著者
山本 祥弘
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.9, no.10, pp.467-475, 1996-10-15 (Released:2011-10-13)
参考文献数
16

Recently, the author proposed a new learning algorithm derived algebraically which is composed of the error back propagation to give a fictitious teacher to each hidden layer and the update rule of each connection. The details of the algorithm with some comments are demonstrated in this paper using the Exclusive-OR problem as an example. Some update rules of each connection are also proposed here. Among them, the update rule using an orthonormalization method with some scheme is most effective. Simulation results show thst 5 steps convergence can be obtained in many cases of different initial values. The exceptional cases which do not show the convergence are also made convergent by some improvement in the nonlinear characteristic of the unit.
著者
松田 稔 秋山 好一
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.8, no.12, pp.685-691, 1995-12-15 (Released:2011-10-13)
参考文献数
14

The nature of the Japanese favorite songs becomes to be gradually clear by the recent research works. In the subject of these research works, “Tonality and Tonic (key note)” of the music (T & T) has been attracted a great deal of attention as an important index to determine the character of music. This paper deals with tonal structure recognition method of Japanese favorite songs using information about pitch name and time-duration that appear on musical score (sample data 2, 777 pieces, 274, 737 notes). As a result, the remarkable characters were found. For example, T & T can be recognized with approximately 90 % accuracy by statistical pitch information of the music score. The time-duration dose not play an important role to infer the T & T.
著者
高木 康夫 坂本 佳直美 中道 亮 佐藤 隆
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.33, no.3, pp.77-86, 2020-03-15 (Released:2020-06-15)
参考文献数
16

The simulation results of the heat medium control and management of A-CAES plant (Adiabatic Compressed Air Energy Storage) are presented. For the study, the dynamic model of the A-CAES plant with liquid heat medium as heat storage is constructed in order to analyze charge-discharge cycle efficiency dependency on actual operating conditions. Various heat management systems for a CAES are proposed. Among the systems, heat medium circulating system is the most feasible solution. The heat management and storage is very important for the A-CAES plant, because about half of the energy is recovered through heat insulation and heat management. Dynamic plant efficiency analysis is also crucial because the dynamic properties of the plant influences on the efficiency. The model consists of the heat exchangers, the heat storages, the air storage and an ideal compressor and expander models. The heat transfer characteristics of the heat exchanger are tested by the experimental setup because the heat exchanger performance is the most important factor for the system efficiency. The plant scale and the heat loss influence on the charge-discharge efficiencies are shown through the simulations.
著者
岡島 寛 川脇 治
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.31, no.11, pp.392-399, 2018-11-15 (Released:2019-02-15)
参考文献数
14

This paper presents a design framework for individualization of control system. Controllers in products are designed for the average user in general. To increase the control performance for a particular person, individual design of controller is required. However, design controller for individual users involve costs. The words “Internet of Things” is used in recent years. It is expected that low cost customization of the control system using individual characteristics observation and application of information of the individual characteristics for control system design. This propose a concept of the design framework of control systems for individual user based on individual user's parameters.
著者
岡島 寛 甲斐 しずく 徳永 慎也
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.34, no.2, pp.47-57, 2021-02-15 (Released:2021-05-15)
参考文献数
17

Management of evacuation centers and flexible support of supplies are required when a largescale disaster occurs. It is necessary to predict demand in order to transport relief goods quickly and appropriately to evacuation centers. Therefore, it is effective to predict the number of refugees in evacuation centers. Generally, the supply and demand trends vary not only due to the scale of the earthquake disaster but also depending on the occurrence situation, power outages and other conditions. In this study, we propose a dynamic model for predicting the number of evacuees. The effectiveness of the proposed model is illustrated by numerical example about case study of the Kumamoto earthquake.
著者
宮崎 剛司 北原 晃輔 岡島 寛 松永 信智
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.31, no.7, pp.274-280, 2018-07-15 (Released:2018-10-24)
参考文献数
16
被引用文献数
1

In recent years autonomous control of automobiles has been focused on. Path-following control is an important technologies of autonomous control of automobiles. In path-following control, it is necessary to calculate an appropriate steering input and velocity input according to the shape of the target path. In previous research, the steering control and velocity control method have been achieved by formulating and solving the optimization problem using variation principle. Since the problem solvable by the two-point boundary value problem is limited, the format of the evaluation function is limited and it is difficult to explicitly consider constraints in some cases. In addition, the real-time performance of the optimization calculation is also a problem considering the implementation in the real plant. In this paper, we propose a method for accurate follow-up to the target path and appropriate velocity control according to the shape of the target path in real time by designing the velocity function as a function of the target path information and state of the plant.
著者
Koji Sasano Hiroshi Okajima Nobutomo Matsunaga
出版者
THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)
雑誌
Transactions of the Institute of Systems, Control and Information Engineers (ISSN:13425668)
巻号頁・発行日
vol.23, no.11, pp.257-264, 2010 (Released:2011-05-21)
参考文献数
22

Recently, the fractional order PID (FO-PID) control, which is the extension of the PID control, has been focused on. Even though the FO-PID requires the high-order filter, it is difficult to realize the high-order filter due to the memory limitation of digital computer. For implementation of FO-PID, approximation of the fractional integrator and differentiator are required. Short memory principle (SMP) is one of the effective approximation methods. However, there is a disadvantage that the approximated filter with SMP cannot eliminate the steady-state error. For this problem, we introduce the distributed implementation of the integrator and the dynamic quantizer to make the efficient use of permissible memory. The objective of this study is to clarify how to implement the accurate FO-PID with limited memories. In this paper, we propose the implementation method of FO-PID with memory constraint using dynamic quantizer. And the trade off between approximation of fractional elements and quantized data size are examined so as to close to the ideal FO-PID responses. The effectiveness of proposed method is evaluated by numerical example and experiment in the temperature control of heat plate.
著者
梅井 啓紀 岡島 寛 松永 信智 浅井 徹
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.27, no.2, pp.67-72, 2014-02-15 (Released:2014-05-15)
参考文献数
19
被引用文献数
7 5

Many control system design methods are developed based on the dynamics of the accurate plant model. However, desired control performance cannot be achieved by the designed controller if the modeling error is not small. To overcome this problem, we have proposed a compensator to minimize the gap between an actual plant and its nominal model in SISO setting. The compensator design problem has been reduced to the standard LMI design problem and the modeling error is minimized. Consequently, the desired control performance can be achieved if we use the designed controller with our proposed compensator. The design method is extended to MIMO systems. In particular, not only error between compensated system and model, but also magnitude of the compensation input are handled in the compensator design. The effectiveness is shown by the numerical examples.
著者
巽 啓司 福島 雅夫
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.8, no.5, pp.204-211, 1995-05-15 (Released:2011-10-13)
参考文献数
9
被引用文献数
7 1

Error back propagation is one of the most popular ideas used in learning algorithms for multilayer neural networks. Since the pioneering work by Rumelhart, Hinton and Williams, error back propagation has been regarded as a gradient descent method or its close approximation to minimize the sum-squared error function. In this paper, we point out that “on-line” back propagation is better interpreted as a successive projection method for solving a system of nonlinear ineqnalities. In particular we proposed a new learning algorithm based on the successive projection method, in which the stepsize is determined quantitatively based on the magnitude of error observed for each input pattern. Some simulation results on XOR and parity check problems indicate that the propsed algorithm is more effective and robust than the standard on-line back propagation algorithm.
著者
佐々木 貴広 下村 卓
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.28, no.4, pp.127-132, 2015-04-10 (Released:2015-07-15)
参考文献数
3
被引用文献数
1 1

In spacecraft attitude control, the quaternion is often used as a kinematic parameter, simply because it has no singularities. In the tracking problem of an attitude control, the error quaternion is needed for quaternion feedback. Due to complexity of the quaternion math, the error quaternion is sometimes misunderstood and its incorrect denition is used for attitude control. Even in such cases, the tracking objective is achieved to some extent. In this paper, we consider attitude control of a spacecraft with RWs and examine the property of the error quaternion.
著者
古本 奈奈代 正満 敏雄 大松 繁 岡久 俊郎
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.5, no.2, pp.80-82, 1992-02-15
参考文献数
5
被引用文献数
1

生活環境政策を計画立案するときは, 住民のニーズを反映させるため, アンケートを行うことがよくある.アンケート項目間の内容は, 物理データと違って複雑に関連し合っているが, それを具体的にどのように扱うかについては充分な検討がなされていない面があった.そのため, ここではまず, デマーテル手法を適用して専門家などの意見を参考に, 項目間の階層的な繋がりや関連度を調べてその構造を分析し, つぎに, それらをもとに, 実質的なニーズを求めることを考えた。これによって, 環境政策をたてる際の無駄な投資は避けられるのではないかという見通しをたてた.また, ここで提案した手法は, 計画立案に当り, コンピュータとの対話型支援システムとして役立てることができると思われる.
著者
西田 一貴 音田 浩臣
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.33, no.5, pp.149-155, 2020-05-15 (Released:2020-08-15)
参考文献数
8

In this paper, we propose a method to detect workers’ nonstandard motion in cell production lines. Our method consists of three features: (1) sensing motion of a person, (2) measuring the time of motion by using Dynamic Time Warping and (3) analysis of the motion time. We applied the method to a prototype cell production line in our factory and verified its effectiveness. In an interview with Industrial Engineer, we have confirmed that our system has the potential to reduce the time taken for discovering nonstandard motion from 10 hours to 2.5 hours. From the above, we conclude that our method can enhance the efficiency of cell production line improvement.
著者
藤原 道良 杉本 末雄
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.8, no.1, pp.17-24, 1995-01-15 (Released:2011-10-13)
参考文献数
18
被引用文献数
9 6

In this paper we present two estimation algorithms of static relative positioning by GPS, where the vector between two antenna stations is determined. There are two important types of GPS observable quantities ; pseudo ranges and carrier phases. The first algorithm here is to utilize the double difference of the carrier phases. And the second algorithm for relative positioning is shown based upon the difference of the estimates for point positioning by using the pseudo ranges, specially, applying Dilution of Precision (DOP). Finally, the experimental results for estimation of the baseline length are shown by using real receiver data obtained at two static points.
著者
岩朝 睦美 戸田 雄一郎 新井 智之 久保田 直行
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.32, no.6, pp.256-264, 2019-06-15 (Released:2019-09-15)
参考文献数
14

It is an important task for mobile robots that search the target and learn the route while recognizing the unknown environment topology. Usually, reinforcement learning is used as a learning method to know the route to the target while exploring the environment. However, in an unknown environment, it is difficult to predict the number of state division. Particularly, when the state division is too fine, the amount of calculation increases exponentially. In this paper, we propose a method to dynamically construct the state space of the environment using Growing Neural Gas and simultaneously search and learn the route to the target using Q-Learning. We applied multiple autonomous mobile robots to increase searching efficiency. The experimental result shows the effectiveness of the proposed method that can respond to dynamic environmental change.
著者
佐藤 文宏 冨永 登夢 土方 嘉徳 酒田 信親 西田 正吾
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.29, no.8, pp.355-361, 2016

<p>Our previous study designed interactive floor projection system with hands and toes input in terms of quick and light input system. This system lets user interact with floor projection by pointing the finger or stepping on projection image. It allows to realize floor interaction without using even a single hands.</p><p>However, in this system, it is difficult for user to input by toes to desired position precisely because of low accuracy of toe detection. In this paper, we propose a new toe detection method by means of implementing a leg model to improve the accuracy of toe detection. The model signifies human leg. It consists of three joints and; thigh, cnemis and foot length. Moreover, we conduct user study to investigate accuracy of toe detection compared with proposed and previous method. As a result, proposed method can detect toe position with higher accuracy than previous method.</p>
著者
Ishikawa Masaaki
出版者
THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.25, no.12, pp.343-348, 2012 (Released:2013-03-15)
参考文献数
19
被引用文献数
2 6

Despite the advanced medical technology, infectious diseases remain a continuing threat to mankind. Hence, a prevention of prevalence of infectious diseases is one of important problems in epidemiology. In the past, the public health system has prepared for some strategies such as antibiotics and vaccines to control the infectious disease development. In order to build up more effective strategies, we need a precise theoretical analysis of infectious diseases. From a theoretical viewpoint, the mathematical model which describes the spread of the infectious disease has a very important role. In this paper, we study the stochastic modeling of the infectious disease in populations consisting of four groups: susceptible, infected, recovered and vaccinated. We consider the optimal vaccination strategy under the framework of the stochastic optimal control problem. Applying the stochastic maximum principle and the four-step scheme to the considered stochastic optimal control problem, we construct a feasible optimal vaccination system.
著者
呉 沙 古谷 栄光
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.29, no.6, pp.258-265, 2016-06-10 (Released:2016-09-15)
参考文献数
17
被引用文献数
2

In critically ill patients suffering from hyperglycemia it has been recently shown that mortality and morbidity can be reduced by keeping glycemia within 80-110 mg/dL (4.4-6.1 mmol/L). However, maintaining blood glucose (BG) levels within such range is difficult because of the time variability in insulin sensitivity through the patient recovery. In this study, we introduce a nonlinear model predictive control algorithm using a time-invariant model of glucose-insulin metabolism for the eventual development of a control system that regulates BG levels of critically ill patients. Simulation results using virtual patients with time-varying insulin sensitivity show that BG levels can be kept 58.3% within the 80-110 mg/dL range with only 1.4% of BG levels decreasing below 80 mg/dL (4.4 mmol/L), which demonstrates the safety of the present control algorithm.
著者
白 鶴 藤井 進 貝原 俊也
出版者
一般社団法人 システム制御情報学会
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.16, no.8, pp.377-387, 2003-08-15
参考文献数
14

In real manufacturing system, changes take place in the shop floor frequently. When a manufacturing simulation system is developed and used for the daily operational planning and evaluation, the simulation model must be in a good correspondence with the real manufacturing system. Therefore, how to reflect various changes in the manufacturing system to the simulation model and thus keep the model updated become important issues to be answered. In this study, towards automated updating, simulation-modelling formalism for manufacturing system is proposed. This formalism makes use of change suppression technique as well as late binding and polymorphism in object-oriented technology to make the simulation model uniform, consistent and keep unchanging even for various changes so as to achieve the automated updating. A generic framework capable to deal with the automated updating for manufacturing system simulation is constructed. The proposed modelling formalism is proved to be effective through experimental simulation system construction.