• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.11-25
• /
• 2012

We present the method to infer Context-Free Grammars by applying genetic algorithm to the Binary Third-order Recurrent Neural Networks(BTRNN). BTRNN is a multiple-layered architecture of recurrent neural networks, each of which is corresponding to an input symbol, and is combined with external stack. All parameters of BTRNN are represented as binary numbers and each state transition is performed with any stack operation simultaneously. We apply Genetic Algorithm to BTRNN chromosomes and obtain the optimal BTRNN inferring context-free grammar of positive and negative input patterns. This proposed method infers BTRNN, which includes the number of its states equal to or less than those of existing methods of Discrete Recurrent Neural Networks, with less examples and less learning trials. Also BTRNN is superior to the recent method of chromosomes representing grammars at recognition time complexity because of performing deterministic state transitions and stack operations at parsing process. If the number of non-terminals is p, the number of terminals q, the length of an input string k, and the max number of BTRNN states m, the parallel processing time is O(k) and the sequential processing time is O(km).

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.39-45
• /
• 2008

This paper considers the multi-objective optimization of a multi-service arrayed waveguide grating-based single-hop WDM network with the two conflicting objectives of maximizing throughput while minimizing delay. This paper presents a genetic algorithm based methodology for finding the optimal throughput-delay tradeoff curve, the so-called Pareto-optimal frontier. Genetic algorithm based methodology provides the network architecture parameters and the Medium Access Control protocol parameters that achieve the Pareto-optima in a computationally efficient manner. The numerical results obtained with this methodology provide the Pareto-optimal network planning and operation solution for a wide range of traffic scenarios. The presented methodology is applicable to other networks with a similar throughput-delay tradeoff.

• Animal Bioscience
• /
• v.34 no.6
• /
• pp.967-974
• /
• 2021

Objective: The objective of this study was to estimate the genetic correlation (rpc) of growth performance between purebred (Duroc and Korean native) and synthetic (WooriHeukDon) pigs using a single-step method. Methods: Phenotypes of 15,902 pigs with genotyped data from 1,792 pigs from a nucleus farm were used for this study. We estimated the rpc of several performance traits between WooriHeukDon and purebred pigs: day of target weight (DAY), backfat thickness (BF), feed conversion rate (FCR), and residual feed intake (RFI). The variances and covariances of the studied traits were estimated by an animal multi-trait model that applied the Bayesian inference. Results: rpc within traits was lower than 0.1 for DAY and BF, but high for FCR and RFI; in particular, rpc for RFI between Duroc and WooriHeukDon pigs was nearly 1. Comparison between different traits revealed that RFI in Duroc pigs was associated with different traits in WooriHeukDon pigs. However, the most of rpc between different traits were estimated with low or with high standard deviation. Conclusion: The results indicated that there were substantial differences in rpc of traits in the synthetic WooriHeukDon pigs, which could be caused by these pigs having a more complex origin than other crossbred pigs. RFI was strongly correlated between Duroc and WooriHeukDon pigs, and these breeds might have similar single nucleotide polymorphism effects that control RFI. RFI is more essential for metabolism than other growth traits and these metabolic characteristics in purebred pigs, such as nutrient utilization, could significantly affect those in synthetic pigs. The findings of this study can be used to elucidate the genetic architecture of crossbred pigs and help develop new breeds with target traits.

• Journal of the Society of Naval Architects of Korea
• /
• v.49 no.1
• /
• pp.68-78
• /
• 2012

A layout of an LNG FPSO should be elaborately determined as compared with that of an onshore plant because many topside process systems are installed on the limited area; the deck of the LNG FPSO. Especially, the layout should be made as multi-deck, not single-deck and have a minimum area. In this study, a multi-floor layout for the liquefaction process, the dual mixed refrigerant(DMR) cycle, of LNG FPSO was determined by using the optimization technique. For this, an optimization problem for the multi-floor layout was mathematically formulated. The problem consists of 589 design variables representing the positions of topside process systems, 125 equality constraints and 2,315 inequality constraints representing limitations on the layout of them, and an objective function representing the total layout cost. To solve the problem, a hybrid optimization method that consists of the genetic algorithm(GA) and sequential quadratic programming(SQP) was used in this study. As a result, we can obtain a multi-floor layout for the liquefaction process of the LNG FPSO which satisfies all constraints related to limitations on the layout.

• Journal of Forest and Environmental Science
• /
• v.28 no.4
• /
• pp.247-253
• /
• 2012

The purpose of this study was to conduct phenology monitoring of forest plant species in Mt. JuWang National Park, thereby establish long-term prediction and management system for species susceptible to climate change, and utilize the result as basic materials necessary for conservation of plant genetic resources in accordance with changes in their growth environment. Global Positioning System coordinates were marked on each indicator species and a specific number ticket was provided to each plant. Changes in their blooming time, time of blossoms falling, time of leaves bursting into life, and time of leaves turning, and time of leaves falling were recorded. Investigation was made once per week from April 10 in 2010 to November 30 in 2011 except for the time period between July and August when investigation was made biweekly. The investigated plants concerned 12 kinds-nine species of trees and three kinds of herbs. According to the result of the penology monitoring of Mt. JuWang National Park, their time of leaves bursting into life, time of leaves turning, and time of leaves falling were largely earlier in 2011 than in 2010. However, it is hard to say that it is due to the factor of climate change. Long-term collection of climate data and continuous monitoring of plant phenology are considered necessary in order to examine correlation between climate change and seasonal change patterns of plants.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.2
• /
• pp.183-194
• /
• 2005

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the premise part of the rule-based structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. We distinguish between two types of the linear fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, the models are experimented with a representative numerical example. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when comparing with other neurofuzzy models.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.3
• /
• pp.341-349
• /
• 2019

Objective: Internal organs indirectly affect economic performance and well-being of animals. Study of internal organs during later layer period will allow full utilization of layer hens. Hence, we conducted a genome-wide association study (GWAS) to identify potential quantitative trait loci or genes that potentially contribute to internal organ weight. Methods: A total of 1,512 chickens originating from White Leghorn and Dongxiang Blue-Shelled chickens were genotyped using high-density Affymetrix 600 K single nucleotide polymorphism (SNP) array. We conducted a GWAS, linkage disequilibrium analysis, and heritability estimated based on SNP information by using GEMMA, Haploview and GCTA software. Results: Our results displayed that internal organ weights show moderate to high (0.283 to 0.640) heritability. Variance partitioned across chromosomes and chromosome lengths had a linear relationship for liver weight and gizzard weight ($R^2=0.493$, 0.753). A total of 23 highly significant SNPs that associated with all internal organ weights were mainly located on Gallus gallus autosome (GGA) 1 and GGA4. Six SNPs on GGA2 affected heart weight. After the final analysis, five top SNPs were in or near genes 5-Hydroxytryptamine receptor 2A, general transcription factor IIF polypeptide 2, WD repeat and FYVE domain containing 2, non-SMC condensin I complex subunit G, and sonic hedgehog, which were considered as candidate genes having a pervasive role in internal organ weights. Conclusion: Our findings provide an understanding of the underlying genetic architecture of internal organs and are beneficial in the selection of chickens.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.2
• /
• pp.66-75
• /
• 2010

This paper proposes an efficient method for design and implementation of the artificial intelligence (AI) of 'omok' game on the GPU. The proposed AI is designed on a cooperative structure using min-max game tree and genetic algorithm. Since the evaluation function needs intensive computation but is independently performed on a lot of candidates in the solution space, it is computed on the GPU in a massive parallel way. The implementation on NVIDIA CUDA and the experimental results show that it outperforms significantly over the CPU, in which parallel game tree and genetic algorithm on the GPU runs more than 400 times and 300 times faster than on the CPU. In the proposed cooperative AI, selective search using genetic algorithm is performed subsequently after the full search using game tree to search the solution space more efficiently as well as to avoid the thread overflow. Experimental results show that the proposed algorithm enhances the AI significantly and makes it run within the time limit given by the game's rule.

• Journal of the Society of Naval Architects of Korea
• /
• v.49 no.1
• /
• pp.33-44
• /
• 2012

In this study, the optimal operating conditions for the dual mixed refrigerant(DMR) cycle were determined by considering the power efficiency. The DMR cycle consists of compressors, heat exchangers, seawater coolers, valves, phase separators, tees, and common headers, and the operating conditions include the equipment's flow rate, pressure, temperature, and refrigerant composition per flow. First, a mathematical model of the DMR cycle was formulated in this study by referring to the results of a past study that formulated a mathematical model of the single mixed refrigerant(SMR) cycle, which consists of compressors, heat exchangers, seawater coolers, and valves, and by considering as well the tees, phase separators, and common headers. Finally, in this study, the optimal operating conditions from the formulated mathematical model was obtained using a hybrid optimization method that consists of the genetic algorithm(GA) and sequential quadratic programming(SQP). Moreover, the required power at the obtained conditions was decreased by 1.4% compared with the corresponding value from the past relevant study of Venkatarathnam.