• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.340-340
• /
• 2019

지구온난화로 유발되는 기후변동성이 증가함에 따라서 정확한 수문인자의 예측은 전 세계적으로 주요 관심사항이 되고 있다. 최근에는 고성능 컴퓨터 자원의 증가로 수문기상학 연구에서 동일한 학습량에 비하여 정확도의 향상이 뚜렷한 기계학습 구조를 활용하여 위성영상 기반의 대기예측, 태풍위치 추적 및 강수량 예측 등의 연구가 활발하게 진행되고 있다. 본 연구에는 기계학습 중 시계열 분석에 널리 활용되고 있는 순환신경망(Recurrent Neural Network, RNN) 기법의 대표적인 LSTM(Long Short-Term Memory) 네트워크를 이용하여 수문인자를 예측하였다. LSTM 네트워크는 가중치 및 메모리 요소에 대한 추가정보를 셀 상태에 저장하고 시계열의 길이 조정하여 모형의 탄력적 활용이 가능하다. LSTM 네트워크를 이용한 다양한 수문인자 예측결과 RMSE의 개선을 확인하였다. 따라서 본 연구를 통하여 개발된 기계학습을 통한 수문인자 예측기술은 권역별 수계별 홍수 및 가뭄대응 계획을 능동적으로 수립하는데 활용될 것으로 판단된다. 향후 연구에서는 LSTM의 입력영역을 Bayesian 추론기법을 활용하여 구성함으로 학습과정의 불확실성을 정량적으로 제어하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.592-601
• /
• 2016

The recurrent neural network (RNN) is a deep learning model which is suitable to sequential or length-variable data. The Long Short-Term Memory (LSTM) mitigates the vanishing gradient problem of RNNs so that LSTM can maintain the long-term dependency among the constituents of the given input sequence. In this paper, we propose a LSTM based language model which can predict following words of a given incomplete sentence to generate a complete sentence. To evaluate our method, we trained our model using multiple Korean corpora then generated the incomplete part of Korean sentences. The result shows that our language model was able to generate the fluent Korean sentences. We also show that the word based model generated better sentences compared to the other settings.

• Journal of Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.73-82
• /
• 2019

Recently, as the occurrence frequency of sudden floods due to climate change increased, the flood damage on riverside social infrastructures was extended so that there has been a threat of overflow. Therefore, a rapid prediction of potential flooding in riverside social infrastructure is necessary for administrators. However, most current flood forecasting models including hydraulic model have limitations which are the high accuracy of numerical results but longer simulation time. To alleviate such limitation, data driven models using artificial neural network have been widely used. However, there is a limitation that the existing models can not consider the time-series parameters. In this study the water surface elevation of the Hangang River bridge was predicted using the NARX model considering the time-series parameter. And the results of the ANN and RNN models are compared with the NARX model to determine the suitability of NARX model. Using the 10-year hydrological data from 2009 to 2018, 70% of the hydrological data were used for learning and 15% was used for testing and evaluation respectively. As a result of predicting the water surface elevation after 3 hours from the Hangang River bridge in 2018, the ANN, RNN and NARX models for RMSE were 0.20 m, 0.11 m, and 0.09 m, respectively, and 0.12 m, 0.06 m, and 0.05 m for MAE, and 1.56 m, 0.55 m and 0.10 m for peak errors respectively. By analyzing the error of the prediction results considering the time-series parameters, the NARX model is most suitable for predicting water surface elevation. This is because the NARX model can learn the trend of the time series data and also can derive the accurate prediction value even in the high water surface elevation prediction by using the hyperbolic tangent and Rectified Linear Unit function as an activation function. However, the NARX model has a limit to generate a vanishing gradient as the sequence length becomes longer. In the future, the accuracy of the water surface elevation prediction will be examined by using the LSTM model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.121-121
• /
• 2019

특정 지역에 집중적으로 비가 내리는 현상인 국지성호우가 빈번히 발생함에 따라 하천 주변 사회기반시설의 침수 위험성이 증가하고 있다. 침수 위험성 판단 여부는 주로 수위정보를 이용하며 수위 예측은 대부분 수치모형을 이용한다. 본 연구에서는 빅데이터 기반의 RNN(Recurrent Neural Networks)기법 알고리즘을 활용하여 수위를 예측하였다. 연구대상지는 조위의 영향을 많이 받는 한강 전역을 대상으로 하였다. 2008년~2018년(10개년)의 실제 침수 피해 실적을 조사한 결과 잠수교, 한강대교, 청담대교 등에서 침수 피해 발생률이 높게 나타났고 SNS(Social Network Services)와 같은 비정형화 자료에서는 청담대교가 가장 많이 태그(Tag)되어 청담대교를 연구범위로 설정하였다. 본 연구에서는 Python에서 제공하는 Tensor flow Library를 이용하여 수위예측 알고리즘을 적용하였다. 데이터는 정형화 데이터와 비정형 데이터를 사용하였으며 정형화 데이터는 한강홍수 통제소나 기상청에서 제공하는 최근 10년간의 (2008~2018) 수위 및 강우량 자료를 수집하였다. 비정형화 데이터는 SNS를 이용하여 민간 정보를 수집하여 정형화된 자료와 함께 전체자료를 구축하였다. 민감도 분석을 통하여 모델의 은닉층(5), 학습률(0.02) 및 반복횟수(100)의 최적값을 설정하였고, 24시간 동안의 데이터를 이용하여 3시간 후의 수위를 예측하였다. 2008년~ 2017년 까지의 데이터는 학습 데이터로 사용하였으며 2018년의 수위를 예측 및 평가하였다. 2018년의 관측수위 자료와 비교한 결과 90% 이상의 데이터가 10% 이내의 오차를 나타내었으며, 첨두수위도 비교적 정확하게 예측되는 것을 확인하였다. 향후 수위와 강우량뿐만 아니라 다양한 인자들도 고려한다면 보다 신속하고 정확한 예측 정보를 얻을 수 있을 것으로 기대된다.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.167-173
• /
• 2023

As research has been published to predict future data using regression analysis or artificial intelligence as a method of analyzing economic indicators. In this study, we designed a system that predicts prospective futures prices using artificial intelligence that utilizes topic probability data obtained from past news articles using topic modeling. Topic probability distribution data for each news article were obtained using the Latent Dirichlet Allocation (LDA) method that can extract the topic of a document from past news articles via unsupervised learning. Further, the topic probability distribution data were used as the input for a Long Short-Term Memory (LSTM) network, a derivative of Recurrent Neural Networks (RNN) in artificial intelligence, in order to predict prospective futures prices. The method proposed in this study was able to predict the trend of futures prices. Later, this method will also be able to predict the trend of prices for derivative products like options. However, because statistical errors occurred for certain data; further research is required to improve accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.999-1005
• /
• 2020

While search portals' 'Portal News' account for the largest portion of aggregated news outlet, its neutrality as an outlet is questionable. This is because news aggregation may lead to prejudiced information consumption by recommending biased news articles. In this paper we introduce a new method of measuring political bias of news articles by using deep learning. It can provide its readers with insights on critical thinking. For this method, we build the dataset for deep learning by analyzing articles' bias from keywords, sourced from the National Assembly proceedings, and assigning bias to said keywords. Based on these data, news article bias is calculated by applying deep learning with a combination of Convolution Neural Network and Recurrent Neural Network. Using this method, 95.6% of sentences are correctly distinguished as either conservative or progressive-biased; on the entire article, the accuracy is 46.0%. This enables analyzing any articles' bias between conservative and progressive unlike previous methods that were limited on article subjects.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.155-167
• /
• 2024

Distribution and logistics industries contribute some of the biggest GDP(gross domestic product) in South Korea and the number of related companies are quarter of the total number of industries in the country. The number of retail tech companies are quickly increased due to the acceleration of the online and untact shopping trend. Furthermore, major distribution and logistics companies try to achieve integrated data management with the fulfillment process. In contrast, small and medium distribution companies still lack of the capacity and ability to develop digital innovation and smartization. Therefore, in this paper, a deep learning-based demand forecasting & recommendation model is proposed to improve business competitiveness. The proposed model is developed based on real sales transaction data to predict future demand for each product. The proposed model consists of six deep learning models, which are MLP(multi-layers perception), CNN(convolution neural network), RNN(recurrent neural network), LSTM(long short term memory), Conv1D-BiLSTM(convolution-long short term memory) for demand forecasting and collaborative filtering for the recommendation. Each model provides the best prediction result for each product and recommendation model can recommend best sales product among companies own sales list as well as competitor's item list. The proposed demand forecasting model is expected to improve the competitiveness of the small and medium-sized distribution and logistics industry.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.