研究者詳細 - 大西　圭

論文 - 大西　圭

分割表示57 件中 1 - 20 件目／全件表示 >>

Noncooperative Population-Based Search Relying on Spatial and/or Temporal Scale-Free Behaviors of Individuals 査読有り国際誌

Ohnishi K.

Journal of Robotics and Mechatronics ( 富士技術出版株式会社 ) 36 ( 3 ) 618 - 627 2024年06月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

Although individuals of species engaging in cooperative foraging behaviors are often modeled as swarm intelligence optimization algorithms, there are also several species whose individuals take noncooperative foraging behaviors. Some such species exhibit common behaviors, which we call scale-free behaviors in this study. A type of scale-free behavior is spatial scale-free behavior, in which the moving distance of an individual from the present food source follows a power-law distribution. Second, the staying duration of an individual at the current food source follows a power-law distribution, and this behavior is called temporal scale-free behavior. We propose two types of noncooperative population-based search methods, based on the two types of scale-free behaviors. We also conducted simulations to compare the two methods, assuming static and dynamic environments in which the position of the food source did not change and changed, respectively. The simulation results showed that temporal scale-free behavior is suitable for specific problems in which individuals around the global optimum can be eliminated probabilistically, and spatial scale-free behavior is suitable for problems in which such elimination never occurs. In other words, the two types of scale-free behaviors are complementary. Next, we first assume problems for which we cannot know if the probabilistic elimination of individuals occurs in advance, and then propose a search method that selects an appropriate type of scale-free behavior for individuals during the search. The simulation results showed that this method demonstrates a good search performance, on average, for such problems.

DOI： 10.20965/jrm.2024.p0618

Scopus

CiNii Research

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85197351648&origin=inward

Probabilistic Model Building Evolutionary Algorithm Using the Same Type and Size of Model for Any Binary Optimization Problems 査読有り国際誌

Kishimoto A., Ohnishi K.

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024 2024年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose a new probabilistic model building evolutionary algorithm that uses the same type and size of probabilistic model for any binary optimization problems. The proposed method represents a population as a binary matrix for any binary optimization problems and solves a given problem by transforming the population in the form of matrix to better one with 512 production rules of cellular automaton. Concretely, the proposed method builds a probabilistic model for generating new solution candidates while applying the 512 production rules to the matrix representing the population. The probabilistic model consists of the 512 inverse production rules and their application probabilities. The strong point of the proposed method is to be able to transform any binary optimization problems to the same size of 512-bit production rule optimization problem. Since the proposed method treats any binary optimization problems in a unified manner, we can easily explore a robust method for various binary optimization problems as the proposed method with particular configurations. As the first evaluation of the proposed method, we apply the proposed method to the same kind but different sizes of problems. The results show that depending strongly on the bit patterns of the global optima, the proposed method with the same configurations realizes a good scalability of the number of function evaluations required for obtaining near optimum to the problem size growth.

DOI： 10.1109/SCISISIS61014.2024.10760174

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85214668926&origin=inward

Real-time Support for Solution Search in Human-based Evolutionary Computation 査読有り国際誌

Utsumi T., Muta H., Tsung C.K., Ohnishi K.

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024 2024年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose a method to extract important words common to good solution candidates in human-based evolutionary computation, like building blocks in genetic algorithms, and present them to the participants in a realtime manner. We also propose a method to obtain and present words similar to the important ones. Furthermore, we propose a method to measure the similarity between participants using the important words for each participant and present it to the participants. All of the proposed methods help participants solve problems by reducing the cognitive load of finding key words and persons. We implement those methods into a human-based evolutionary computation system and evaluate the proposed methods through human subject experiments using the system. The experimental results show that although the evaluation result to the outputs from the system incorporating the methods by a third party is not so good, the system is shown to be useful for participants to create solutions.

DOI： 10.1109/SCISISIS61014.2024.10759881

Kyutacar

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85214653519&origin=inward

人間ベース進化計算とChatGPTの実験による比較

大西圭, 釘宮由成, 吉川大弘

日本知能情報ファジィ学会ファジィシステムシンポジウム講演論文集 ( 日本知能情報ファジィ学会 ) 40 ( 0 ) 558 - 563 2024年01月

群知能最適化手法間の類似度測定方法の提案

大西圭, 村上楓

日本知能情報ファジィ学会ファジィシステムシンポジウム講演論文集 ( 日本知能情報ファジィ学会 ) 40 ( 0 ) 578 - 583 2024年01月

Comparison of Quality-based and Quantity-based Real-time Rankings of Participants in Human-based Evolutionary Computation Systems 査読有り国際誌

Hiroki Muta, Kei Ohnishi

The 20th World Congress of the International Fuzzy Systems Association (IFSA 2023) 146 - 152 2023年08月

協調戦略を持つ個体の集団による生存ゲームとしての進化計算

大西圭

日本知能情報ファジィ学会ファジィシステムシンポジウム講演論文集 ( 日本知能情報ファジィ学会 ) 39 ( 0 ) 672 - 677 2023年01月

ビルディングブロック提示機能を実装した人間ベース進化計算システム

牟田大輝, 大西圭

日本知能情報ファジィ学会ファジィシステムシンポジウム講演論文集 ( 日本知能情報ファジィ学会 ) 39 ( 0 ) 678 - 683 2023年01月

Swarm Intelligence Numerical Optimization Algorithm Representing Individuals as Dynamic Graphs in the Euclidean Search Space 査読有り国際誌

Hayashi K., Ohnishi K.

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023 1201 - 1207 2023年01月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose a new swarm intelligence numerical optimization algorithm that represents individuals as dynamic graphs in the Euclidean search space. We call it Graph Building Optimization Algorithm or GBO. The unique point of GBO is that an individual is represented by a dynamic graph whose nodes have coordinates (search points) in the Euclidean search space. Due to this unique point, we can draw a GBO's search process as a generation-transition of a feature of a graph. It is expected that we can obtain better understandings on a given problem by comparing the generation-transition for the given problem to the baseline for the simplest unimodal problem. We assume the maximum node degree in the best individual as the feature and the generation-transition of the feature for F1 in the CEC'13 test problems as the baseline. We demonstrate that we can guess the characteristics of other 27 problems in the CEC'13 test problems by comparing their generation-transitions to the baseline. In addition, we evaluate GBO using the same problems and show that GBO is capable of finding good solutions for various problems.

DOI： 10.1109/SSCI52147.2023.10371876

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85182950881&origin=inward

Framework of Systems for Creating Intelligent Behaviors of Imaginary Creatures for Humans 査読有り国際誌

Ohnishi K., Kumano Y.

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023 1195 - 1200 2023年01月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

The paper proposes a framework of systems for creating intelligent behaviors of imaginary creatures for humans, which is built upon a framework of swarm intelligence optimization algorithms. The paper assumes and models an imaginary slime mold, which is an amoeboid unicellular creature, as an imaginary creature in the framework concretely. In addition, the paper conducts basic evaluations of the framework. Various swarm intelligence optimization algorithms have been proposed so far, but there is a common feature among them. That is that a set of search points in a search space, which are called individuals, move around in the space according to algorithm specific rules using fitness values of the individuals, and the differences among algorithms are in algorithm specific rules. Therefore, under the use of one swarm intelligence optimization algorithm, that is, one particular set of rules, if a fitness function is varied, behaviors of individuals are also varied. Based on this fact, the proposed framework optimizes a parametric fitness function for individuals to behave intelligently for a human. In the basic evaluation of the concrete system, a fitness function of computer program which returns a fitness value calculated with a distribution of individuals is used instead of a human, and it is demonstrated that optimization of a parametric fitness function indeed yields desired behaviors of individuals.

DOI： 10.1109/SSCI52147.2023.10371904

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85182934151&origin=inward

Experiment to Investigate Awareness of Tastes for Users in Interactive Evolutionary Computation 査読有り国際誌

Obata R., Ohnishi K., Fukumoto M., Ohsaki M.

2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2022 2022年11月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Interactive evolutionary computation (IEC) is one type of evolutionary computation which includes a human user as an evaluation system. Unlike a computer program in standard EC, an IEC user is expected to be aware of his/her tastes more clearly with iteration of evaluations. However, there has not been any research that tries to confirm it so far. If it is confirmed, IEC is desired to design based on that fact. In the paper we first propose an experimental way to investigate it and then conduct an experiment following the proposed way. In addition, we try to extract features of solutions which correspond to the awareness well. The results show that most subjects can be more aware of their tastes with iteration and the extracted features correspond to the awareness well.

DOI： 10.1109/SCISISIS55246.2022.10002067

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146685707&origin=inward

Evolutionary Computation System Solving Group Decision Making Multiobjective Problems for Human Groups 査読有り国際誌

Hironao Sakamoto, Kotaro Nakamoto, and Kei Ohnishi

Journal of Advanced Computational Intelligence and Intelligent Informatics (JACIII) 26 ( 2 ) 196 - 205 2022年03月

Test Problem in Which Bits Used for Fitness Calculation Depend on Bit Pattern" 査読有り国際誌

Kei Ohnishi, Daiki Koga, and Tian-Li Yu

IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021) 2021年12月

Non-generational Geometric Semantic Genetic Programming 査読有り国際誌

Daiki Koga and Kei Ohnishi

IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021) 2021年12月

NNR-GL: A Measure to Detect Co-Nonlinearity Based on Neural Network Regression Regularized by Group Lasso 査読有り国際誌

Miho Ohsaki, Naoya Kishimoto, Hayato Sasaki, Ryoji Ikeura, Shigeru Katagiri, Kei Ohnishi, Yakub Sebastian, and Patrick Then

IEEE Access 9 132033 - 132052 2021年09月

Evaluation of the Neural-network-based Method to Discover Sets and Representatives of Nonlinearly Dependent Variables 査読有り

Ohsaki M., Sasaki H., Kishimoto N., Katagiri S., Ohnishi K., Sebastian Y., Then P.

2021 5th IEEE International Conference on Cybernetics, CYBCONF 2021 101 - 106 2021年06月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

It is desired in a variety of fields to identify which variables are dependent, and variable dependence measures have been studied. The majority of such measures detect a linear or a certain range of nonlinear dependence between paired variables. To go beyond them, a method based on Neural Network Regression, Group Lasso, and Information Aggregation has been proposed in our past study. It can detect a wide range of nonlinear dependences among multi variables and discover the sets and representatives of the detected dependences. Its fundamental effectiveness has already been examined using synthesized artificial datasets containing a single dependence. For further evaluation in the present study, we conducted an experiment using those containing multi dependences. The proposed method succeeded in discovering the sets and representatives, and its performance was robust to data size and noise rate. The experimental results suggested that the proposed method works well for difficult tasks to handle multi dependences.

DOI： 10.1109/CYBCONF51991.2021.9464151

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85113741640&origin=inward

Acquiring Consensus Solutions by Multi-human-agent-based Evolutionary Computation 査読有り国際誌

Sakamoto H., Nakamoto K., Ohnishi K.

2021 5th IEEE International Conference on Cybernetics, CYBCONF 2021 12 - 18 2021年06月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

The paper proposes a system to acquire consensus solutions among people to a multiobjective problem which does not require direct communication among the people. It relies on multi-human-agent-based evolutionary computation (Mhab-EC) with a mechanism for making solutions of agents converged. In the system, people prepare their own agents who can be tuned by themselves, and then submit their agents to a simulation of Mhab-EC and acquire a convergence solution from the simulation. Then, examining the simulation result, they tune their agents again to be closer to their desired solutions and submit the agents to the simulation and obtain a convergence solution. The mechanism repeats this procedure pre-determined times and outputs a convergence solution of the final simulation as the consensus solution. In basic evaluation of the system, we focus on if the system can make solution converged and show that it can indeed do it.

DOI： 10.1109/CYBCONF51991.2021.9464147

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85113724521&origin=inward

Genetic algorithms using neural network regression and group lasso for dynamic selection of crossover operators 査読有り

Kato M., Ohsaki M., Ohnishi K.

2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2020 2020年12月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose real-coded genetic algorithms that utilize a method for detecting dependency relationships between variables. The method consists of neural network regression and group lasso. The proposed genetic algorithms select an appropriate crossover operator based on dependency information between variables, which are obtained from past solution candidates. Simulation results using the CEC'13 benchmark functions show that the proposed algorithms outperform conventional real-coded genetic algorithms.

DOI： 10.1109/SCISISIS50064.2020.9322697

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85100428039&origin=inward

An evolutionary algorithm inspired by evolution of birdsong grammars to quickly obtain practical solutions to large-scaled problems 査読有り

Tabata N., Ohnishi K.

2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2020 2020年12月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We propose an evolutionary algorithm inspired by evolution of birdsong grammars. The proposed algorithm is designed to quickly obtain practical solutions to large-scaled problems. The main mechanism for obtaining practical solutions quickly is to represent solution candidates in a compact way using grammars, that is to say, to make the search space smaller than the original one using grammars. Also, we apply the algorithm to a large-scaled OneMax problem and its variants. The simulation results show that the algorithm tends to quickly produce solution candidates with simple bit patterns and with not so bad fitness values for large-scaled problems as a bit pattern of the global optimum becomes more random. That can be considered as that practical solutions to large-scaled problems are obtained quickly. It is also shown that when the problem size is smaller, the algorithm tends to produce a precise bit pattern of the global optimum.

DOI： 10.1109/SCISISIS50064.2020.9322703

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85100402217&origin=inward

An empirical investigation on evolutionary algorithm evolving developmental timings 査読有り

Ohnishi K., Hamano K., Koeppen M.

Electronics (Switzerland) 9 ( 11 ) 1 - 27 2020年11月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

Recently, evolutionary algorithms that can efficiently solve decomposable binary optimization problems have been developed. They are so-called model-based evolutionary algorithms, which build a model for generating solution candidates by applying a machine learning technique to a population. Their central procedure is linkage detection that reveals a problem structure, that is, how the entire problem consists of sub-problems. However, the model-based evolutionary algorithms have been shown to be ineffective for problems that do not have relevant structures or those whose structures are hard to identify. Therefore, evolutionary algorithms that can solve both types of problems quickly, reliably, and accurately are required. The objective of the paper is to investigate whether the evolutionary algorithm evolving developmental timings (EDT) that we previously proposed can be the desired one. The EDT makes some variables values more quickly converge than the remains for any problems, and then, decides values of the remains to obtain a higher fitness value under the fixation of the variables values. In addition, factors to decide which variable values converge more quickly, that is, developmental timings are evolution targets. Simulation results reveal that the EDT has worse performance than the linkage tree genetic algorithm (LTGA), which is one of the state-of-the-art model-based evolutionary algorithms, for decomposable problems and also that the difference in the performance between them becomes smaller for problems with overlaps among linkages and also that the EDT has better performance than the LTGA for problems whose structures are hard to identify. Those results suggest that an appropriate search strategy is different between decomposable problems and those hard to decompose.

DOI： 10.3390/electronics9111866

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85095940596&origin=inward

　前のページ- 次のページ　

<大西 圭>

論文 - 大西 圭

<大西　圭>

論文 - 大西　圭