• 한국지능시스템학회논문지
• /
• 제14권1호
• /
• pp.52-56
• /
• 2004

주식시장에서 KOSPI200지수의 상승 또는 하락으로 분류 및 예측하는 정보는 선물 및 옵션시장에서 포토폴리오를 설계할 때 의사결정을 위해 중요한 기준이 된다. 경제지표인 시계열 패턴들의 향후 추세는 가장 최근의 경제패턴에 매우 종속적이기 때문에 최근의 패턴들을 가장 우선적으로 학습해야 할 필요가 있다. 본 논문에서는 시계열분석, 신경회로망, 그리고 다양한 분야에서 각광을 받고 있는 SVM(Support Vector Machine)과 Fuzzy SVM 모형의 분류 및 예측성능을 비교하였다. 특히 학습 DB에 따라 시계열성 속성을 갖는 퍼지소속함수에 가장 적합한 차원을 제시함으로서 Fuzzy SVM이 우수함을 입증하였다.

• 대한산업공학회지
• /
• 제40권1호
• /
• pp.8-17
• /
• 2014

In this research, we employed various data mining techniques to build predictive models for win-loss prediction in Korean professional baseball games. The historical data containing information about players and teams was obtained from the official materials that are provided by the KBO website. Using the collected raw data, we additionally prepared two more types of dataset, which are in ratio and binary format respectively. Dividing away-team's records by the records of the corresponding home-team generated the ratio dataset, while the binary dataset was obtained by comparing the record values. We applied seven classification techniques to three (raw, ratio, and binary) datasets. The employed data mining techniques are decision tree, random forest, logistic regression, neural network, support vector machine, linear discriminant analysis, and quadratic discriminant analysis. Among 21(= 3 datasets${\times}$7 techniques) prediction scenarios, the most accurate model was obtained from the random forest technique based on the binary dataset, which prediction accuracy was 84.14%. It was also observed that using the ratio and the binary dataset helped to build better prediction models than using the raw data. From the capability of variable selection in decision tree, random forest, and stepwise logistic regression, we found that annual salary, earned run, strikeout, pitcher's winning percentage, and four balls are important winning factors of a game. This research is distinct from existing studies in that we used three different types of data and various data mining techniques for win-loss prediction in Korean professional baseball games.

• 한국정보전자통신기술학회논문지
• /
• 제13권4호
• /
• pp.283-292
• /
• 2020

4차 산업혁명의 대표적인 이미지 중 하나인 인공지능은 2016년 알파고 이후에 인공지능 인식이 매우 높아져 있다. 본 논문은 학국교육학술정보원에서 제공하는 국내 논문 중 '인공지능', '기계학습', '딥 러닝'으로 검색된 국내 발표 논문에 대해서 분석하였다. 검색된 논문은 약 1만여건이며 논문 동향을 파악하기 위해 빈도분석과 토픽 모델링, 의미 연결망을 이용하였다. 추출된 논문을 분석한 결과, 2015년에 비해 2016년에는 인공지능 분야는 600%, 기계학습은 176%, 딥 러닝 분야는 316% 증가하여 알파고 이후에 인공지능 분야의 연구가 활발히 진행됨을 확인할 수 있었다. 또한, 2018년 부터는 기계학습보다 딥 러닝 분야가 더 많이 연구 발표되고 있다. 기계학습에서는 서포트 벡터 머신 모델이, 딥 러닝에서는 텐서플로우를 이용한 컨볼루션 신경망이 많이 활용되고 있음을 알 수 있었다. 본 논문은 '인공지능', '기계학습', '딥 러닝' 분야의 향후 연구 방향을 설정하는 도움을 제공할 수 있다.

• The Korean Journal of Physiology and Pharmacology
• /
• 제16권6호
• /
• pp.387-392
• /
• 2012

In this study, we examined the antinociceptive effect of Cyperi rhizoma (CR) and Corydalis tuber (CT) extracts using a chronic constriction injury-induced neuropathic pain rat model. After the ligation of sciatic nerve, neuropathic pain behavior such as mechanical allodynia and thermal hyperalgesia were rapidly induced and maintained for 1 month. Repeated treatment of CR or CT (per oral, 10 or 30 mg/kg, twice a day) was performed either in induction (day 0~5) or maintenance (day 14~19) period of neuropathic pain state. Treatment of CR or CT at doses of 30 mg/kg in the induction and maintenance periods significantly decreased the nerve injury-induced mechanical allodynia. In addition, CR and CT at doses of 10 or 30 mg/kg alleviated thermal heat hyperalgesia when they were treated in the maintenance period. Finally, CR or CT (30 mg/kg) treated during the induction period remarkably reduced the nerve injury-induced phosphorylation of NMDA receptor NR1 subunit (pNR1) in the spinal dorsal horn. Results of this study suggest that extracts from CR and CT may be useful to alleviate neuropathic pain.

• 조명전기설비학회논문지
• /
• 제23권12호
• /
• pp.154-161
• /
• 2009

연료전지 발전 시스템은 비선형성을 내포한 다수의 제어 루로들로 구성된 매우 복잡한 형태의 시스템이다. 연료전지 발전 시스템의 제어를 위하여 연료전지의 스텍 모델이 개발되고 있으며 연료전지 발전 시스템의 간략화된 프로세스 흐름도도 제시되고 있다. 본 연구에서는 이러한 모델을 사용하여 연료전지 발전 시스템을 지능적으로 제어할 수 있는 I-SRG(Intelligent Setpoint Reference Governor)를 개발한다. I-SRG는 시스템의 제약조건과 성능목표에 대한 최적의 운전 설정치를 산출하고 각 제어 루프의 앞먹임 제어입력을 생성한다. I-SRG는 PSO(Particle Swarm Optimization) 알고리즘을 최적화 기법에 사용하고 신경회로망으로 구현되어진다. MCFC 발전 시스템의 전력 프로파일에 대한 추종 제어의 모의실험을 수행하여 제안된 I-SRG의 유용성을 보인다.

• Journal of Power Electronics
• /
• 제18권1호
• /
• pp.70-80
• /
• 2018

A novel strategy based on a zero common mode voltage pulse-width modulation (ZCMV-PWM) technique and zero-sequence circulating current (ZSCC) feedback control is proposed in this study to eliminate ZSCCs between three-level neutral point clamped (NPC) voltage source inverters, with common AC and DC buses, that are operating in parallel. First, an equivalent model of ZSCC in a three-phase three-level NPC inverter paralleled system is developed. Second, on the basis of the analysis of the excitation source of ZSCCs, i.e., the difference in common mode voltages (CMVs) between paralleled inverters, the ZCMV-PWM method is presented to reduce CMVs, and a simple electric circuit is adopted to control ZSCCs and neutral point potential. Finally, simulation and experiment are conducted to illustrate effectiveness of the proposed strategy. Results show that ZSCCs between paralleled inverters can be eliminated effectively under steady and dynamic states. Moreover, the proposed strategy exhibits the advantage of not requiring carrier synchronization. It can be utilized in inverters with different types of filter.

• Nuclear Engineering and Technology
• /
• 제39권3호
• /
• pp.193-206
• /
• 2007

The Korea Atomic Energy Research Institute has developed an advanced fast reactor concept, KALIMER-600, which satisfies the Generation IV reactor design goals of sustainability, economics, safety, and proliferation resistance. The concept enables an efficient utilization of uranium resources and a reduction of the radioactive waste. The core design has been developed with a strong emphasis on proliferation resistance by adopting a single enrichment fuel without blanket assemblies. In addition, a passive residual heat removal system, shortened intermediate heat-transport system piping and seismic isolation have been realized in the reactor system design as enhancements to its safety and economics. The inherent safety characteristics of the KALIMER-600 design have been confirmed by a safety analysis of its bounding events. Research on important thermal-hydraulic phenomena and sensing technologies were performed to support the design study. The integrity of the reactor head against creep fatigue was confirmed using a CFD method, and a model for density-wave instability in a helical-coiled steam generator was developed. Gas entrainment on an agitating pool surface was investigated and an experimental correlation on a critical entrainment condition was obtained. An experimental study on sodium-water reactions was also performed to validate the developed SELPSTA code, which predicts the data accurately. An acoustic leak detection method utilizing a neural network and signal processing units were developed and applied successfully for the detection of a signal up to a noise level of -20 dB. Waveguide sensor visualization technology is being developed to inspect the reactor internals and fuel subassemblies. These research and developmental efforts contribute significantly to enhance the safety, economics, and efficiency of the KALIMER-600 design concept.

• Parasites, Hosts and Diseases
• /
• 제58권4호
• /
• pp.461-466
• /
• 2020

Toxoplasma gondii is an obligate intracellular protozoan parasite that can invade various organs in the host body, including the central nervous system. Chronic intracranial T. gondii is known to be associated with neuroprotection against neurodegenerative diseases through interaction with host brain cells in various ways. The present study investigated the neuroprotective effects of chronic T. gondii infection in mice with cerebral ischemia experimentally produced by middle cerebral artery occlusion (MCAO) surgery. The neurobehavioral effects of cerebral ischemia were assessed by measurement of Garcia score and Rotarod behavior tests. The volume of brain ischemia was measured by triphenyltetrazolium chloride staining. The expression levels of related genes and proteins were determined. After cerebral ischemia, corrected infarction volume was significantly reduced in T. gondii infected mice, and their neurobehavioral function was significantly better than that of the uninfection control group. Chronic T. gondii infection induced the expression of hypoxia-inducible factor 1-alpha (HIF-1α) in the brain before MCAO. T. gondii infection also increased the expression of vascular endothelial growth factor after the cerebral ischemia. It is suggested that chronic intracerebral infection of T. gondii may be a potential preconditioning strategy to reduce neural deficits associated with cerebral ischemia and induce brain ischemic tolerance through the regulation of HIF-1α expression.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.754-758
• /
• 2005

Optimization of process variables such as arc current, welding voltage and welding speed in terms of the weld characteristics desired is the key step in achieving high quality and improving performance characteristics without increasing the cost. Consequently, incorrect settings of those process variables give rise to deviations in the welding characteristics from the desired bead geometry. Therefore, trainee welders are referred to the tabulated information relating different metal types and thickness as to recommend the desired values of process variables. Basically, the bead geometry plays an important role in determining the mechanical properties of the weld. So that it is very important to select the process variables for obtaining optimal bead geometry. However, it is difficult for the traditional identification methods to provide an accurate model because the optimized welding process is non-linear and time-dependent. In this paper, the possibilities of the Infra-red sensor in sensing and control of the bead geometry in the automated welding process are presented. Infra-red sensor is a well-known method to deal with the problems with a high degree of fuzziness so that the sensor is employed to build the relationship between process variables and the quality characteristic the proposed above respectively. Based on several neural networks, the mathematical models are derived from extensive experiments with different welding parameters and complex geometrical features. The developed system enables to select the optimal welding parameters and control the desired weld dimensions during arc welding process.

• Molecules and Cells
• /
• 제40권2호
• /
• pp.151-161
• /
• 2017

Proper synaptic function in neural circuits requires precise pairings between correct pre- and post-synaptic partners. Errors in this process may underlie development of neuropsychiatric disorders, such as autism spectrum disorder (ASD). Development of ASD can be influenced by genetic factors, including copy number variations (CNVs). In this study, we focused on a CNV occurring at the 16p11.2 locus in the human genome and investigated potential defects in synaptic connectivity caused by reduced activities of genes located in this region at Drosophila larval neuromuscular junctions, a well-established model synapse with stereotypic synaptic structures. A mutation of rolled, a Drosophila homolog of human mitogen-activated protein kinase 3 (MAPK3) at the 16p11.2 locus, caused ectopic innervation of axonal branches and their abnormal defasciculation. The specificity of these phenotypes was confirmed by expression of wild-type rolled in the mutant background. Albeit to a lesser extent, we also observed ectopic innervation patterns in mutants defective in Cdk2, Gq, and Gp93, all of which were expected to interact with Rolled MAPK3. A further genetic analysis in double heterozygous combinations revealed a synergistic interaction between rolled and Gp93. In addition, results from RT-qPCR analyses indicated consistently reduced rolled mRNA levels in Cdk2, Gq, and Gp93 mutants. Taken together, these data suggest a central role of MAPK3 in regulating the precise targeting of presynaptic axons to proper postsynaptic targets, a critical step that may be altered significantly in ASD.