• 한국전기전자재료학회논문지
• /
• 제15권1호
• /
• pp.7-14
• /
• 2002

In this paper, neutral networks are used to build models of oxide film etched In CHF$_3$/CF$_4$ with a magnetically enhanced reactive ion etcher(MERIE). A statistical 2$\^$4-1/ experimental design plus one center point was used to characterize relationships between process factors and etch responses. The factors that were varied include radio frequence(rf) power, pressure, CHF$_3$ and CF$_4$ flow rates. Resultant 9 experiments were used to train neural networks and trained networks were subsequently tested on its appropriateness using additionally conducted 8 experiments. A total of 17 experiments were thus conducted for this modeling. The etch responses modeled are dc bias voltage, etch rate and etch uniformity A qualitative, good agreement was obtained between predicted and observed behaviors.

• 전자통신동향분석
• /
• 제37권2호
• /
• pp.83-95
• /
• 2022

5G goes beyond people to serve indoor and outdoor companies and industries, as well as campuses such as halls, industrial complexes, educational institutions, stadiums, dense urban areas, rural areas, and government institutions. Therefore, a new approach to small cells is needed. Accordingly, 3GPP and Small Cell Forum are researching 5G small cell architecture; 3GPP, Small Cell Forum, and 5G Alliance for Connected Industries and Automation are also researching private networks tailored to meet the specific requirements of various companies and local governments. In particular, in the UK, a small cell-based technology is required for realizing the Joint Operator Technical Specifications-Neutral Host In-Building specification to cost-effectively secure indoor coverage. Further, the research on the SON(Self-Organizing Network) technology for small cells in 5G, where commercialization has begun, is required. The 5G-based small cell structure, private network, and Neutral Host In-Building and SON reviewed in this study are at the initial research stages; therefore, additional research is needed to secure the competitiveness of the small cell technology in 5G and Beyond 5G.

• 전기학회논문지
• /
• 제62권4호
• /
• pp.544-553
• /
• 2013

In this paper, we propose the pattern classifier of Radial Basis Function Neural Networks(RBFNNs) for diagnosis of 3-phase partial discharge. Conventional methods map the partial discharge/noise data on 3-PARD map, and decide whether the partial discharge occurs or not from 3-phase or neutral point. However, it is decided based on his own subjective knowledge of skilled experter. In order to solve these problems, the mapping of data as well as the classification of phases are considered by using the general 3-PARD map and PA method, and the identification of phases occurring partial discharge/noise discharge is done. In the sequel, the type of partial discharge occurring on arbitrary random phase is classified and identified by fuzzy clustering-based polynomial Radial Basis Function Neural Networks(RBFNN) classifier. And by identifying the learning rate, momentum coefficient, and fuzzification coefficient of FCM fuzzy clustering with the aid of PSO algorithm, the RBFNN classifier is optimized. The virtual simulated data and the experimental data acquired from practical field are used for performance estimation of 3-phase partial discharge pattern classifier.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.916-919
• /
• 2017

최근 딥러닝의 발달로 인해 Sentiment analysis분야에서도 다양한 기법들이 적용되고 있다. 이미지, 음성인식 분야에서 높은 성능을 보여주었던 Convolutional Neural Networks (CNN)은 최근 자연어처리 분야에서도 활발하게 연구가 진행되고 있으며 Sentiment analysis에도 효과적인 것으로 알려져 있다. 기존의 머신러닝에서는 lexicon을 이용한 기법들이 활발하게 연구되었지만 word embedding이 등장하면서 이러한 시도가 점차 줄어들게 되었다. 그러나 lexicon은 여전히 sentiment analysis에서 유용한 정보를 제공한다. 본 연구에서는 SemEval 2017 Task4에서 제공한 Twitter dataset과 다양한 lexicon corpus를 사용하여 lexicon을 CNN과 결합하였을 때 모델의 성능이 얼마큼 향상되는지에 대하여 연구하였다. 또한 word embedding과 lexicon이 미치는 영향에 대하여 분석하였다. 모델을 평가하는 metric은 positive, negative, neutral 3가지 class에 대한 macroaveraged F1 score를 사용하였다.

• EDISON SW 활용 경진대회 논문집
• /
• 제6회(2017년)
• /
• pp.39-45
• /
• 2017

We present a Brownian dynamics simulation study on the diffusion of a neutral tracer particle confined in a regularly crosslinked polymer network, especially, when the tracer size is comparable to the mesh size of the network. Polymer networks with different mesh sizes are prepared and compressed to the extent that the total polymer densities become the same. Irrespective of the network mesh size, the tracer diffusion in the networks is slowed down, showing the subdiffusion on intermediate time scales followed by the normal diffusion at long times. However, the confinement effect on the tracer diffusion becomes more significant when network strands are tightly stretched with smaller mesh size. The time scales of dynamic transitions are analyzed in terms of the probability distribution of time-correlated particle displacements.

• Journal of Power Electronics
• /
• 제19권3호
• /
• pp.702-713
• /
• 2019

Multilevel Inverters (MLIs) are widely used in medium voltage applications due to their various advantages. In addition, there are numerous types of MLIs for such applications. However, the diode-less 3-level (3L) T-type Neutral Point Clamped (NPC) MLI is the most advantageous due to its low conduction losses and high potential efficiency. The power circuit of a 3L T-type NPC is derived by the conventional two level inverter by a slight modification. In order to explore the MLI performance for various Pulse Width Modulation (PWM) schemes, this paper examines the operation of a 3L (five level line to line) T-type NPC MLI for various types of Multi-Carriers Pulse Width Modulation (MCPWM) schemes. These PWM schemes are compared in terms of their voltage profile, total harmonic distortion (THD) and conduction losses. In addition, a 3L T-type NPC MLI is also compared with the conventional NPC in terms of number of switches, clamping diodes, main diodes and capacitors. Moreover, the capacitor-balancing problem is also investigated using the Neutral Point Fluctuation (NPF) method with all of the MCPWM schemes. A 1kW 3L T-type NPC MLI is simulated in MATLAB/Simulink and implemented experimentally and its performance is tested with a 1HP induction motor. The results indicate that the 3L T-type NPC MLI has better performance than conventional NPC MLIs.

• 디지털융복합연구
• /
• 제9권4호
• /
• pp.91-101
• /
• 2011

본 연구는 인공지능 네트워크 시스템의 개발을 위해 존재하는 방법론들이 어떠한 것이 있는지를 연구하고자 한다. 인공지능 네트워크 개발에 대해 현재 발표된 것과 방법론을 명확히 하기위한 관점들을 측정하였으며 그것은 이러한 네트워크 개발에 이용되었다. 광범위한 이러한 방법론들을 어떻게 범주화하고, 만약 이런 방법론들이 인공지능 네트워크 개발에 대한 일반적, 근본적이고 포괄적인 방법론으로 증명할 수 있는지, 그리고 이런 방법론들이 기존 시스템 개발 방법론들과 어떻게 다른지 본 연구를 통해 시험했다.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2000년도 춘계학술발표논문집
• /
• pp.353-356
• /
• 2000

본 논문에서는 데이터 내의 비선형 속성을 보다 빠르고 정확하게 추출하기 위한 수정된 학습알고리즘의 비선형 주요 성분분석 신경망을 제안한다. 제안된 학습알고리즘은 신경망의 학습시에 과거의 속성을 반영하기 위한 모멘트 항이 추가된 학습기법이다. 이는 최적해로의 수렴에 따른 발전을 억제하여 그 수렴성능을 좀더 개선시키는 모멘텀의 장점을 그대로 살리기 위함이다. 제안된 학습알고리즘을 이용한 신경망을 128$\times$128 픽셀의 Lenna와 256$\times$128 픽셀의 차량 번호판 영상들을 대상으로 시뮬레이션 한 결과, 제안된 학습알고리즘이 기존의 비선형 주요성분 분석을 위한 신경망이나 선형속성을 가지는 역전파 알고리즘을 이용한 신경망보다 더욱 우수한 수렴 성능과 특징추출 성능이 있음을 확인하였다.

• 한국전자거래학회지
• /
• 제5권1호
• /
• pp.1-18
• /
• 2000

As the networks (i.e., intranet and internet) proliferate all over the world, it is inevitable to move some (or all) of the enterprise activities into virtual spaces. Differently from business data, product data have complex semantics and thus are not properly exchanged among different application programs. Even though some neutral formats of product data have been developed by standard organizations, translating them among various application programs still needs the comprehensive understanding of the complex semantics. Recently, it is widely recognized that capturing more knowledge is the next step In overcome the current difficulties on sharing product data. In this paper, we present Web-based knowledge management that facilitates seamless sharing of product data among various application programs in virtual enterprises. Three types of knowledge are managed by the knowledge management system - metadata, ontology, and mapping. In this environment, we consider both business applications (e.g., ERP, SCM, and EDI System) and engineering applications (e.g., CAD and CAM system).

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(2)
• /
• pp.309-312
• /
• 2001

A primitive gas classification system which can classify limited species of gas was designed and simulated. The 'electronic nose' consists of an array of 4 metal oxide gas sensors with different selectivity patterns, signal collecting unit and a signal pattern recognition and decision Part in PLD(programmable logic device) chip. Sensor array consists of four commercial, tin oxide based, semiconductor type gas sensors. BP(back propagation) neutral networks with MLP(Multilayer Perceptron) structure was designed and implemented on CPLD of fifty thousand gate level chip by VHDL language for processing the input signals from 4 gas sensors and qualification of gases in air. The network contained four input units, one hidden layer with 4 neurons and output with 4 regular neurons. The 'electronic nose' system was successfully classified 4 kinds of industrial gases in computer simulation.