time required for examinations and consultation. The proposed method accesses database associated with public transport via some Application Programming Interface, and finally provides transit time and waiting time estimated by the simulation. Experimental results on estimating waiting time show that the average daily difference between actuality and estimation is acceptable.

Copyright © 2017 The Institute of Electronics, Information and Communication Engineers. To promote effective guidance by health checkup results, this paper predict a likelihood of developing lifestyle-related diseases from health check data. In this paper, we focus on the fluctuation of hemoglobin A1c (HbA1c) value, which deeply connected with diabetes onset. Here we predict incensement of HbA1c value and examine which kind of health checkup item has important role for HbA1c fluctuation. Our experimental results show that, when we classify the subjects according to their gender and triglyceride (TG) fluctuation value, we will effectively evaluate the risk of diabetes onset for each class.

To promote effective guidance by health checkup results, this paper predict a likelihood of developing lifestyle-related diseases from health check data. In this paper, we focus on the fluctuation of hemoglobin A1c (HbA1c) value, which deeply connected with diabetes onset. Here we predict incensement of HbA1c value and examine which kind of health checkup item has important role for HbA1c fluctuation. Our experimental results show that, when we classify the subjects according to their gender and triglyceride (TG) fluctuation value, we will effectively evaluate the risk of diabetes onset for each class.

In this paper, we present a method of analyzing relationships between items in specific health examination data, as one of the basic researches to address increases of lifestyle-related diseases. We use self-organizing maps, and pick up the data from the examination dataset according to the condition specified by some item values. We then focus on twelve items such as hemoglobin A1c (HbA1c), aspartate transaminase (AST), alanine transaminase (ALT), gamma-glutamyl transpeptidase (gamma-GTP), and triglyceride (TG). We generate training data presented to a map by calculating the difference between item values associated with successive two years and normalizing the values of this calculation. We label neurons in the map on condition that one of the item values of training data is employed as a parameter. We finally examine the relationships between items by comparing results of labeling (clusters formed in the map) to each other. From experimental results, we separately reveal the relationships among HbA1c, AST, ALT, gamma-GTP and TG in the unfavorable case of HbA1c value increasing and those in the favorable case of HbA1c value decreasing.

In this paper, broadband ultrasonic imaging is presented to check the diameters of tubules. The proposed method applies continuous wavelet transform instead of short-time Fourier transform, and hence overcomes both issues of spatial resolution and frequency resolution. The proposed method can visualize positions of test objects more clearly than the previous work.

Chronic thromboembolic pulmonary hypertension (CTEPH) is one of the lung diseases caused by thrombi, which occurs in pulmonary arteries. By measuring a size of region dominated by arterial subtree which has thrombi, physicians find a higher treatment effect point. This paper proposes an automated method to extract the lung region dominated by an arterial subtree from MDCT images. The method extracts an arterial subtree associated with a seed point and a region dominated by the extracted arterial subtree. And visualizes them. The results show a clinical ability of visualization and extraction of dominant region from MDCT Images.

In this paper, a method of classifying the data of female subjects taking the specific health examination is presented, using self-organizing maps (SOM's). The proposed method focuses on female subjects fulfilling the standard specified by body mass index and abdominal circumference. It defines the following data classes: the class with subjects of which hemoglobin Alc (HbAlc) values and item values associated with a liver belong to unhealthy levels, that with subjects having HbAlc and triglyceride values included in unhealthy levels, and that with remaining subjects. It generates the data for normal SOM learning from values of twelve items such as HbAlc and glutamic-oxaloacetic. SOM learning is made to construct the map, and its neurons are labeled. The class of data to be checked depends on the label of a winner, when the data is presented. Experimental results establish that the proposed method achieves the reasonably favorable accuracy of consistency on data classification.

In the infertility treatment, medical examinations using ultrasonic devices, which can diagnose the mother's body safely on real time, are major. It is very difficult to judge the existence of an ovum before carrying out the paracentesis. A system which can distinguish the existence of the ovum in the ovarian follicle using ultrasonic devices is required. In this paper, several features of the deformation of ovarian follicle are defined and extracted from the ultrasonic moving image in a paracentesis operation. These features are extracted from the ultrasonic moving image obtained at the time of an ovum extraction operation. We investigate whether some clusters according to the existence of the ovum are formed using the defined features. Moreover, we also investigate whether some tendency exists in these features by the existence of an ovum.

In this paper, an application of self-organizing maps (SOM's) in classifying and predicting data of female subjects with unhealthy-level visceral fat is discussed. The proposed method chooses subjects fulfilling the standard specified by body mass index and abdominal circumference. It defines the class with subjects of which hemoglobin A1c (HbA1c) values and item values associated with a liver deteriorate, that with subjects having HbA1c and triglyceride values deteriorate, and that with remaining subjects. Normal SOM learning is conducted, using data generated from original values of twelve items such as HbA1c and glutamic-oxaloacetic. The constructed map consists of neurons with labels. The label of a winner determines the class of the presented unknown data. The prediction depends on the label of a winner for the presented unknown data, a set of original data that determine the label, and a set of next year's data of the subjects with the above original data. Experimental results reveal that the proposed method achieves the reasonably favorable accuracies in classifying data and in predicting HbA1c values.

In this paper, an application of self-organizing maps (SOM's) in classifying and predicting data of female subjects with unhealthy-level visceral fat is discussed. The proposed method chooses subjects fulfilling the standard specified by body mass index and abdominal circumference. It defines the class with subjects of which hemoglobin A1c (HbA1c) values and item values associated with a liver deteriorate, that with subjects having HbA1c and triglyceride values deteriorate, and that with remaining subjects. Normal SOM learning is conducted, using data generated from original values of twelve items such as HbA1c and glutamic-oxaloacetic. The constructed map consists of neurons with labels. The label of a winner determines the class of the presented unknown data. The prediction depends on the label of a winner for the presented unknown data, a set of original data that determine the label, and a set of next year's data of the subjects with the above original data. Experimental results reveal that the proposed method achieves the reasonably favorable accuracies in classifying data and in predicting HbA1c values.

In the infertility treatment, medical examinations using ultrasonic devices, which can diagnose the mother's body safely on real time, are major. It is very difficult to judge the existence of an ovum before carrying out the paracentesis. A system which can distinguish the existence of the ovum in the ovarian follicle using ultrasonic devices is required. In this paper, several features of the deformation of ovarian follicle are defined and extracted from the ultrasonic moving image in a paracentesis operation. These features are extracted from the ultrasonic moving image obtained at the time of an ovum extraction operation. We investigate whether some clusters according to the existence of the ovum are formed using the defined features. Moreover, we also investigate whether some tendency exists in these features by the existence of an ovum.