• 한국정보시스템학회지:정보시스템연구
• /
• 제25권4호
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.

• 약학회지
• /
• 제27권1호
• /
• pp.11-19
• /
• 1983

Rifampicin-arginine complex was prepared to increase the solubility and dissolution rate of rifampicin. Solvation method was applied to make the complex and its formation was identified by the solubility method, powder x-ray diffractometry, differential thermal analysis and spectroscopic determination. The complex was formed in the molar ratio of 1 : 1 which was proved by the slope ratio method and continuous variation method. The complex was a non-crystalline form determined by the x-ray powder diffractometric analysis. The solubility of complex in water was significantly higher than that of rifampicin itself. The stability constant and thermodynamical properties of the complex were determined to investigate the solubilization phenomena. The thermodynamic data showed that the complexation between rifampicin and arginine was an exothermic and spontaneous reaction. Simulated absorption studies carried out through the artificial lipid barrier in artificial gastric and intestinal juices. The results showed that the complex had an enhanced absorption rate of rifampicin nearly twice compared with that of rifampicin itself.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.118-129
• /
• 2023

The expansion of smart cities drives the growth of data generated from sensor devices, benefitting citizens with enhanced governance, intelligent decision-making, optimized and sustainable management of available resources. The exposure of user data during its collection from sensors, storage in databases, and processing by artificial intelligence-based solutions presents significant security and privacy challenges. In this paper, we investigate the various threats and attacks affecting the growth of future smart cities and discuss the available countermeasures using artificial intelligence and blockchain-based solutions. Open challenges in existing literature due to the lack of countermeasures against quantum-inspired attacks are discussed, focusing on postquantum security solutions for resource-constrained sensor devices. Additionally, we discuss future research and challenges for the growing smart city environment and suggest possible solutions.

• 전자통신동향분석
• /
• 제37권6호
• /
• pp.32-42
• /
• 2022

Recently, decentralized approaches to artificial intelligence (AI) development, such as federated learning are drawing attention as AI development's cost and time inefficiency increase due to explosive data growth and rapid environmental changes. Collaborative AI technology that dynamically organizes collaborative groups between different agents to share data, knowledge, and experience and uses distributed resources to derive enhanced knowledge and analysis models through collaborative learning to solve given problems is an alternative to centralized AI. This article investigates and analyzes recent technologies and applications applicable to the research of multi-agent collaboration of AI bots, which can provide collaborative AI functionality autonomously.

• Structural Engineering and Mechanics
• /
• 제24권4호
• /
• pp.429-446
• /
• 2006

Experimental investigation was conducted to evaluate the seismic ductility of earthquake-experienced concrete columns with an aspect ratio of 2.5. Eight circular concrete columns with a diameter of 600 mm were constructed with three test parameters: confinement ratio, lap-splice of longitudinal bars, and retrofitting with Fiber Reinforced Polymer (FRP) materials. The objective of this research is to examine the seismic performance of RC bridge piers subjected to a Quasi static test (QST), which were preliminary tested under a series of artificial earthquake motions referred to as a Pseudo dynamic test (PDT). The seismic enhancement effect of FRP wrap was also investigated on these RC bridge piers. Six specimens were loaded to induce probable damage by four series of artificial earthquakes, which were developed to be compatible with earthquakes in the Korean peninsula by the Korea Highway Corporation (KHC). Directly after the PDT, six earthquake-experienced columns were subjected to inelastic cyclic loading under a constant axial load of $0.1{f_c}^{\prime}A_g$. Two other reference specimens without the PDT were also subjected to similar quasi-static loads. Test results showed that specimens pre-damaged by moderate artificial earthquakes generally demonstrated good residual seismic performance, which was similar to the corresponding reference specimen. Moreover, RC bridge specimens retrofitted with wrapping fiber composites in the potential plastic hinge region exhibited enhanced flexural ductility.

• 설비공학논문집
• /
• 제29권10호
• /
• pp.497-503
• /
• 2017

In recent years, studies on the prediction of building load using Artificial Neural Network (ANN) models have been actively conducted in the field of building energy In general, building loads predicted by ANN models show a sharp deviation unless large data sets are used for learning. On the other hands, some of the input data are hard to be acquired by common measuring devices. In this work, we estimate daily building loads with a limited number of input data and fewer pastdatasets (3 to 10 days). The proposed model with fewer input data gave satisfactory results as regards to the ASHRAE Guide Line showing 21% in CVRMSE and -3.23% in MBE. However, the level of accuracy cannot be enhanced since data used for learning are insufficient and the typical ANN models cannot account for thermal capacity effects of the building. An attempt proposed in this work is that learning procersses are sequenced frequrently and past data are accumulated for performance improvement. As a result, the model met the guidelines provided by ASHRAE, DOE, and IPMVP with by 17%, -1.4% in CVRMSE and MBE, respectively.

• Journal of the korean society of oceanography
• /
• 제36권3호
• /
• pp.72-82
• /
• 2001

The progress of giant dyke construction off the Mangyung and Donajin rivers, has yielded enormous impact on the estuarine environment, both hydrodynamically and sedimentologically. Especially the inter-dyke gap in the northern Saemankeum area, 4 km wide between Yamido and Piungdo, has acted as an artificial tidal inlet. Due to such a changed geometry, tidal regime has been reversed from being flood- to ebb-dominated with a directional change from NE-SW to E-W. As a result, a large tongue-like tidal sand bar (named Saemankeum Bar) has conspicuously grown seaward through the artificial tidal inlet. The Saemankeum Bar composed of well-sorted very fine sands (3.0-3.5${\phi}$) has grown at a rate of 1.63 km/yr for the past three yews (1996-1998). Such a rapid growth of the sand bar is attributed to enhanced sediment supply derived from the degradation of former tidal sand bars at the mouth of the Mangyung River. Eventually the reworking of the tidal sand bars also caused the pre-existing tidal channels to be wider, deeper and more straightened. All of these phenomena well examplify the critical effect of artificial modifications on the natural estuarine environments.

• Journal of Microbiology and Biotechnology
• /
• 제22권7호
• /
• pp.939-946
• /
• 2012

Antibiotic production with Streptomyces sindenensis MTCC 8122 was optimized under submerged fermentation conditions by artificial neural network (ANN) coupled with genetic algorithm (GA) and Nelder-Mead downhill simplex (NMDS). Feed forward back-propagation ANN was trained to establish the mathematical relationship among the medium components and length of incubation period for achieving maximum antibiotic yield. The optimization strategy involved growing the culture with varying concentrations of various medium components for different incubation periods. Under non-optimized condition, antibiotic production was found to be $95{\mu}g/ml$, which nearly doubled ($176{\mu}g/ml$) with the ANN-GA optimization. ANN-NMDS optimization was found to be more efficacious, and maximum antibiotic production ($197{\mu}g/ml$) was obtained by cultivating the cells with (g/l) fructose 2.7602, $MgSO_4$ 1.2369, $(NH_4)_2PO_4$ 0.2742, DL-threonine 3.069%, and soyabean meal 1.952%, for 9.8531 days of incubation, which was roughly 12% higher than the yield obtained by ANN coupled with GA under the same conditions.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.72-83
• /
• 2021

The use of the predictive analytics (PA) powered by the artificial intelligence (AI) is more important in the movie sector during the COVID-19 pandemic, because Hollywood witnessed the impact of the 'Netflix Effect' and began to invest in data and AI. Our purpose is to discover a few cases of the AI centered PA in the movie industry value chain based on five objectives of PA: Compete, grow, enforce, improve, and satisfy. Even if movie companies' interest is to predict future success for competing with over-the-tops (OTTs) at a first glance, it is observed, once they start to use the PA with the AI, they try to utilize the enhanced PA platforms for remaining four objectives. As a result, ScriptBook, Vault, Pilot, Cinelytic and Merlin Video (Merlin) are use cases for the objective 'compete.' Movio of Vista Group International and Datorama of Salesforce are use cases for the objective 'grow.' Industrial Light & Magic (ILM) and Geena Davis Institute on Gender in Media (GDI) with Disney are use cases for the objective 'enforce.' Watson, Benjamin, and Greenlight Essential are use cases for the objective 'improve.' Disney Research (DR) with Simon Fraser University and California Institute of Technology is the use case for the objective 'satisfy.'

• 한국안전학회지
• /
• 제37권1호
• /
• pp.41-48
• /
• 2022

Bridge engineering documents have essential contents that must be referenced continuously throughout a structure's entire life cycle, but research related to the quality of the contents is still lacking. XML schema matching is an excellent technique to improve the quality of stored data; however, it takes excessive computing time when applied to documents with many contents and a deep hierarchical structure, such as bridge engineering documents. Moreover, it requires a manual parametric study for matching elements' weight factors, maintaining a high matching accuracy. This study proposes an efficient weight-factor determination method based on an artificial neural network (ANN) model using the simplified XML schema-matching method proposed in a previous research to reduce the computing time. The ANN model was generated and verified using 580 data of document properties, weight factors, and matching accuracy. The proposed ANN-based schema-matching method showed superiority in terms of accuracy and efficiency compared with the previous study on XML schema matching for bridge engineering documents.