• Advances in Computational Design
• /
• v.7 no.2
• /
• pp.113-128
• /
• 2022

Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.6
• /
• pp.385-392
• /
• 2022

Naval ship could face a variety of threats in isolated seas. In particular, fires and flooding are defined as disasters that are very likely to cause irreparable damage to ships. These disasters have a very high risk of personal injury as well. Therefore, when a disaster occurs, it must be quickly suppressed, but if there are people in the disaster area, the protection of life must be given priority. In order to quickly evacuate the ship crew in case of a disaster, we would like to propose a plan to quickly explore the evacuation route even in urgent situations. Using commercial escape simulation software, we obtain the data for deep neural network learning with simulations according to aisle characteristics and the properties and number of evacuation person. Using the obtained data, the passage prediction model is trained with a deep learning, and the passage time is predicted through the learned model. Construct a numerical map of a naval ship and construct a distance matrix of the vessel using predicted passage time data. The distance matrix configured in one of the path search algorithms, the Dijkstra algorithm, is applied to explore the evacuation path of naval ship.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.8
• /
• pp.39-52
• /
• 2022

Multilayer perceptron neural network was trained to determine the factor of safety and slip surface of the slope. Slope geometry is a simple slope based on Korean design standards, and the case of dry and existing groundwater levels are both considered, and the properties of the soil composing the slope are considered to be sandy soil including fine particles. When curating the data required for model training, slope stability analysis was performed in 42,000 cases using the limit equilibrium method. Steady-state seepage analysis of groundwater was also performed, and the results generated were applied to slope stability analysis. Results show that the multilayer perceptron model can predict the factor of safety and failure arc with high performance when the slope's physical properties data are input. A method for quantitative validation of the model performance is presented.

• Nuclear Engineering and Technology
• /
• v.54 no.5
• /
• pp.1825-1834
• /
• 2022

Performing high-fidelity computational fluid dynamics (HF-CFD) to predict the flow and heat transfer state of the coolant in the reactor core is expensive, especially in scenarios that require extensive parameter search, such as uncertainty analysis and design optimization. This work investigated the performance of utilizing a multi-fidelity reduced-order model (MF-ROM) in PWR rod bundles simulation. Firstly, basis vectors and basis vector coefficients of high-fidelity and low-fidelity CFD results are extracted separately by the proper orthogonal decomposition (POD) approach. Secondly, a surrogate model is trained to map the relationship between the extracted coefficients from different fidelity results. In the prediction stage, the coefficients of the low-fidelity data under the new operating conditions are extracted by using the obtained POD basis vectors. Then, the trained surrogate model uses the low-fidelity coefficients to regress the high-fidelity coefficients. The predicted high-fidelity data is reconstructed from the product of extracted basis vectors and the regression coefficients. The effectiveness of the MF-ROM is evaluated on a flow and heat transfer problem in PWR fuel rod bundles. Two data-driven algorithms, the Kriging and artificial neural network (ANN), are trained as surrogate models for the MF-ROM to reconstruct the complex flow and heat transfer field downstream of the mixing vanes. The results show good agreements between the data reconstructed with the trained MF-ROM and the high-fidelity CFD simulation result, while the former only requires to taken the computational burden of low-fidelity simulation. The results also show that the performance of the ANN model is slightly better than the Kriging model when using a high number of POD basis vectors for regression. Moreover, the result presented in this paper demonstrates the suitability of the proposed MF-ROM for high-fidelity fixed value initialization to accelerate complex simulation.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.19-33
• /
• 2022

With the explosive growth of social media, its abundant text-based data generated by web users has become an important source for data analysis. For example, we often witness online movie reviews from the 'Naver Movie' affecting the general public to decide whether they should watch the movie or not. This study has conducted analysis on the Naver Movie's text-based review data to predict the actual ratings. After examining the distribution of movie ratings, we performed semantics analysis using Korean Natural Language Processing. This research sought to find the best review rating prediction model by comparing machine learning and deep learning models. We also compared various regression and classification models in 2-class and multi-class cases. Lastly we explained the causes of review misclassification related to movie review data characteristics.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.70-70
• /
• 2023

강우 발생 중 용담댐 상류로부터 용담댐으로 유입되는 유입량을 정확하게 예측하는 것은 하류 지역의 홍수 피해를 최소화하기 위한 댐의 적절한 운영에 필수적이다. 물리 기반 강우-유출 시뮬레이션 모형은 물리적 과정의 이해를 바탕으로 홍수 예측 분야에 광범위하게 사용되고 있다. 그러나 복잡한 물리 과정을 완벽히 이해하는 것은 거의 불가능하므로 다양한 가정 조건들을 이용해 복잡한 과정을 단순화하여 계산해야 하는 한계가 존재한다. 최근에는 방대한 데이터의 축적과 컴퓨터 능력의 향상으로 인해 데이터 기반 모형이 다양한 실무 문제를 해결하는 데 강력한 도구로 활용되고 있을 뿐 아니라 시뮬레이션 및 예측 등에도 다양하게 이용되고 있다. 그러나 예측 시간이 늘어날수록 입력자료로 이용되는 과거 자료와 출력자료로 이용되는 미래자료와의 상관관계가 줄어들어 모형의 성능이 저하된다. 따라서 본 연구에서는 용담댐의 시간당 유입량을 예측하기 위해 물리 기반 강우-유출 모형과 오차 보정 모형을 결합한 하이브리드 접근 방식을 제안한다. 물리 기반 강우-유출 모형으로는 HEC-HMS 모형을 사용하였으며, 오차 보정 모형에는 기계학습 모형인 인공신경망(Artificial Neural Network, ANN) 모형을 사용하였다. HEC-HMS 모형, ANN 및 하이브리드 모형(HEC-HMS + ANN)의 성능을 비교하기 위해 20 개의 홍수 사상을 모형 구축 및 검증에 사용하였다. 그 결과 하이브리드 모형은 예측 시간이 늘어날수록 HEC-HMS 및 ANN 모형보다 우수한 성능을 나타냈다. 물리모형에 기계학습을 이용한 오차 보정 절차를 통합한 경우 홍수 유출 예측의 정확성이 향상되었다. 다양한 모형의 비교 결과 본 연구에서 적용한 하이브리드 모형이 물리기반 강우-유출 모형 및 순수 기계학습 모형보다 우수한 성능을 보여줌으로써, 하이브리드 모형은 물리모형과 순수 기계학습 모형의 단점들을 보완하는데 이용할 수 있음을 나타낸다. 이 연구의 주요 목적은 강우-유출 시물레이션 모형의 오차 보정 기술에 대한 더 깊은 이해를 제공하는데 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.292-292
• /
• 2023

본 연구에서는 인공신경망을 이용한 통계적 모형을 구성하여 금강권역의 봄철(3~5월) 강수량 예측을 수행하였다. 통계적 모형의 예측인자로서는 NOAA 등에서 제공하는 AAO, AMM, AO 등 36종의 기후지수와 대상권역인 금강권역의 강수량, 기온 등의 기상인자 8종 등 총 44종의 기후지수를 활용하였다. 예측대상기간을 기준으로 선행기간(1~18개월)에 따른 상관성을 분석하여 상관도가 높은 10개의 기후지수를 예측인자로 선정하였다. 예측모형 형태는 10개의 입력층과 1개의 은닉층으로 되어 있는 인공신경망모형을 구성하였다. 모형 구성과정에서의 불확실성을 최소화하고 예측모형의 적합도를 높이기 위해 예측대상기간을 기준으로 과거 40년간의 자료에 대해 임의로 20년간 자료를 선별하여 모형을 구성하고, 너머지 기간에 대해 검증하는 무작위 교차검증을 반복하여, 예측대상기간 및 예측시점에 따라 각각 적합도가 높은 1000개의 예측모형을 선별하였다. 과거기간(1991~2022년)을 대상으로 예측시점에 따라 각 연도별 1000개의 예측결과를 도출하여, 실제 해당년도의 관측값과의 비교를 통해 예측성을 분석하였다. 예측성은 크게 예측치의 최대값과 최소값 범위 및 예측치의 25%~75% 범위 안에 관측치가 포함될 확률, 그리고 과거 관측값의 3분위 구간을 기준으로 한 예측확률 등을 평가하였다. 관측치가 예측치의 범위 안에 포함될 확률은 평균 87.5%, 예측치의 25~75% 범위 안에 포함될 확률은 30.2%로 나타났으며, 3분위 예측확률은 35.6%로 분석되었다. 관측값과의 일대일 비교는 정확도가 떨어지지만 3분위 예측확률이 33.3% 이상인 점으로 볼 때 예측성은 확보된다고 볼 수 있다. 다만, 우리나라 강수량의 불규칙성과 통계적 모형 특성상 과거 관측되지 않은 패턴에 대해서는 예측이 어려운 문제가 있어, 특정년도의 예측결과가 관측치를 크게 벗어나는 경우도 종종 나타나고 있다.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.305-307
• /
• 2021

Alzheimer's Disease (AD) is a cognitive disorder characterized by memory impairment that can be assessed at early stages based on administering clinical tests. However, the AD pathophysiological mechanism is still poorly understood due to the difficulty of distinguishing different levels of AD severity, even using a variety of brain modalities. Therefore, in this study, we present a hybrid EEG-fNIRS modalities to compensate for each other's weaknesses with the help of Machine Learning (ML) techniques for classifying four subject groups, including healthy controls (HC) and three distinguishable groups of AD levels. A concurrent EEF-fNIRS setup was used to record the data from 41 subjects during Oddball and 1-back tasks. We employed both a traditional neural network (NN) and a CNN-LSTM hybrid model for fNIRS and EEG, respectively. The final prediction was then obtained by using majority voting of those models. Classification results indicated that the hybrid EEG-fNIRS feature set achieved a higher accuracy (71.4%) by combining their complementary properties, compared to using EEG (67.9%) or fNIRS alone (68.9%). These findings demonstrate the potential of an EEG-fNIRS hybridization technique coupled with ML-based approaches for further AD studies.