• 한국지능시스템학회논문지
• /
• 제13권3호
• /
• pp.360-365
• /
• 2003

본 논문에서는 데이터의 효율적인 활용과 정확성에서 보다 우수한 특성을 보이는 GMDH(Croup Method of Data Handling) 알고리즘을 전력수요예측에 적용함으로써 입력 데이터의 선정을 용이하게 하였고, 다양한 데이터를 기반으로 보다 정확한 예측을 할 수 있게 하였다. 그리고, 예측 시에 경제적인 요인(GDP, 수출, 수입, 취업자 수, 경제활동인구, 석유소비량)과 기후적인 요인(평균기온)을 모두 고려하였다. 또한 목표 예측 기간을 1999년 1/4분기에서 2001년 1/4분기까지 9개의 분기로 가정하고, 가정한 목표 기간의 예측 정확도를 높이기 위해 3단계의 시뮬레이션 과정(최적 입력 분기 수를 결정하는 과정, 입력 데이터와 예측값의 시간적 연관성을 분석하는 과정, 입력 데이터의 최적화 과정)을 이용함으로써 더 정확한 전력수요예측 방법을 제시하였고, 제안된 기법으로 목표한 예측 기간에서 0.96%의 평균 에러율을 얻을 수 있었다.

• The Plant Pathology Journal
• /
• 제38권4호
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• 한국전자통신학회논문지
• /
• 제18권6호
• /
• pp.1331-1336
• /
• 2023

머신러닝을 이용한 텍스트 기반 어류 질병 분류에서 머신러닝 모델의 입력 파라미터가 너무 많은 문제가 존재하지만, 성능의 문제로 임의로 입력 파라미터를 줄일 수 없다. 본 논문에서는 이 문제를 해결하고자 SHAP 분석 기법을 활용해 넙치 질병 분류에 특화된 입력 파라미터 최적화 방안을 제시한다. 제안한 방법은 SHAP 분석 기법을 적용하여 넙치 질병 문진표에서 추출한 질병 정보의 데이터 전처리와 AutoML을 활용한 머신러닝 모델 평가 과정을 포함한다. 이를 통해 AutoML의 입력 파라미터의 성능을 평가하고, 최적의 입력 파라미터 조합을 도출한다. 본 연구에서 제안 방법은 필요한 입력 파라미터 수를 감소시키면서도 기존의 성능을 유지할 수 있을 것으로 기대되며, 이는 텍스트 기반 넙치 질병 분류의 효율성 및 실용성을 높이는 데 기여할 것이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2393-2398
• /
• 2003

In this paper, we proposes a new fuzzy inference system for modeling nonlinear systems given input and output data. In the suggested fuzzy inference system, the number of fuzzy rules and parameter values of membership functions are automatically decided by using the kernel-based method. The kernel-based method individually performs linear transformation and kernel mapping. Linear transformation projects input space into linearly transformed input space. Kernel mapping projects linearly transformed input space into high dimensional feature space. The structure of the proposed fuzzy inference system is equal to a Takagi-Sugeno fuzzy model whose input variables are weighted linear combinations of input variables. In addition, the number of fuzzy rules can be reduced under the condition of optimizing a given criterion by adjusting linear transformation matrix and parameter values of kernel functions using the gradient descent method. Once a structure is selected, coefficients in consequent part are determined by the least square method. Simulated result illustrates the effectiveness of the proposed technique.

• 한국환경과학회지
• /
• 제30권12호
• /
• pp.1053-1065
• /
• 2021

In this study, the prediction technology of Hydrological Quantitative Precipitation Forecast (HQPF) was improved by optimizing the weather predictors used as input data for machine learning. Results comparison was conducted using bias and Root Mean Square Error (RMSE), which are predictive accuracy verification indicators, based on the heavy rain case on August 21, 2021. By comparing the rainfall simulated using the improved HQPF and the observed accumulated rainfall, it was revealed that all HQPFs (conventional HQPF and improved HQPF 1 and HQPF 2) showed a decrease in rainfall as the lead time increased for the entire grid region. Hence, the difference from the observed rainfall increased. In the accumulated rainfall evaluation due to the reduction of input factors, compared to the existing HQPF, improved HQPF 1 and 2 predicted a larger accumulated rainfall. Furthermore, HQPF 2 used the lowest number of input factors and simulated more accumulated rainfall than that projected by conventional HQPF and HQPF 1. By improving the performance of conventional machine learning despite using lesser variables, the preprocessing period and model execution time can be reduced, thereby contributing to model optimization. As an additional advanced method of HQPF 1 and 2 mentioned above, a simulated analysis of the Local ENsemble prediction System (LENS) ensemble member and low pressure, one of the observed meteorological factors, was analyzed. Based on the results of this study, if we select for the positively performing ensemble members based on the heavy rain characteristics of Korea or apply additional weights differently for each ensemble member, the prediction accuracy is expected to increase.

• 전자공학회논문지
• /
• 제53권3호
• /
• pp.143-150
• /
• 2016

본 논문에서는 안면근육 표면근전도를 기반으로 근육 조합 최적화를 통한 한국어 단모음 인식 방법을 제안한다. 표면근전도 신호는 한국어 단모음 발음에 따라 서로 다른 패턴과 근육 활성도를 보였다. 이전 연구에서 높은 인식 정확도를 보였던 RMS, VAR, MMAV1, MMAV2와 Cepstral Coefficients를 특징 추출 알고리즘으로 사용하였으며, QDA(Quadratic Discriminant Analysis)와 HMM(Hidden Markov Model)으로 한국어 단모음을 분류하였다. 트레이닝 단계에서 입력 받은 데이터로 근육조합을 최적화하고, 최적화 결과를 인식단계에 적용한다. 이때, 새로운 근전도 신호를 입력받고 한국어 단모음을 최종 인식한다. 실험결과 제안한 방법의 인식 정확도가 QDA에서 평균 85.7%, HMM에서 평균 75.1%를 보였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권1호
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• Structural Engineering and Mechanics
• /
• 제63권1호
• /
• pp.115-124
• /
• 2017

In this paper, a different technique to predict the effects of soil-structure interaction (SSI) on seismic response of building systems is investigated. The technique use a machine learning algorithm called Support Vector Regression (SVR) with technical and analytical results as input features. Normally, the effects of SSI on seismic response of existing building systems can be identified by different types of large data sets. Therefore, predicting and estimating the seismic response of building is a difficult task. It is possible to approximate a real valued function of the seismic response and make accurate investing choices regarding the design of building system and reduce the risk involved, by giving the right experimental and/or numerical data to a machine learning regression, such as SVR. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The results show that the performance of the technique can be predicted by reducing the number of real data input features. Further, performance enhancement was achieved by optimizing the RBF kernel and SVR parameters through grid search.

• 인터넷정보학회논문지
• /
• 제25권4호
• /
• pp.47-56
• /
• 2024

본 연구는 BERT 기반 자연어처리 모델들을 미세 조정하여 한국어 리뷰 데이터를 대상으로 감성 분석을 수행하는 방법을 제안한다. 이 과정에서 입력 시퀀스 길이에 변화를 주어 그 성능을 비교 분석함으로써 입력 시퀀스 길이에 따른 최적의 성능을 탐구하고자 한다. 이를 위해 의류 쇼핑 플랫폼 M사에서 수집한 텍스트 리뷰 데이터를 활용한다. 웹 스크래핑을 통해 리뷰 데이터를 수집하고, 데이터 전처리 단계에서는 긍정 및 부정 만족도 점수 라벨을 재조정하여 분석의 정확성을 높였다. 구체적으로, GPT-4 API를 활용하여 리뷰 텍스트의 실제 감성을 반영한 라벨을 재설정하고, 데이터 불균형 문제를 해결하기 위해 6:4 비율로 데이터를 조정하였다. 의류 쇼핑 플랫폼에 존재하는 리뷰들을 평균적으로 약 12 토큰의 길이를 띄었으며, 이에 적합한 최적의 모델을 제공하기 위해 모델링 단계에서는 BERT기반 사전학습 모델 5가지를 활용하여 입력 시퀀스 길이와 메모리 사용량에 집중하여 성능을 비교하였다. 실험 결과, 입력 시퀀스 길이가 64일 때 대체적으로 가장 적절한 성능 및 메모리 사용량을 나타내는 경향을 띄었다. 특히, KcELECTRA 모델이 입력 시퀀스 길이 64에서 가장 최적의 성능 및 메모리 사용량을 보였으며, 이를 통해 한국어 리뷰 데이터의 감성 분석에서 92%이상의 정확도와 신뢰성을 달성할 수 있었다. 더 나아가, BERTopic을 활용하여 새로 입력되는 리뷰 데이터를 카테고리별로 분류하고, 최종 구축한 모델로 각 카테고리에 대한 감성 점수를 추출하는 한국어 리뷰 감성 분석 프로세스를 제공한다.

• 한국분무공학회지
• /
• 제27권2호
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.