• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.686-691
• /
• 2011

This study is concerned with the identification of fuzzy models. To address the optimization of fuzzy model, we proposed an improved space search evolutionary algorithm (ISSA) which is realized with the combination of space search algorithm and Gaussian mutation. The proposed ISSA is exploited here as the optimization vehicle for the design of fuzzy models. Considering the design of fuzzy models, we developed a hybrid identification method using information granulation and the ISSA. Information granules are treated as collections of objects (e.g. data) brought together by the criteria of proximity, similarity, or functionality. The overall hybrid identification comes in the form of two optimization mechanisms: structure identification and parameter identification. The structure identification is supported by the ISSA and C-Means while the parameter estimation is realized via the ISSA and weighted least square error method. A suite of comparative studies show that the proposed model leads to better performance in comparison with some existing models.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.312-318
• /
• 2022

The article notes that one of the reasons for the crisis in education was the sharp discrepancy between the emerging new forms and content and the model of macro-management that has developed over the decades. The level of management of the educational system did not emerge as a specific activity characterized by its own mechanisms and processes, just as qualified carriers of this activity - professionals - managers - did not appear. At the same time, there is practically no theoretical and methodological model of the macrolevel of education management, that is, management of the educational system as an integral structure.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.248-253
• /
• 2015

In order to adapt to human's life and perform missions, a humanoid robot needs a height at least similar with children's. In this paper, we proposed a humanoid robot which is like a child who is taller than 1m. We presented showing the humanoid robot's kinematics, designing of a three-dimensional model, developing mechanisms, and the hardware structures using servo motors and compact size PC. Through this process, we designed and manufactured child humanoid robot 'CHARLES(Cognitive Humanoid Autonomous Robot with Learning and Evolutionary Systems)' that is robot is 1m 10cm tall and 8.16kg in weight. For robot's walking, we applied to ZMP-based walking technique and the creation algorithm is applied for walking patterns. Through experiments, we analyzed walking patterns according to the creation and changing parameter values.

• Korean Journal of Environmental Biology
• /
• v.40 no.4
• /
• pp.525-549
• /
• 2022

The process of biological invasion is led by the dynamics of a population as a demographic and evolutionary unit. Spatial structure can affect the population dynamics, and it is worth being considered in research on biological invasion which is always accompanied by dispersal. Metapopulation theory is a representative approach to spatially structured populations, which is chiefly applied in the field of ecology and evolutionary biology despite the controversy about its definition. In this study, metapopulation was considered as a spatially structured population that includes at least one subpopulation with significant extinction probability. The early phase of the invasion is suitable to be analyzed in aspects of the metapopulation concept because the introduced population usually has a high extinction probability, and their ecological·genetic traits determining the invasiveness can be affected by the metapopulation structure. Although it is important in the explanation of the prediction of the invasion probability, the metapopulation concept is rarely used in ecological research about biological invasion in Korea. It is expected that applying the metapopulation theory can supply a more detailed investigation of the invasion process at the population level, which is relatively inadequate in Korea. In this study, a framework dividing the invasive metapopulation into long- and middle-distance scales by the relative distance of movement to the natural dispersal range of species is proposed to easily analyze the effect of a metapopulation in real cases. Increased understanding of the mechanisms underlying invasions and improved prediction of future invasion risk are expected with the metapopulation concept and this framework.

• Journal of Ecology and Environment
• /
• v.31 no.2
• /
• pp.89-95
• /
• 2008

Sensing the approach of a predator is critical to the survival of prey, especially when the prey has no choice but to escape at a precisely timed moment. Escape behavior has been approached from both proximate and ultimate perspectives. On the proximate level, empirical research about electrophysiological mechanisms for detecting predators has focused on vision, an important modality that helps prey to sense approaching danger. Studies of looming-sensitive neurons in locusts are a good example of how the selective sensitivity of nervous systems towards specific targets, especially approaching objects, has been understood and realistically modeled in software and robotic systems. On the ultimate level, general optimality models have provided an evolutionary framework by considering costs and benefits of visually elicited escape responses. A recent paper showed how neural network models can be used to understand the evolution of visually mediated antipredatory behaviors. We discuss this new trend towards integration of these relatively disparate approaches, the proximate and the ultimate perspectives, for understanding of the evolution of behavior of predators and prey. Focusing on one of the best-studied escape pathway models, the Orthopteran LGMD/DCMD pathway, we discuss how ultimate-level optimality modeling can be integrated with proximate-level studies of escape behaviors in animals.

• IMMUNE NETWORK
• /
• v.14 no.1
• /
• pp.7-13
• /
• 2014

Molecular mimicry is an attractive mechanism for triggering autoimmunity. In this review, we explore the potential role of evolutionary conserved bacterial proteins in the production of autoantibodies with focus on granulomatosis with polyangiitis (GPA) and rheumatoid arthritis (RA). Seven autoantigens characterized in GPA and RA were BLASTed against a bacterial protein database. Of the seven autoantigens, proteinase 3, type II collagen, binding immunoglobulin protein, glucose-6-phosphate isomerase, ${\alpha}$-enolase, and heterogeneous nuclear ribonuclear protein have well-conserved bacterial orthologs. Importantly, those bacterial orthologs are also found in human-associated bacteria. The wide distribution of the highly conserved stress proteins or enzymes among the members of the normal flora and common infectious microorganisms raises a new question on how cross-reactive autoantibodies are not produced during the immune response to these bacteria in most healthy people. Understanding the mechanisms that deselect auto-reactive B cell clones during the germinal center reaction to homologous foreign antigens may provide a novel strategy to treat autoimmune diseases.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.483-487
• /
• 2005

We introduce a new architecture of hetero-hybridized feed-forward neural networks composed of fuzzy set-based polynomial neural networks (FSPNN) and polynomial neural networks (PM) that are based on a genetically optimized multi-layer perceptron and develop their comprehensive design methodology involving mechanisms of genetic optimization and Information Granulation. The construction of Information Granulation based HFSPNN (IG-HFSPNN) exploits fundamental technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks, and genetic algorithms(GAs) and Information Granulation. The architecture of the resulting genetically optimized Information Granulation based HFSPNN (namely IG-gHFSPNN) results from a synergistic usage of the hybrid system generated by combining new fuzzy set based polynomial neurons (FPNs)-based Fuzzy Neural Networks(PM) with polynomial neurons (PNs)-based Polynomial Neural Networks(PM). The design of the conventional genetically optimized HFPNN exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being tuned by using Genetie Algorithms throughout the overall development process. However, the new proposed IG-HFSPNN adopts a new method called as Information Granulation to deal with Information Granules which are included in the real system, and a new type of fuzzy polynomial neuron called as fuzzy set based polynomial neuron. The performance of the IG-gHFPNN is quantified through experimentation.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2888-2890
• /
• 2005

In this paper, we introduce a new structure of fuzzy-neural networks Fuzzy Set-based Polynomial Neural Networks (FSPNN). The two underlying design mechanisms of such networks involve genetic optimization and information granulation. The resulting constructs are Fuzzy Polynomial Neural Networks (FPNN) with fuzzy set-based polynomial neurons (FSPNs) regarded as their generic processing elements. First, we introduce a comprehensive design methodology (viz. a genetic optimization using Genetic Algorithms) to determine the optimal structure of the FSPNNs. This methodology hinges on the extended Group Method of Data Handling (GMDH) and fuzzy set-based rules. It concerns FSPNN-related parameters such as the number of input variables, the order of the polynomial, the number of membership functions, and a collection of a specific subset of input variables realized through the mechanism of genetic optimization. Second, the fuzzy rules used in the networks exploit the notion of information granules defined over systems variables and formed through the process of information granulation. This granulation is realized with the aid of the hard C- Means clustering (HCM). The performance of the network is quantified through experimentation in which we use a number of modeling benchmarks already experimented with in the realm of fuzzy or neurofuzzy modeling.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1505-1509
• /
• 2005

This paper introduces a new architecture of genetically optimized self-organizing fuzzy polynomial neural networks by means of information granulation. The conventional SOFPNNs developed so far are based on mechanisms of self-organization and evolutionary optimization. The augmented genetically optimized SOFPNN using Information Granulation (namely IG_gSOFPNN) results in a structurally and parametrically optimized model and comes with a higher level of flexibility in comparison to the one we encounter in the conventional FPNN. With the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The GA-based design procedure being applied at each layer of genetically optimized self-organizing fuzzy polynomial neural networks leads to the selection of preferred nodes with specific local characteristics (such as the number of input variables, the order of the polynomial, a collection of the specific subset of input variables, and the number of membership function) available within the network. To evaluate the performance of the IG_gSOFPNN, the model is experimented with using gas furnace process data. A comparative analysis shows that the proposed IG_gSOFPNN is model with higher accuracy as well as more superb predictive capability than intelligent models presented previously.

• Animal cells and systems
• /
• v.3 no.1
• /
• pp.1-7
• /
• 1999

Gonadotropin-releasing hormone (GnRH) was originally isolated as a hypothalamic peptide that regulates reproduction by stimulating the release of gonadotropins. Using comparative animal models has led to the discovery that GnRH has a more ancient evolutionary origin. Durinq evolution GnRH peptide underwent gene duplication and structural changes to give rise to multiple molecular forms of GnRHs. Mammalian GnRH initially considered to be the sole molecular form, is now grouped as a family of peptides along with GnRH variants determined from representatives in all classes of vertebrates. Vertebrate species including primates and humanshave more than one GnRH variant in individual brains; a unique GnRH form in the forebrain and chicken IIGnRH in the midbrain. Furthermore, several species of bony fish have three molecular variants of GnRH: salmon GnRH sea-bream GnRH and chicken II GnRH. Also, it has been shown that in addition to the olfactory placodes and the midbrain, there is a third embryonic source of GnRH neurons from the basal diencephalon in birds and fish, which might be true for other vertebrates. Therefore, comparative animal models like fish with discrete sites of expression of three molecular variants of GnRH in individual brains, could provide insight into novel functions of GnRH variants, conservation of gene regulation, and mechanisms governing reproduction in vertebrates.