• 디지털융복합연구
• /
• 제11권6호
• /
• pp.199-204
• /
• 2013

음성 인식 시스템은 정확하지 않게 입력된 음성으로부터 학습 모델을 구성하고 유사한 음소 모델로 인식하기 때문에 인식률 저하를 가져온다. 따라서 본 논문에서는 바타차랴 알고리즘을 이용한 음성 인식 최적 학습 모델 구성 방법을 제안하였다. 음소가 갖는 특징을 기반으로 학습 데이터의 음소에 HMM 특징 추출 방법을 이용하였으며 유사한 학습 모델은 바타챠랴 알고리즘을 이용하여 정확한 학습 모델로 인식할 수 있도록 하였다. 바타챠랴 알고리즘을 이용하여 최적의 학습 모델을 구성하여 인식 성능을 평가하였다. 본 논문에서 제안한 시스템을 적용한 결과 음성 인식률에서 98.7%의 인식률을 나타내었다.

• 대한안전경영과학회지
• /
• 제17권4호
• /
• pp.335-342
• /
• 2015

The increasing interests on patents have led many individuals and companies to apply for many patents in various areas. Applied patents are stored in the forms of electronic documents. The search and categorization for these documents are issues of major fields in data mining. Especially, the keyword extraction by which we retrieve the representative keywords is important. Most of techniques for it is based on vector space model. But this model is simply based on frequency of terms in documents, gives them weights based on their frequency and selects the keywords according to the order of weights. However, this model has the limit that it cannot reflect the relations between keywords. This paper proposes the advanced way to extract the more representative keywords by overcoming this limit. In this way, the proposed model firstly prepares the candidate set using the vector model, then makes the graph which represents the relation in the pair of candidate keywords in the set and selects the keywords based on this relationship graph.

• 공업화학
• /
• 제30권3호
• /
• pp.337-344
• /
• 2019

본 연구에서는 금은화와 회화나무꽃으로부터 항산화성분을 추출하는 용매추출공정의 최적화를 위해 반응표면분석법 중 중심합성계획모델을 이용하였다. 반응표면분석법의 반응치로는 추출수율과 DPPH 라디칼소거활성을 설정하였고, 독립변수로는 추출시간, 주정/초순수 부피비, 추출온도 등을 설정하였다. 중심합성계획모델로 최적화과정을 수행한 결과 금은화의 경우 최적조건은 추출시간(2.08 h), 주정/초순수의 부피비(41.53 vol.%), 추출온도($55.08^{\circ}C$)이었으며, 이 때 수율(37.38 wt.%), DPPH 라디칼소거활성(40.37%) 값을 나타내었다. 또한 회화나무꽃의 경우 추출시간(2.13 h), 주정/초순수의 부피비(62.89 vol.%), 추출온도($50.42^{\circ}C$)에서 개별 최대값인 수율(35.43 wt.%), DPPH 라디칼소거활성(55.27%) 값을 나타내었다.

• 한국환경과학회지
• /
• 제9권2호
• /
• pp.159-164
• /
• 2000

For the purpose of development of a liquid membrane permeator which separates metal ions from aqueous solutions continuously and effectively, a continuous membrane permeator with the membrane solution trapped between extraction and stripping phases by two micro-porous hydrophilic films was manufactured. Experimental researches on the separation of zinc ion from aqueous solutions were performed in the liquid membrane permeator with 30 vol % D2EHPA solution in kerosine as liquid membrane. As results, the liquid membrane permeator separates zinc ion from aqueous solutions continuously and effectively in the wide range of operating conditions. A simple mass transfer rate model using equilibrium constant of the extraction reaction for the system used were proposed, and the model was compared with experimental results of separation of zinc ion in the permeator. And the effects of operating factors, such as space time, pH of extraction solution, extraction temperature, on the separation rate of zinc ion in the permeator were experimentally examined.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 II
• /
• pp.763-766
• /
• 2003

A direct parameter extraction method using several two-port parameter equations derived in cutoff and active bias modes has been studied to obtain an accurate Gummel-Poon BJT model. First, dc model parameters were extracted from slopes and y-axis intercepts of I-V curve and Gummel plot. The pad capacitances and junction capacitance parameters were determined by using measured S-parameter sets in the cutoff bias. The resistance and transit time parameters were extracted by using measured S-parameter sets in the active bias.

• 공업화학
• /
• 제29권5호
• /
• pp.565-570
• /
• 2018

본 연구에서는 초음파 용매추출공정을 이용하여 닥나무로부터 항산화성분을 추출하고, 중심합성계획모델을 이용하여 추출공정을 최적화하였다. 중심합성계획모델의 반응치로는 추출수율과 DPPH 라디칼소거활성을 설정하고, 독립변수인 추출시간, 주정/초순수 부피비, 초음파 조사세기에 따른 주효과도와 교호효과도를 해석하였다. 추출수율과 DPPH 라디칼소거활성 모두 계량인자의 주효과도와 교호효과도를 모두 고려하였을 때 가장 큰 영향을 미치는 인자는 주정/초순수 부피비이었다. 반응표면분석법을 이용하여 추출공정의 최적화과정을 수행한 결과 최적추출조건은 추출시간(19.92 min), 주정/초순수 부피비(54.23 vol%), 초음파 조사세기(557.65 W)로 나타났다. 이 조건으로부터 예상되는 반응치의 값은 추출수율(38.93 wt%), DPPH 라디칼소거활성(55.33%)으로 나타났다.

• 한국항해항만학회지
• /
• 제36권9호
• /
• pp.741-751
• /
• 2012

This article analyzes the interdependency between nonrenewable marine sand resources and renewable fishery resources by the developed dynamic bioeconomic model. The developed bioeconomic model is applied to a case study of efficient sustainable management for marine sand mining, which adversely affects a valuable blue crab fishery and its habitat in Korea. The socially-efficient extraction plan for marine sand and the time-variant environmental external costs to society in terms of diminished harvest rate of blue crab are determined. To take into account long-term effects from destroyed fishery habitat, a Beverton-Holt age structure model is integrated into the bioeconomic model. The illustrative results reveal that the efficient sand extraction plan is dynamically constrained by the stock size of the blue crab fishery over time. Thus, the dynamic environmental external cost is more realistic resource policy option than the classical fixed external cost for determining socially optimal extraction plans. Additionally, the economic value of bottom habitat, which supports the on- and off-site commercial blue crab fishery is estimated. The empirical results are interpreted with emphasis on guidelines for management policy for marine sand mining.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• Nuclear Engineering and Technology
• /
• 제53권10호
• /
• pp.3229-3235
• /
• 2021

The key process used in nuclear industries for the management of radiotoxicity associated with spent fuel in a closed fuel cycle is solvent extraction. An understanding of hydrodynamics and mass transfer is of primary importance for the design of mass transfer equipment used in solvent extraction processes. Understanding the interfacial phenomenon and the associated hydrodynamics of the liquid drops is essential for model-based design of mass transfer devices. In this work, the phenomenon of drop formation at the tip of a nozzle submerged in quiescent immiscible liquid phase is revisited. Previously reported force balance based models and empirical correlations are analyzed. Experiments are carried out to capture the process of drop formation using high-speed imaging technique. The images are digitally processed to measure the average drop diameter. A correlation based on the force balance model is proposed to estimate drop diameter and jet length. The average drop diameter obtained from the proposed model is in good agreement with experimental data with an average error of 6.3%. The developed model is applicable in both the necking as well as jetting regime and is validated for liquid-liquid systems having low, moderate and high interfacial tension.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.147-149
• /
• 2004

There are no authentic solutions in a face region extraction problem though it is an important part of pattern recognition and has diverse application fields. It is not easy to develop the facial region extraction algorithm because the facial image is very sensitive according to age, sex, and illumination. In this paper, to solve these difficulties, a fuzzy color filer based on the facial region extraction algorithm is proposed. The fuzzy color filter makes the robust facial region extraction enable by modeling the skin color. Especially, it is robust in facial region extraction with various illuminations. In addition, to identify the fuzzy color filter, a linear matrix inequality(LMI) optimization method is used. Finally, the simulation result is given to confirm the superiority of the proposed algorithm.