Search Sites

Transactions of the Institute of Systems, Control and Information Engineers Vol. 28 (2015), No. 5

ISIJ International
belloff
ONLINE ISSN: 2185-811X
PRINT ISSN: 1342-5668
Publisher: THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)

Backnumber

  1. Vol. 36 (2023)

  2. Vol. 35 (2022)

  3. Vol. 34 (2021)

  4. Vol. 33 (2020)

  5. Vol. 32 (2019)

  6. Vol. 31 (2018)

  7. Vol. 30 (2017)

  8. Vol. 29 (2016)

  9. Vol. 28 (2015)

  10. Vol. 27 (2014)

  11. Vol. 26 (2013)

  12. Vol. 25 (2012)

  13. Vol. 24 (2011)

  14. Vol. 23 (2010)

  15. Vol. 22 (2009)

  16. Vol. 21 (2008)

  17. Vol. 20 (2007)

  18. Vol. 19 (2006)

  19. Vol. 18 (2005)

  20. Vol. 17 (2004)

  21. Vol. 16 (2003)

  22. Vol. 15 (2002)

  23. Vol. 14 (2001)

  24. Vol. 13 (2000)

  25. Vol. 12 (1999)

  26. Vol. 11 (1998)

  27. Vol. 10 (1997)

  28. Vol. 9 (1996)

  29. Vol. 8 (1995)

  30. Vol. 7 (1994)

  31. Vol. 6 (1993)

  32. Vol. 5 (1992)

  33. Vol. 4 (1991)

  34. Vol. 3 (1990)

  35. Vol. 2 (1989)

  36. Vol. 1 (1988)

Transactions of the Institute of Systems, Control and Information Engineers Vol. 28 (2015), No. 5

Genetic Programming for Cooperative Single-Objective Optimization

Keiko Ono, Masahito Kumano, Masahiro Kimura

pp. 173-180

Abstract

We consider a method for solving cooperative single-objective optimization problems using genetic programming. The cooperative single-objective optimization problems are the special cases of single-objective optimization problems, where 1) multi-objective functions are defined, 2) the goal of this problem is to find optimal solution sets which each contain a different solution for each objective function, 3) cooperative evolving between objective-functions is effective for performance improvement. Many real-world systems involve cooperative single-objective optimization in their operations, so it is important to deal with this kind of optimization problems. In this paper, we first give the problem definition of a single-objective optimization problem, and then present a genetic programming method for a cooperative single-objective optimization problem which can collaborate among components in exchanging frequent tree structures extracted from good individuals.

Bookmark

Share it with SNS

Article Title

Genetic Programming for Cooperative Single-Objective Optimization

Development of Keihanna Eco City Community Energy Management System (CEMS)

Satoko Sakajo, Masaki Inomoto, Yoshiyuki Takuma, Masafumi Iwata

pp. 181-188

Abstract

In recent years, a lot of energy-smart community demonstration projects are being conducted around the world. The principal concept is the optimization of energy utilization in the whole community not the individuals in order to contribute to the coexistence of CO2 reduction and QOL(Quality of Life). CEMS (Community Energy Management System) is one of the key technologies,which manages power demand and supply appropriately in the community. We developed Community EMS which cooperate with and request demand response to consumer EMS involving HEMS,BEMS, EV-charging management center through “Keihanna Eco-City Next Generation Energy and Social System Demonstration Project ”. CEMS also control community storage battery in order to compensate for the lack of demand response. In this paper we propose the method to improve the effect of demand response and describe the verification through Keihanna Demonstration Project.

Bookmark

Share it with SNS

Article Title

Development of Keihanna Eco City Community Energy Management System (CEMS)

Machine Learning Algorithm for the Fitness Landscape Learning Evolutionary Computation

Taku Hasegawa, Naoki Mori, Keinosuke Matsumoto

pp. 189-197

Abstract

One of the most important issues for evolutionary computation (EC) is to consider fitness landscape and the number of fitness evaluations. Especially, reducing the number of fitness evaluations is required in applications of EC to various kind of problems. In this paper, we proposed a novel EC framework called the Fitness Landscape Learning Evolutionary Computation: FLLEC with surrogate model which can predict the ranks of two individuals using SVM. The effectiveness of the proposed method is confirmed by computer simulation taking an Nk-landscape problem and a knapsack problem as examples by Air GA which is one of the FLLEC.

Bookmark

Share it with SNS

Article Title

Machine Learning Algorithm for the Fitness Landscape Learning Evolutionary Computation

Statistical Mechanical Analysis of Active Noise Control with Time-varying Primary Path

Nobuhiro Egawa, Yoshinobu Kajikawa, Seiji Miyoshi

pp. 198-204

Abstract

We analyze the learning curves in active noise control with a time-varying primary path using a statistical-mechanical method. The cross-correlation between the element of a primary path and that of the adaptive filter and autocorrelations of the elements of the adaptive filter are treated as macroscopic variables. We obtain simultaneous differential equations that describe the dynamical behaviors of the macroscopic variables under the condition that the tapped-delay line is sufficiently long. We analyze the case where the primary-path has the Markovian property. As a result, we show that an optimal step size is clear when time is relatively small and it disappears from the practical viewpoint as time passed.

Bookmark

Share it with SNS

Article Title

Statistical Mechanical Analysis of Active Noise Control with Time-varying Primary Path

Sound-aided Tracing System for Visually Impaired People

Yuki Uranishi, Hikaru Takizawa, Shunsuke Yoshimoto, Masataka Imura, Osamu Oshiro

pp. 205-212

Abstract

Barrier-free signs, such as a sound device on a traffic signaling mechanism or a Braille on a map,are widely used in a modern society for the benefit of the visually impaired people. This paper proposes a sound-aided tracing system with a mobile touch screen for understanding a structure of an image. The proposed system represents a structural feature of a line-drawing image with a guiding sound. The structural features are extracted from the image and guide sounds corresponding to the features are assigned to the pixels on the image. A prototype of the map guiding system has been implemented. The experimental results with the prototype have shown that the proposed system enables subjects to trace a correct route on the map, although there remain some usability improvements for practical use.

Bookmark

Share it with SNS

Article Title

Sound-aided Tracing System for Visually Impaired People

A Study of Optimal Guide Procedure in Building Using Agent Simulation and Optimal Location Problem

Keita Sugiura, Masahiro Arakawa

pp. 213-220

Abstract

In this paper, a study of optimal guide method is discussed to effectively evacuate people in floor in building by using agent simulation. The agent simulation is developed to evaluate behavior of evacuee. Guide sign is focused on to effectively evacuate people in floor. Mathematical model is constructed to decide the optimal locations of emergency guide sign. The agent simulation is performed to evaluate the optimal locations of the signs obtained by the mathematical model. Furthermore, Guide Support Sign system which dynamically controls direction of exit is proposed to effectively guide evacuee under the condition that people are ununiformly distributed on the floor. The effectiveness of the Guide Support Sign system is evaluated by the agent simulation.

Bookmark

Share it with SNS

Article Title

A Study of Optimal Guide Procedure in Building Using Agent Simulation and Optimal Location Problem

Visualization Technique for Large-scale Data by Particle-based Volume Rendering

Takuma Kawamura, Yasuhiro Idomura, Hiroko (Nakamura) Miyamura, Toshiyuki Imamura, Hiroshi Takemiya

pp. 221-227

Abstract

In analyzing and understanding complicated simulation results, it is useful to visualize large-scale data via volume rendering technique. However, volume rendering in existing remote visualization tools has server bottlenecks in the processing speed, the memory size and the data transfer. The proposed remote visualization system using Particle-Based Volume Rendering resolves these bottlenecks by converting large-scale volume data into small visualization particle data, and enables interactive remote visualization. Particle data processing on massively parallel supercomputers shows excellent strong scaling up to 1,000 cuncurrency, and data with 108 cells is processed in a few seconds.

Bookmark

Share it with SNS

Article Title

Visualization Technique for Large-scale Data by Particle-based Volume Rendering

Arm Angle Estimation for Computational System Rehabilitation with Range Image Sensor

Junya Kusaka, Takenori Obo, Naoyuki Kubota

pp. 228-235

Abstract

This paper proposes a method of arm angle estimation by using a range image sensor that can detect each angle position in the non-contact measurement. We can solve the inverse kinematics by using relative position data, but the estimation quality is not good owing to the measurement noise of the sensor. Therefore, we apply genetic algorithm to solve the optimization problem. Furthermore, if we can model the human motion pattern from the measured data, it can be prevented falling into the local solution. In the method, we apply a feed-forward neural network (NN) for learning the motion patterns. In this paper, we show some experimental results of the angle estimation and discuss the effectiveness through the experimental results.

Bookmark

Share it with SNS

Article Title

Arm Angle Estimation for Computational System Rehabilitation with Range Image Sensor

You can use this feature after you logged into the site.
Please click the button below.

Advanced Search

Article Title

Author

Abstract

Journal Title

Year

Please enter the publication date
with Christian era
(4 digits).

Please enter your search criteria.