• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.712-717
• /
• 2008

In swarm robot systems, each robot must act by itself according to the its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method with SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of SVM is adopted in this paper.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.279-284
• /
• 2009

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method using many SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of Cascade SVM is adopted in this paper.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2000.11a
• /
• pp.34-37
• /
• 2000

The effect of novel N-crotyl-N,N-dimethyl-4-methylanilinium hexafluroantimonate (CMH) curing agent on cure behavior and thermal properties of DGEBA epoxy cationic system was investigated. From DSC measurements of DGEBA/CMH system, it was shown that this system exhibits an excellent thermal latent characteristic in a given temperature and reveals complex cure behavior as indicated by multiple exotherms. The conversion and conversion rate of DGEBA/CMH system increased with increasing the concentration of initiator due to high activity of CMH. Viscoelastic properties during gel formation of DGEBA with CMH were investigated by rheological techniques under isothermal condition. The gel time obtained from the modulus crossover. point t(G')=G", was affected by high curing temperature and concentration of CMH, resulting in high degree of network formation in cationic polymerization. The thermal stabilities were discussed in terms of the activation energy for decomposition and thermal factors determined from TGA measurements.ents.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.18 no.1
• /
• pp.35-40
• /
• 2018

Background: The sight of dental injection can bring about severe anxiety in children. Therefore, an alternative method that is convenient, effective, and keeps the needle hidden making it child friendly is necessary. The objective of the study was to compare the efficacy of a camouflaged syringe and conventional syringe on behavior and anxiety in 6-11-year-old children during local anesthesia administration. Methods: The study was a randomized, crossover clinical study including 30 children. Children were separated into two groups. Group 1 consisted of 15 children aged 6-8 years while group 2 consisted of 15 children aged 9-11 years. This study involved two sessions wherein all the children were injected using conventional and camouflaged syringes in separate sessions. Their behavior was assessed using the Faces, Legs, Activity, Cry, Consolability (FLACC) behavior pain scale and anxiety was assessed by measuring changes in pulse rate. Patient and operator preferences were compared. Results: The results showed a lower mean change in pulse rate and FLACC scores in the camouflaged group, suggesting a positive behavior and lesser anxiety with camouflaged syringes than with conventional syringes. Conclusions: The use of camouflaged syringes for anesthesia was demonstrated to be effective in improving the behavior of children and decreasing their anxiety, and is therefore recommended as an alternative to the use of conventional syringes for local anesthesia.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.131-137
• /
• 2006

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, the new learning and evolution method based on reinforcement learning having delayed reward ability and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. Reinforcement learning having delayed reward is still useful even though when there is no immediate reward. And by distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning is adopted in this paper. we verify the effectiveness of the proposed method by applying it to cooperative search problem.

• Elastomers and Composites
• /
• v.38 no.3
• /
• pp.213-226
• /
• 2003

The cure and rheological behavior of diglycidyl ether of bisphenol F/nadic methyl anhydride resin system with the kinds of imidazole were studied using a differential scanning calorimeter (DSC) and a rotational rheometer. The isothermal traces were employed to analyze cure reaction. The DGEBF/ anhydride conversion profiles showed autocatalyzed reaction characterized by maximum conversion rate at $20{\sim}40 %$ of the reaction. The rate constants ($k_1,\;k_2$) showed temperature dependance, but reaction order did not. The reaction order (m+n) was calculated to be close to 3. There are two reaction mechanisms with the kinds oi catalyst. The gel time was determined by using G'-G" crossover method, and the activation energy was obtained from this results. From measurement of rheological properties it was found that the logarithmic 1:elation time of fused silica filled DBEBF epoxy compounds linearly increased with the content of filler and decreased with temperature. The highly filled epoxy compounds showed typical pseudoplastic behavior, and the viscosity of those decreased with increasing maximum packing ratio.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.591-597
• /
• 2007

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, the new polygon based Q-learning algorithm and distributed genetic algorithms are proposed for behavior learning and evolution of collective autonomous mobile robots. And by distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning is adopted in this paper. we verify the effectiveness of the proposed method by applying it to cooperative search problem.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.157-160
• /
• 2001

This paper has been studied a Adaptive Mutation rate Genetic Algorithm Processor. Genetic Algorithm(GA) has some control parameters such as the probability of bit mutation or the probability of crossover. These value give a priori by the designer There exists a wide variety of values for for control parameters and it is difficult to find the best choice of these values in order to optimize the behavior of a particular GA. We proposed a Adaptive mutation rate GA within a steady-state genetic algorithm in order to provide a self-adapting mutation mechanism. In this paper, the proposed a adaptive mutation rate GAP is implemented on the FPGA board with a APEX EP20K600EBC652-3 devices. The proposed a adaptive mutation rate GAP increased the speed of finding optimal solution by about 10%, and increased probability of finding the optimal solution more than the conventional GAP

• Journal of the korean society of oceanography
• /
• v.35 no.1
• /
• pp.11-15
• /
• 2000

The scaling behavior of random fractals and multifractals is investigated numerically on the seabottom depth in the seabottom topography. In the self-affine structure the critical length for the crossover can be found from the value of standard deviations for the seabottom depth. The generalized dimension and the spectrum in the multifractal structure are discussed numerically, as it is assumed that the seabottom depth is located on a two-dimensional square lattice. For this case, the fractal dimension D$_0$ is respectively calculated as 1.312476, 1.366726, and 1.372243 in our three regions, and our result is compared with other numerical calculations.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.254-254
• /
• 2000

This paper presents a genetic programming based evolutionary strategy for on-line adaptive learnable evolvable hardware. genetic programming can be useful control method for evolvable hardware for its unique tree structured chromosome. However it is difficult to represent tree structured chromosome on hardware, and it is difficult to use crossover operator on hardware. Therefore, genetic programming is not so popular as genetic algorithms in evolvable hardware community in spite of its possible strength. We propose a chromosome representation methods and a hardware implementation method that can be helpful to this situation. Our method uses context switchable identical block structure to implement genetic tree on evolvable hardware. We composed an evolutionary strategy (or evolvable hardware by combining proposed method with other's striking research results. Proposed method is applied to the autonomous mobile robots cooperation problem to verify its usefulness.