• The Journal of the Acoustical Society of Korea
• /
• v.42 no.1
• /
• pp.32-41
• /
• 2023

Recently, studies on reverberation suppression using Non-negative Matrix Factorization (NMF) have been actively conducted. The NMF method uses a cost function based on the Kullback-Leibler divergence for optimization. And some constraints are added such as temporal continuity, pulse length, and energy ratio between reverberation and target. The tendency of constraints are controlled by hyperparameters. Therefore, in order to effectively suppress reverberation, hyperparameters need to be optimized. However, related studies are insufficient so far. In this paper, the reverberation suppression performance according to the three hyperparameters of the NMF was analyzed by using sea experimental data. As a result of analysis, when the value of hyperparameters for time continuity and pulse length were high, the energy ratio between the reverberation and the target showed better performance at less than 0.4, but it was confirmed that there was variability depending on the ocean environment. It is expected that the analysis results in this paper will be utilized as a useful guideline for planning precise experiments for optimizing hyperparameters of NMF in the future.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.31-34
• /
• 2024

태양광 에너지는 탄소 중립 이행을 위한 주요 방안으로 많은 주목을 받고 있다. 태양광 발전량은 여러 환경적 요인에 따라 크게 달라질 수 있으므로, 정확한 발전량 예측은 전력 네트워크의 안정성과 효율적인 에너지 관리에 근본적으로 중요하다. 대표적인 인공지능 기술인 신경망(Neural Network)은 불안정한 환경 변수와 복잡한 상호작용을 효과적으로 학습할 수 있어 태양광 발전량 예측에서 우수한 성능을 도출하였다. 하지만, 신경망은 모델의 구조나 초매개변수(Hyperparameter)를 최적화하는 것은 복잡하고 시간이 많이 드는 작업이므로, 에너지 분야에서 실제 산업 적용에 한계가 존재한다. 본 논문은 2단계 신경망 최적화를 통한 태양광 발전량 예측 기법을 제안한다. 먼저, 태양광 발전량 데이터 셋을 훈련 집합과 평가 집합으로 분할한다. 훈련 집합에서, 각기 다른 은닉층의 개수로 구성된 여러 신경망 모델을 구성하고, 모델별로 Optuna를 적용하여 최적의 초매개변숫값을 선정한다. 다음으로, 은닉층별 최적화된 신경망 모델을 이용해 훈련과 평가 집합에서는 각각 5겹 교차검증을 적용한 발전량 추정값과 예측값을 출력한다. 마지막으로, 스태킹 앙상블 방식을 채택해 기본 초매개변숫값으로 설정해도 우수한 성능을 도출하는 랜덤 포레스트를 이용하여 추정값을 학습하고, 평가 집합의 예측값을 입력으로 받아 최종 태양광 발전량을 예측한다. 인천 지역으로 실험한 결과, 제안한 방식은 모델링이 간편할 뿐만 아니라 여러 신경망 모델보다 우수한 예측 성능을 도출하였으며, 이를 바탕으로 국내 에너지 산업에 이바지할 수 있을 것으로 기대한다.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Korean Chemical Engineering Research
• /
• v.59 no.4
• /
• pp.532-541
• /
• 2021

Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.143-143
• /
• 2023

최근 대청댐('17), 평림댐('19) 등 광역 취수원에서 망간의 먹는 물 수질기준(0.05mg/L 이하) 초과 사례가 발생되어, 다수의 민원이 제기되는 등 취수원의 망간 관리 중요성이 부각되고 있다. 특히, 동절기 전도(Turn-over)시기에 고농도 망간이 발생되는 경우가 많은데, 현재 정수장에서는 망간을 처리하기 위해 유입구간에 필터를 설치하고 주기적으로 교체하는 방식으로 처리하고 있다. 그러나 단기간에 고농도 망간 다량 유입 시 처리용량의 한계 등 정수장에서의 공정관리가 어려워지므로 사전 예측에 의한 대응 체계 고도화가 필요한 실정이다. 본 연구는 광역취수원인 주암댐을 대상으로 망간 예측의 정확도 향상 및 예측기간 확대를 위해 다양한 머신러닝 기법들을 적용하여 비교 분석하였으며, 독립변수 및 초매개변수 최적화를 진행하여 모형의 정확도를 개선하였다. 머신러닝 모형은 수심별 탁도, 저수위, pH, 수온, 전기전도도, DO, 클로로필-a, 기상, 수문 자료 등의 독립변수와 화순정수장에 유입된 망간 농도를 종속변수로 각 변수에 해당하는 실측치를 학습데이터로 사용하였다. 그리고 데이터기반 모형의 정확도를 개선하기 위해서 성층의 수준을 판별하는 지표로서 PEA(Potential Energy Anomaly)를 도입하여 데이터 분석에 활용하고자 하였다. 분석 결과, 망간 유입률은 계절 주기에 따라 농도가 달라지는 것을 확인하였고 동절기 전도시점과 하절기 장마기간 난류생성 시기에 저층의 고농도 망간이 유입이 되는 것을 분석하였다. 또한, 두 시기의 망간 농도의 변화 패턴이 상이하므로 예측 모델은 각 계절별로 구축해 학습을 진행함으로써 예측의 정확도를 향상할 수 있었다. 다양한 머신러닝 모델을 구축하여 성능 비교를 진행한 결과, 동절기에는 Gradient Boosting Machine, 하절기에는 eXtreme Gradient Boosting의 기법이 우수하여 추론 모델로 활용하고자 하였다. 선정 모델을 통한 단기 수질예측 결과, 전도현상 발생 시기에 대한 추종 및 예측력이 기존의 데이터 모형만 적용했을 경우대비 약 15% 이상 예측 효율이 향상된 것으로 나타났다. 본 연구는 머신러닝 모델을 활용한 망간 농도 예측으로 정수장의 신속한 대응 체계 마련을 지원하고, 수처리 공정의 효율성을 높이는 데 기여할 것으로 기대되며, 후속 연구로 과거 시계열 자료 활용 및 물리모형과의 연결 등을 통해 모델의 신뢰성을 제고 할 계획이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.846-849
• /
• 2020

하이퍼파라미터(초매개변수) 최적화란 모델의 학습에 앞서 미리 설정해야 하는 값인 하이퍼파라미터의 최적값을 탐색하는 문제이다. 이때의 최적값은 학습을 끝낸 모델의 성능을 가능한 최대치로 높이게 하는 값이다. 한편, 최근 모바일 장치를 이용한 포지셔닝 데이터의 대량 수집이 가능해지면서 이를 활용하여 위치 기반 서비스(Location-Based Service)를 위한 데이터 분석 및 예측에 관한 연구가 활발히 이루어졌다. 그중 이동 경로를 이미지로 패턴화하여 국소 지역 내에서 다음 위치를 예측하는 CNN 모델에 대해서 하이퍼파라미터 튜닝을 진행하였다. 결과적으로 베이지안 최적화(Bayesian Optimization)를 통해 모델의 성능을 평균 3.7%, 최대 9.5%까지 개선할 수 있음을 확인하였다.

• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.69-81
• /
• 2019

We consider bivariate long range dependent (LRD) time series forecasting using a deep learning method. A long short-term memory (LSTM) network well-suited to time series data is applied to forecast bivariate time series; in addition, we compare the forecasting performance with bivariate fractional autoregressive integrated moving average (FARIMA) models. Out-of-sample forecasting errors are compared with various performance measures for functional MRI (fMRI) data and daily realized volatility data. The results show a subtle difference in the predicted values of the FIVARMA model and VARFIMA model. LSTM is computationally demanding due to hyper-parameter selection, but is more stable and the forecasting performance is competitively good to that of parametric long range dependent time series models.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.147-170
• /
• 2022

Although the number of patent which is one of the core outputs of technological innovation continues to increase, the number of low-value patents also hugely increased. Therefore, efficient evaluation of patents has become important. Estimation of patent lifespan which represents private value of a patent, has been studied for a long time, but in most cases it relied on a linear model. Even if machine learning methods were used, interpretation or explanation of the relationship between explanatory variables and patent lifespan was insufficient. In this study, patent lifespan (number of renewals) is predicted based on the idea that patent lifespan represents the value of the patent. For the research, 4,033,414 patents applied between 1996 and 2017 and finally granted were collected from USPTO (US Patent and Trademark Office). To predict the patent lifespan, we use variables that can reflect the characteristics of the patent, the patent owner's characteristics, and the inventor's characteristics. We build four different models (Ridge Regression, Random Forest, Feed Forward Neural Network, Gradient Boosting Models) and perform hyperparameter tuning through 5-fold Cross Validation. Then, the performance of the generated models are evaluated, and the relative importance of predictors is also presented. In addition, based on the Gradient Boosting Model which have excellent performance, Accumulated Local Effects Plot is presented to visualize the relationship between predictors and patent lifespan. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the evaluation reason of individual patents, and discuss applicability to the patent evaluation system. This study has academic significance in that it cumulatively contributes to the existing patent life estimation research and supplements the limitations of existing patent life estimation studies based on linearity. It is academically meaningful that this study contributes cumulatively to the existing studies which estimate patent lifespan, and that it supplements the limitations of linear models. Also, it is practically meaningful to suggest a method for deriving the evaluation basis for individual patent value and examine the applicability to patent evaluation systems.