• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.225-225
• /
• 2015

Drought events usually evolve slowly in time and their impacts generally span a long period of time. This indicates that the sequence of drought is not completely random. The Hidden Markov Model (HMM) is a probabilistic model used to represent dependences between invisible hidden states which finally result in observations. Drought characteristics are dependent on the underlying generating mechanism, which can be well modelled by the HMM. This study employed a HMM with Gaussian emissions to fit the Standardized Precipitation Index (SPI) series and make multi-step prediction to check the drought characteristics in the future. To estimate the parameters of the HMM, we employed a Bayesian model computed via Markov Chain Monte Carlo (MCMC). Since the true number of hidden states is unknown, we fit the model with varying number of hidden states and used reversible jump to allow for transdimensional moves between models with different numbers of states. We applied the HMM to several stations SPI data in South Korea. The monthly SPI data from January 1973 to December 2012 was divided into two parts, the first 30-year SPI data (January 1973 to December 2002) was used for model calibration and the last 10-year SPI data (January 2003 to December 2012) for model validation. All the SPI data was preprocessed through the wavelet denoising and applied as the visible output in the HMM. Different lead time (T= 1, 3, 6, 12 months) forecasting performances were compared with conventional forecasting techniques (e.g., ANN and ARMA). Based on statistical evaluation performance, the HMM exhibited significant preferable results compared to conventional models with much larger forecasting skill score (about 0.3-0.6) and lower Root Mean Square Error (RMSE) values (about 0.5-0.9).

• 한국전자통신학회논문지
• /
• 제16권2호
• /
• pp.329-338
• /
• 2021

본 연구는 풍력발전의 합리적인 운영 계획과 에너지 저장창치의 용량산정을 위한 풍력 발전량을 예측한다. 예측을 위해 물리적 접근법과 통계적 접근법을 결합하여 풍력 발전량의 예측 방법을 제시하고 풍력 발전의 요인을 분석하여 변수를 선정한다. 선정된 변수들의 과거 데이터를 수집하여 딥러닝을 이용해 풍력 발전량을 예측한다. 사용된 모델은 Bidirectional LSTM(:Long short term memory)과 CNN(:Convolution neural network) 알고리즘을 결합한 하이브리드 모델을 구성하였으며, 예측 성능 비교를 위해 MLP 알고리즘으로 이루어진 모델과 오차를 비교하여, 예측 성능을 평가하고 그 결과를 제시한다.

• 농업과학연구
• /
• 제46권4호
• /
• pp.843-856
• /
• 2019

Real-time flood prediction has an important role in significantly reducing potential damage caused by floods for urban residential areas located downstream of river basins. This paper presents an effective approach for flood forecasting based on the construction of a deep neural network (DNN) model. In addition, this research depends closely on the open-source software library, TensorFlow, which was developed by Google for machine and deep learning applications and research. The proposed model was applied to forecast the flowrate one, two, and three days in advance at the Son Tay hydrological station on the Red River, Vietnam. The input data of the model was a series of discharge data observed at five gauge stations on the Red River system, without requiring rainfall data, water levels and topographic characteristics. The research results indicate that the DNN model achieved a high performance for flood forecasting even though only a modest amount of data is required. When forecasting one and two days in advance, the Nash-Sutcliffe Efficiency (NSE) reached 0.993 and 0.938, respectively. The findings of this study suggest that the DNN model can be used to construct a real-time flood warning system on the Red River and for other river basins in Vietnam.

• 정보학연구
• /
• 제5권4호
• /
• pp.173-183
• /
• 2002

본 논문에서는 무선통신 서비스를 위한 필수 자원인 주파수의 수요예측 방법론을 제시한다. 이는 효율적인 국내 전파자원 관리를 위해 필수적인 업무이다. 제안한 방법론은 크게 기본 서비스군 분류, 유효 트래픽 도출 및 주파수 수요예측의 세단계로 구성된다. 기본 서비스군 분류 단계에서는 기존의 주파수 수요예측 방법론의 결과를 이용하여 서비스를 Wide area mobile, Short range radio, Fixed wireless access 및 Digital video broadcasting으로 나누며, 유효 트래픽 도출 단계에서는 총 트래픽을 erlang 및 bps 단위로 환산하여 구하는 방법을 제안한다. 구체적으로 유효 트래픽 도출 단계에서는 사용자 분류, 기본 어플리케이션 분류 및 어플리케이션별 유효 트래픽 추정의 과정을 거친다. 끝으로, 주파수 수요예측 단계에서 각 서비스군별로 서로 다른 주파수 수요예측 방법론을 제시한다.

• 전기전자학회논문지
• /
• 제26권4호
• /
• pp.545-552
• /
• 2022

특정 분야의 특허출원수는 기술의 수명주기 및 산업의 활성화 정도와 밀접한 관계를 가지고 있다. 따라서 사전에 사업을 준비하는 기업들과 미래 유망 기술을 초기 단계에서 선발하여 투자하고자 하는 정부 기관들은 미래의 특허 출원수 예측에 대해 큰 관심을 가지고 있다. 본 논문에서는 시계열 데이터에 적합한 RNN의 기법 중 하나인 양방향 LSTM 기법을 이용하여 기존 예측 방법들보다 정확도를 높이는 방법을 제안한다. 5개 분야의 대한민국 특허 출원 데이터에 대해서 제안된 방법은 기존에 사용되던 확산 모델 중 하나인 Bass 모델과 비교하여 평균 절대 백분율 오차(MAPE)의 값이 약 16퍼센트 향상된 결과를 보여준다.

• Journal of information and communication convergence engineering
• /
• 제5권2호
• /
• pp.171-176
• /
• 2007

To give a guarantee a consistently high level of quality and reliability of Telematics traffic service, traffic flow forecasting is very important issue. In this paper, we proposed an adaptable integrated prediction model to predict the traffic flow in the future. Our model combines two methods, short-term prediction model and long-term prediction model with different combining coefficients to reflect current traffic condition. Short-term model uses the Kalman filtering technique to predict the future traffic conditions. And long-term model processes accumulated speed patterns which means the analysis results for all past speeds of each road by classifying the same day and the same time interval. Combining two models makes it possible to predict future traffic flow with higher accuracy over a longer time range. Many experiments showed our algorithm gives a better precise prediction than only an accumulated speed pattern that is used commonly. The result can be applied to the car navigation to support a dynamic shortest path. In addition, it can give users the travel information to avoid the traffic congestion areas.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권2호
• /
• pp.147-163
• /
• 2021

Purpose The study aims to predict real estate prices by utilizing regional characteristics. Since real estate has the characteristic of immobility, the characteristics of a region have a great influence on the price of real estate. In addition, real estate prices are closely related to economic development and are a major concern for policy makers and investors. Accurate house price forecasting is necessary to prepare for the impact of house price fluctuations. To improve the performance of our predictive models, we applied LSTM, a widely used deep learning technique for predicting time series data. Design/methodology/approach This study used time series data on real estate prices provided by the Ministry of Land, Infrastructure and Transport. For time series data preprocessing, HP filters were applied to decompose trends and SOM was used to cluster regions with similar price directions. To build a real estate price prediction model, SVR and LSTM were applied, and the prices of regions classified into similar clusters by SOM were used as input variables. Findings The clustering results showed that the region of the same cluster was geographically close, and it was possible to confirm the characteristics of being classified as the same cluster even if there was a price level and a similar industry group. As a result of predicting real estate prices in 1, 2, and 3 months, LSTM showed better predictive performance than SVR, and LSTM showed better predictive performance in long-term forecasting 3 months later than in 1-month short-term forecasting.

• 국제지역연구
• /
• 제13권3호
• /
• pp.331-359
• /
• 2009

본 연구는 기술예측분야에서 자주 사용되는 성장곡선모형을 통해 BT산업 세부산업별 성장추세를 2030년까지 전망하고, 미국의 BT산업 및 한국의 ICT산업의 성장추세와 접목하여 비교 실증분석을 실시하였다. 연구결과에 따르면, 1) 한국의 BT산업 전체 명목생산액은 2007년 3조 7천억원에서 2016년 7조 3천억원, 2020년 8조 7천억원, 2030년 10조 8천억원으로 성장할 것으로 예측되었다. 2) BT 세부산업별로는 생물의약산업의 성장세가 두드러진 가운데 전체 BT산업 대비 비중이 2007년 45.4%에서 2016년 55.3%, 2020년 60.8%, 2030년 70%대로 점차 확대될 것으로 예측되었다. 3) 예측전망에 기초하여 향후 한국 BT산업발전이 수출지향적인 생물의약분야를 중심으로 전개될 것으로 판단된다. 4) 한국 BT산업 대비 미국의 BT산업규모는 2007년 15배에서 2030년 21배로 확대되나, 생물의약부문에 한정시킬 경우 2007년 33배에서 2030년 26배로 그 격차가 다소 완화될 것으로 예측되었다. 5) 한국 ICT산업은 대체로 성숙기에 접어들었음이 확인되었고, 미국 BT산업과 한국 생물의약산업에 비해 성장률 측면에서 대략 5년~10년 정도 앞서가고 있음을 발견하였다. 이상의 연구결과는 바이오신약 등 생물의약분야에 대한 선택과 집중을 통한 지원과 수출지향적인 정책마련이 필요함을 시사한다.

• 한국컴퓨터정보학회논문지
• /
• 제28권5호
• /
• pp.155-161
• /
• 2023

우리나라 수출의 97.5%, 수입의 87.2%가 해상운송으로 이뤄지며 항만이 한국 경제의 중요한 구성요소이다. 이러한 항만의 효율적인 운영을 위해서는 항만 물동량의 단기 예측을 통해 개선시킬 수가 있으며 과학적인 연구방법이 필요하다. 이전 연구는 주로 장기예측을 기반으로 대규모 인프라투자를 위한 연구에 중점을 두었으며 컨테이너 항만물동량에만 집중한 측면이 크다. 본 연구는 국내 대표적인 석유항만인 울산항의 석유 및 가스화물 물동량에 대한 단기 예측을 수행하였으며 딥러닝 모델인 LSTM(Long Short Term Memory) 모델을 사용하여 RMSE기준으로 예측성능을 확인하였다. 본 연구의 결과는 석유 및 가스화물 물동량 수요 예측의 정확도를 높여 항만 운영의 효율성을 개선하는 근거가 될 수 있을 것으로 기대된다. 또한 기존 연구의 한계로 컨테이너 항만 물동량뿐만 아니라 석유 및 가스화물 물동량 예측에도 LSTM의 활용할 수 있다는 가능성을 확인할 수 있으며 향후 추가 연구를 통해 일반화가 가능할 것으로 기대된다.

• 수산경영론집
• /
• 제41권1호
• /
• pp.25-52
• /
• 2010

The purpose of this paper is to suggest major strategies and necessary new projects for the medium- and long-term development of the Korean Fisheries Outlook Project. To suggest the Korean Fisheries Outlook Center with the above purpose, this paper employs Analytic Hierarchy Process analysis based on surveys obtained by special groups related with the KFOP. The survey is broadly composed of two goals; the medium- and long-term development directions and setting up of new furtherance projects. Each goal has upper and lower strategies respectively. The first goal, the medium- and long-term development directions, has four factors as upper strategies. The upper strategies are composed of accuracy, efficiency, timeliness, and political effectiveness of the fisheries outlook information. In addition, each upper strategy has three lower strategies respectively. For example, accuracy of the fisheries outlook information includes strength of data collection function, strength of satellite photography function, and strength of data analysis function. The second goal, setting up of new furtherance projects, has three factors as upper strategies. The upper strategies consist of accuracy promotion of outlook information using high-technique, field expansion of outlook species, and strength of analyzing function on oversea fisheries information. Each upper strategy has three lower strategies respectively. For instant, accuracy promotion of outlook information using high-technique has strength of information analysis function covered from production to consumption, strength of satellite information function, and structure of forecasting model on demand and supply by outlook species. The above upper and lower strategies were analytically drawn out through insightful interviews with special groups such as officials of the government, presidents of the producer and distributor groups, and researchers of the Korea Maritime Institute and other research institutes. As a result of AHP analysis, first, priorities of upper strategies with the medium- and long-term development directions are analyzed as accuracy, timeliness, political effectiveness, and efficiency in order. Also, priorities of all lower strategies reflecting priorities of upper strategies are examined as includes strength of data collection function on the fisheries outlook information, delivery of rapid information on outlook products for all people interested, strength of data analysis function on fisheries outlook information, strength of consumption outlook function on fish products, and strength of early warning system for domestic fish products in order. Second, priorities of upper strategies with the setting up of new furtherance projects are analyzed as accuracy promotion of outlook information using high-technique, field expansion of outlook species, and strength of analysis function on oversea fisheries information in order. In addition, priorities of all lower strategies reflecting priorities of upper strategies are examined as building up of forecasting model on demand and supply by outlook species, strength of information analysis function covering all steps from production to consumption, expansion of consumption outlook for consumers, strength of movement analysis function of oversea farming industry, and outlook expansion of farming species.