• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.629-632
• /
• 2021

기계 번역(machine translation)은 자연 언어로 된 텍스트를 다른 언어로 자동 번역 하는 기술로, 최근에는 주로 신경망 기계 번역(Neural Machine Translation) 모델에 대한 연구가 진행되었다. 신경망 기계 번역은 일반적으로 자기회귀(autoregressive) 모델을 이용하며 기계 번역에서 좋은 성능을 보이지만, 병렬화할 수 없어 디코딩 속도가 느린 문제가 있다. 비자기회귀(non-autoregressive) 모델은 단어를 독립적으로 생성하며 병렬 계산이 가능해 자기회귀 모델에 비해 디코딩 속도가 상당히 빠른 장점이 있지만, 멀티모달리티(multimodality) 문제가 발생할 수 있다. 본 논문에서는 단어 정렬(word alignment)을 이용한 비자기회귀 신경망 기계 번역 모델을 제안하고, 제안한 모델을 한국어-영어 기계 번역에 적용하여 단어 정렬 정보가 어순이 다른 언어 간의 번역 성능 개선과 멀티모달리티 문제를 완화하는 데 도움이 됨을 보인다.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.297-309
• /
• 2024

This paper evaluates the performance of the neural network autoregressive model combined with an exponential smoothing model, called the NNARX+ETS model. The combined model utilizes the components of ETS as exogenous variables for NNARX, to forecast time series data using artificial neural networks. The main idea is to enhance the performance of NNAR using only lags of the original time series data, by combining traditional time series analysis methods with the neural networks through NNARX. We employ two real data for performance evaluation and compare the NNARX+ETS with NNAR and traditional time series analysis methods such as ETS and ARIMA (autoregressive integrated moving average) models.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3
• /
• pp.62-67
• /
• 1999

In this paper, we investigates a reliable model of the Predictive Recurrent Neural Network for the speech recognition. Predictive Neural Networks are modeled by syllable units. For the given input syllable, then a model which gives the minimum prediction error is taken as the recognition result. The Predictive Neural Network which has the structure of recurrent network was composed to give the dynamic feature of the speech pattern into the network. We have compared with the recognition ability of the Recurrent Network proposed by Elman and Jordan. ETRI's SAMDORI has been used for the speech DB. In order to find a reliable model of neural networks, the changes of two recognition rates were compared one another in conditions of: (1) changing prediction order and the number of hidden units: and (2) accumulating previous values with self-loop coefficient in its context. The result shows that the optimum prediction order, the number of hidden units, and self-loop coefficient have differently responded according to the structure of neural network used. However, in general, the Jordan's recurrent network shows relatively higher recognition rate than Elman's. The effects of recognition rate on the self-loop coefficient were variable according to the structures of neural network and their values.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.1516-1519
• /
• 2011

예측에 필요한 중요한 자료에는 비선형 자료와 시계열과 같은 선형 자료 등이 있다. 이들 자료는 그 함축적인 관계가 매우 복잡하여 전통적인 통계분석 도구로 식별하는데 어려움이 많다. 신경망 분석은 비모수적 문제나 비선형 곡선 적합능력의 우수성 때문에 현실세계에서의 고유한 복잡성을 다루는 많은 경제 응용 분야에서 널리 이용되고 있다. 신경망은 또한 경제 시계열자료의 예측분야에서도 여러 연구에서 훌륭한 도구로서 적용되고 있다. 전통적으로 우리나라에서 시계열자료의 예측은 선형 자료적 분석을 중심으로 하는 분석도구인 자기회귀누적이동평균(ARIMA)모형을 이용한 시계열분석이 일반적이다. 이 연구에서는 신경망과 ARIMA 모형을 이용하여 한국의 주가변동 자료 및 자동차등록 현황 자료등과 같은 시계열자료를 이용한 예측결과를 비교한다. 연구의 결과는 신경망을 이용한 예측 방법들이 ARIMA 예측 결과보다 통계적으로 작은 오차를 주는 보다 효율적인 방법임을 보여주고 있다.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.335-351
• /
• 2011

In order to resolve data scarcity problem related to crisis, Oh and Kim (2007) proposed to use stability oriented approach which focuses a base period of financial market, fits asymptotic stationary autoregressive model to the base period and then compares the fitted model with the current market situation. Based on such approach, they developed financial market instability index. However, since neural network, their major tool, depends on the base period too heavily, their instability index tends to suffer from inaccuracy. In this study, we consider linear asymptotic stationary autoregressive model and neural network to fit the base period and produce two instability indexes independently. Then the two indexes are combined into one integrated instability index via newly proposed combining method. It turns out that the combined instability performs reliably well.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.29 no.4
• /
• pp.180-188
• /
• 2017

Recently, as the strength of winds and waves increases due to the climate change, abnormal waves such as swells have been also increased, which results in the increase of downtime events of loading/unloading in a harbour. To reduce the downtime events, breakwaters were constructed in a harbour to improve the tranquility. However, it is also important and useful for efficient port operation by predicting accurately and also quickly the downtime events when the harbour operation is in a limiting condition. In this study, numerical simulations were carried out to calculate the wave conditions based on the forecasted wind data in offshore area/outside harbour and also the long-term observation was carried out to obtain the wave data in a harbour. A forecasting method was designed using an auto-regressive (AR) and artificial neural networks (ANN) models in order to establish the relationship between the wave conditions calculated by wave model (SWAN) in offshore area and observed ones in a harbour. To evaluate the applicability of the proposed method, this method was applied to predict wave heights in a harbour and to forecast the downtime events in Pohang New Harbour with highly complex topography were compared. From the verification study, it was observed that the ANN model was more accurate than the AR model.

• The Journal of Korean Association of Computer Education
• /
• v.16 no.2
• /
• pp.39-48
• /
• 2013

This study investigates the predictive model of the adolescents' computer entertainment behavior using neural network with the KYPS data (3449 in the junior high school; 1725 boys and 1724 girls). This study compares the results of neural network(model 1) to the logistic regression model and neural network(model 2) with the exact same variables used in logistic regression. The results reveal that the prediction of neural network model 1 is the highest among three models and with gender, computer use time, family income, the number of close friends, the number of misdeed friends, individual study time, self-control, private education time, leisure time, self-belief, stress, adaptation to school, and study related worries, the neural network model 1 predicts the computer entertainment behavior more efficiently. These results suggest that the neural network could be used for diagnosing and adjusting the adolescents' computer entertainment behavior.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.303-314
• /
• 2020

The hydrological characteristics of watersheds and hydraulic systems of urban and river floods are highly nonlinear and contain uncertain variables. Therefore, the predicted time series of rainfall-runoff data in flood analysis is not suitable for existing neural networks. To overcome the challenge of prediction, a NARX (Nonlinear Autoregressive Exogenous Model), which is a kind of recurrent dynamic neural network that maximizes the learning ability of a neural network, was applied to forecast a flood in real-time. At the same time, NARX has the characteristics of a time-delay neural network. In this study, a hydrological model was constructed for the Taehwa river basin, and the NARX time-delay parameter was adjusted 10 to 120 minutes. As a result, we found that precise prediction is possible as the time-delay parameter was increased by confirming that the NSE increased from 0.530 to 0.988 and the RMSE decreased from 379.9 ㎥/s to 16.1 ㎥/s. The machine learning technique with NARX will contribute to the accurate prediction of flow rate with an unexpected extreme flood condition.

• Journal of Digital Convergence
• /
• v.10 no.9
• /
• pp.357-362
• /
• 2012

We have compared and predicted for non-linear time series data which are real data having different variences using GRCA(1) model and neural network method. In particular, using Korea Composite Stock Price Index rate, mean square errors of prediction are obtained in genaralized random coefficient autoregressive model and neural network method. Neural network method prove to be better in short-term forecasting, however GRCA(1) model perform well in long-term forecasting.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1085-1092
• /
• 2009

The ozone data is one of the important environmental data for measurement of the atmospheric condition of the country. In this article, the Autoregressive Error (ARE) model and Neural Networks (NN) model have been considered for analyzing the ozone data at the northern part of the Gyeonggi-Do, Paju monitoring site in Korea. In the both ARE model and NN model, seven meteorological variables and four pollution variables are used as the explanatory variables for the ozone data set. The seven meteorological variables are daily maximum temperature, wind speed, relative humidity, rainfall, dew point temperature, steam pressure, and amount of cloud. The four air pollution explanatory variables are Sulfur dioxide ($SO_2$), Nitrogen dioxide ($NO_2$), Cobalt (CO), and Promethium 10 (PM10). The result showed that the NN model is generally better suited for describing the ozone concentration than the ARE model. However, the ARE model will be expected also good when we add the explanatory variables in the model.