• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1231-1242
• /
• 2019

This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.

• 대기
• /
• 제25권1호
• /
• pp.1-18
• /
• 2015

The most objective way to overcome the limitation of numerical weather prediction model is to represent the uncertainty of prediction by introducing probabilistic forecast. The uncertainty of the numerical weather prediction system developed due to the parameterization of unresolved scale motions and the energy losses from the sub-scale physical processes. In this study, we focused on the growth of model errors. We performed ensemble forecast to represent model uncertainty. By employing the multi-physics scheme (PHYS) and the stochastic kinetic energy backscatter scheme (SKEBS) in simulating typhoon Rusa (2002), we assessed the performance level of the two schemes. The both schemes produced better results than the control run did in the ensemble mean forecast of the track. The results using PHYS improved by 28% and those based on SKEBS did by 7%. Both of the ensemble mean errors of the both schemes increased rapidly at the forecast time 84 hrs. The both ensemble spreads increased gradually during integration. The results based on SKEBS represented model errors very well during the forecast time of 96 hrs. After the period, it produced an under-dispersive pattern. The simulation based on PHYS overestimated the ensemble mean error during integration and represented the real situation well at the forecast time of 120 hrs. The displacement speed of the typhoon based on PHYS was closest to the best track, especially after landfall. In the sensitivity tests of the model uncertainty of SKEBS, ensemble mean forecast was sensitive to the physics parameterization. By adjusting the forcing parameter of SKEBS, the default experiment improved in the ensemble spread, ensemble mean errors, and moving speed.

• International journal of advanced smart convergence
• /
• 제11권1호
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.183-190
• /
• 2021

In this paper, we implement a system for a fund recommendation based on the investment propensity and for a future fund price prediction. The investment propensity is classified by scoring user responses to series of questions. The proposed system recommends the funds with a suitable risk rating to the investment propensity of the user. The future fund prices are predicted by Prophet model which is one of the machine learning methods for time series data prediction. Prophet model predicts future fund prices by learning the parameters related to trend changes. The prediction by Prophet model is simple and fast because the temporal dependency for predicting the time-series data can be removed. We implement web pages for the fund recommendation and for the future fund price prediction.

• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1471-1476
• /
• 2021

수해는 홍수나 해일을 유발하여 막대한 인명과 재산의 피해를 초래할 수 있다. 이에 대해 홍수 예측을 통한 빠른 대피 결정으로 피해를 줄일 수 있으며, 해당 분야에서는 시계열 데이터를 활용하여 홍수를 예측하려는 연구들도 많이 진행되고 있다. 본 논문에서는 CNN 기반의 시계열 예측 모델을 제안한다. 하천의 수위와 강수량을 사용하여 CNN 기반의 수위 예측 모델을 구현하였고, 시계열 예측에 많이 사용되는 LSTM, GRU 모델과 비교하여 성능을 확인하였다. 또한 입력 데이터의 크기에 따른 성능 차이를 확인하여 보완해야 할 점을 찾을 수 있었고, LSTM과 GRU보다 더 좋은 성능을 낼 수 있다는 것을 확인하였다. 이를 통해 홍수 예측을 위한 초기 연구로서 활용할 수 있을 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1712-1732
• /
• 2011

Cloud provides dynamically scalable virtualized computing resources as a service over the Internet. To achieve higher resource utilization over virtualization technology, an optimized strategy that deploys virtual machines on physical machines is needed. That is, the total number of active physical host nodes should be dynamically changed to correspond to their resource usage rate, thereby maintaining optimum utilization of physical machines. In this paper, we propose a pattern-based prediction model for resource provisioning which facilitates best possible resource preparation by analyzing the resource utilization and deriving resource usage patterns. The focus of our work is on predicting future resource requests by optimized dynamic resource management strategy that is applied to a virtualized data center in a Cloud computing environment. To this end, we build a prediction model that is based on user request patterns and make a prediction of system behavior for the near future. As a result, this model can save time for predicting the needed resource amount and reduce the possibility of resource overuse. In addition, we studied the performance of our proposed model comparing with conventional resource provisioning models under various Cloud execution conditions. The experimental results showed that our pattern-based prediction model gives significant benefits over conventional models.

• 대한교통학회지
• /
• 제18권1호
• /
• pp.47-59
• /
• 2000

본 연구에서는 고속도로 교통관리시스템에서 VDS 교통정보 와 대상지역의 TCS로부터 여행시간을 수집하고, 이들 자료를 토대로 신경망 이론을 이용한 여행시간 추정(Estimation)모형을 구축하였다. 또한, 신경망 이론에 칼만필터기법(Kalman Filter Technique)을 연계하여 단위시간 동안의 여행시간을 예측(Prediction)하여, 고속도로 이용자에게 보다 향상된 실시간 여행시간정보를 제공할 수 있는 여행시간 추정 및 예측 알고리즘을 개발하였다. 신경망 모형의 여행시간 추정 방식과 현재 적용되고 있는 여행시간 산출 방식의 비교/분석을 위해 각 각의 여행시간 산출방식에 의한 평가지표별로 시행한 평가의 결과는 신경망 모형이 제시한 대부분의 지표에서 상대적으로 우수하게 나타났다.

• Journal of Astronomy and Space Sciences
• /
• 제33권4호
• /
• pp.279-285
• /
• 2016

The space radiation dose over air routes including polar routes should be carefully considered, especially when space weather shows sudden disturbances such as coronal mass ejections (CMEs), flares, and accompanying solar energetic particle events. We recently established a heliocentric potential (HCP) prediction model for real-time operation of the CARI-6 and CARI-6M programs. Specifically, the HCP value is used as a critical input value in the CARI-6/6M programs, which estimate the aviation route dose based on the effective dose rate. The CARI-6/6M approach is the most widely used technique, and the programs can be obtained from the U.S. Federal Aviation Administration (FAA). However, HCP values are given at a one month delay on the FAA official webpage, which makes it difficult to obtain real-time information on the aviation route dose. In order to overcome this critical limitation regarding the time delay for space weather customers, we developed a HCP prediction model based on sunspot number variations (Hwang et al. 2015). In this paper, we focus on improvements to our HCP prediction model and update it with neutron monitoring data. We found that the most accurate method to derive the HCP value involves (1) real-time daily sunspot assessments, (2) predictions of the daily HCP by our prediction algorithm, and (3) calculations of the resultant daily effective dose rate. Additionally, we also derived the HCP prediction algorithm in this paper by using ground neutron counts. With the compensation stemming from the use of ground neutron count data, the newly developed HCP prediction model was improved.

• 한국수자원학회논문집
• /
• 제51권12호
• /
• pp.1207-1216
• /
• 2018

본 연구는 물리적 수리 수문모형의 적용이 제한적인 감조하천에서의 수위예측을 목적으로 하고 있으며, 이를 위해 한강 잠수교를 대상으로 딥러닝 오픈소스 소프트웨어 라이브러리인 TensorFlow를 활용하여 LSTM 모형을 구성하고 2011년부터 2017년까지의 10분 단위의 잠수교 수위, 팔당댐 방류량과 한강하구 강화대교지점의 예측조위 자료를 이용하여 모형학습(2011~2016) 및 수위예측(2017)을 수행하였다. 모형 매개변수는 민감도 분석을 통해 은닉층의 개수는 6개, 학습속도는 0.01, 학습횟수는 3000번로 결정하였으며, 모형 학습 시 학습정보의 시간적 양을 결정하는 중요한 매개변수인 시퀀스길이는 1시간, 3시간, 6시간으로 변화시키며 모의하였다. 최종적으로 선행시간에 따른 모의 예측능력을 평가하기 위해 LSTM 모형의 예측 선행시간을 6개(1 ~ 24시간)로 구분하여 실측수위와 예측수위와의 비교 분석을 수행한 결과, LSTM 모형의 최적의 성능을 내는 결과는 시퀀스길이를 1시간으로 하였을 때로 분석되었으며, 특히 선행시간 1시간에 대한 예측정확도는 RMSE는 0.065 m, NSE는 0.99로 실측수위에 매우 근접한 예측 결과를 나타내었다. 또한 시퀀스길이에 상관없이 선행시간이 길어질수록 모형의 예측 정확도는 2017년 전기간에 걸쳐 평균적으로 RMSE 0.08 m에서 0.28 m로 오차가 증가하였으며, NSE는 0.99에서 0.74로 감소하였다.

• 한국항행학회논문지
• /
• 제11권3호
• /
• pp.252-258
• /
• 2007

무선모바일 통신망에서는 사용자의 이동성보장 기술과 사용자가 요구하는 서비스품질(QoS)을 만족시키기 위한 효율적인 무선자원관리기술이 많이 연구되어 왔다. 본 연구에서는 시계열 예측기법(Time series prediction) 인 ARMA(Auto Regressive Moving Average) 모델을 이용하여 사용자가 요구하는 자원의 양을 예측하여 동적으로 자원을 할당함으로써 사용자의 이동성에 따른 QoS를 보장할 수 있는 자원할당방법을 제안한다. 제안한 방법은 ARMA 예측모델을 사용하여 이전에 핸드오프연결이 사용한 채널 수를 기초로 앞으로 필요로 하는 채널 수를 예측하여 예약함으로써 원하는 핸드오프 손실률에서 서비스가 이루어지도록 한다. 시뮬레이션을 통하여 기존의 RCS(Reserved channel scheme) 방법과 비교하여 핸드오프 연결의 손실률과 자원의 이용률에서 우수함을 보인다.