• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• 대한조선학회논문집
• /
• 제58권5호
• /
• pp.281-293
• /
• 2021

Oil and steel prices, which are major pricescosts in the shipbuilding industry, were predicted. Firstly, the error of the moving average line (N=3-5) was examined, and in all three error analyses, the moving average line (N=3) was small. Secondly, in the linear prediction of data through existing theory, oil prices rise slightly, and steel prices rise sharply, but in reality, linear prediction using existing data was not satisfactory. Thirdly, we identified the limitations of linear prediction methods and confirmed that oil and steel price prediction was somewhat similar to actual moving average line prediction methods. Due to the high volatility of major price flows, large errors were inevitable in the forecast section. Through the time series analysis method at the end of this paper, we were able to achieve not bad results in all analysis items relative to artificial intelligence (Prophet). Predictive data through predictive analysis using eight predictive models are expected to serve as a good research foundation for developing unique tools or establishing evaluation systems in the future. This study compares the basic settings of artificial intelligence programs with the results of core price prediction in the shipbuilding industry through time series prediction theory, and further studies the various hyper-parameters and event effects of Prophet in the future, leaving room for improvement of predictability.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.251-258
• /
• 2023

안정적으로 전력을 공급하고 전력계통을 운영하기 위해서는 최대전력을 정확히 예측해야 한다. 특히, 최대전력이 높게 발생하는 겨울과 여름에는 그 중요성이 매우 커진다. 최대전력을 실제 수요보다 높게 예측하면 발전소 기동 비용이 증가하여 경제적 손실이 발생하고, 최대전력을 실제 수요보다 낮게 예측하면 기동이 가능한 발전소가 부족하여 정전이 발생할 수 있다. 최대전력의 예측 오차를 최소화함으로써 경제적 손실과 정전을 예방할 수 있다. 본 논문에서는 최대전력 예측의 오차를 최소화하기 위하여 최신 딥러닝 모델인 TCN을 이용한다. 딥러닝 모델은 하이퍼 파라미터를 어떻게 설정하느냐에 따라 성능 차이가 발생하므로, TCN의 하이퍼 파라미터를 최적화하는 방법을 제안한다. 2006년부터 2021년까지의 데이터를 입력하여 모델을 훈련하고, 2022년의 데이터를 이용하여 예측 오차를 실험하였다. 실험을 수행한 결과 본 논문에서 제안한 최적화 방법을 이용한 TCN 모델의 성능이 다른 딥러닝 모델보다 성능이 우수한 것을 확인하였다.

• 한국산학기술학회논문지
• /
• 제10권4호
• /
• pp.736-739
• /
• 2009

영상 내의 움직임 적응적인 효과적인 무손실 영상 압축 알고리즘을 제안한다. 이 알고리즘은 비선형 예측기를 토대로 움직임에 적응하는 단계와, 예측기에 의한 차분 데이터를 압축하는 단계로 구성된다. 제안한 비선형 예측기는 과거의 예측 오차로부터 화면간 혹은 화면내 예측치를 선택하며, 움직임 적응 단계를 진행되면서 주변 화소들의 예측 오차를 고려하여, 현재 화소에 대한 예측 오차를 줄이는 능력을 가진다. 예측 오차는 기존의 문맥 적응적인 코딩 기법에 의해서 압축된다. 실험결과는 제안한 알고리즘이 FELICS, CALC, JPEG-LS와 같은 문맥 모델링에 기반을 둔 무손실 압축 기법보다 우수한 압축률을 보여준다.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1997년도 춘계학술대회논문집
• /
• pp.56-60
• /
• 1997

The study of human erroneous actions has traditionally taken place along two different lines of approach. One has been concerned with finding and explaining the causes of erroneous actions, such as studies in the psychology of "error". The other has been concerned with the qualitative and quantitative prediction of possible erroneous actions, exemplified by the field of human reliability analysis (HRA). Another distinction is also that the former approach has been dominated by an academic point of view, hence emphasising theories, models, and experiments, while the latter has been of a more pragmatic nature, hence putting greater emphasis on data and methods. We have been developing a method to make predictions about error modes. The input to the method is a detailed task description of a set of scenarios for an experiment. This description is then analysed to characterise thd nature of the individual task steps, as well as the conditions under which they must be carried out. The task steps are expressed in terms of a predefined set of cognitive activity types. Following that each task step is examined in terms of a systematic classification of possible error modes and the likely error modes are identified. This effectively constitutes a qualitative analysis of the possibilities for erroneous action in a given task. In order to evaluate the accuracy of the predictions, the data from a large scale experiment were analysed. The experiment used the full-scale nuclear power plant simulator in the Halden Man-Machine Systems Laboratory (HAMMLAB) and used six crews of systematic performance observations by experts using a pre-defined task description, as well as audio and video recordings. The purpose of the analysis was to determine how well the predictions matiched the actually observed performance failures. The results indicated a very acceptable rate of accuracy. The emphasis in this experiment has been to develop a practical method for qualitative performance prediction, i.e., a method that did not require too many resources or specialised human factors knowledge. If such methods are to become practical tools, it is important that they are valid, reliable, and robust.

• 한국해양공학회지
• /
• 제37권4호
• /
• pp.145-157
• /
• 2023

Due to a recent increase in maritime activities in South Korea, the frequency of maritime distress is escalating and poses a significant threat to lives and property. The aim of this study was to validate a drift trajectory prediction technique to help mitigate the damages caused by maritime distress incidents. In this study, OpenDrift was verified using satellite drifter data from the Korea Hydrographic and Oceanographic Agency. OpenDrift is a Monte-Carlo-based Lagrangian trajectory modeling framework that allows for considering leeway, an important factor in predicting the movement of floating marine objects. The simulation results showed no significant differences in the performance of drift trajectory prediction when considering leeway using four evaluation methods (normalized cumulative Lagrangian separation, root mean squared error, mean absolute error, and Euclidean distance). However, leeway improved the performance in an analysis of location prediction conformance for maritime search and rescue operations. Therefore, the findings of this study suggest that it is important to consider leeway in drift trajectory prediction for effective maritime search and rescue operations. The results could help with future research on drift trajectory prediction of various floating objects, including marine debris, satellite drifters, and sea ice.

• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.1053-1063
• /
• 2017

Power prediction is critical to improve power efficiency in Smart Grids. Markov chain provides a useful tool for power prediction. With careful investigation of practical power datasets, we find an interesting phenomenon that the stochastic property of practical power datasets does not follow the Markov features. This mismatch affects the prediction accuracy if directly using Markov prediction methods. In this paper, we innovatively propose a spatial transform based data processing to alleviate this inconsistency. Furthermore, we propose an enhanced power prediction method, named by Spatial Mapping Markov-Difference (SMMD), to guarantee the prediction accuracy. In particular, SMMD adopts a second prediction adjustment based on the differential data to reduce the stochastic error. Experimental results validate that the proposed SMMD achieves an improvement in terms of the prediction accuracy with respect to state-of-the-art solutions.

• Journal of the Korean Data and Information Science Society
• /
• 제23권6호
• /
• pp.1241-1247
• /
• 2012

The paper considers empirical Bayes (EB) and hierarchical Bayes (HB) predictors of the finite population mean under a linear regression model with measurement errors We discuss how to calculate the mean squared prediction errors of the EB predictors using jackknife methods and the posterior standard deviations of the HB predictors based on the Markov Chain Monte Carlo methods. A simulation study is provided to illustrate the results of the preceding sections and compare the performances of the proposed procedures.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.983-984
• /
• 2008

This paper proposes a variable break that can offset prediction error as well as a pre-selection methods, based on the variable break, for enhanced unit selection. In Japanese, a sentence consists of several APs (Accentual phrases) and MPs (Major phrases), and the breaks between these phrases must predicted to realize text-to-speech systems. An MP also consists of several APs and plays a decisive role in making synthetic speech natural and understandable because short pauses appear at its boundary. The variable break is defined as a break that is able to change easily from an AP to an MP boundary, or from an MP to an AP boundary. Using CART (Classification and Regression Trees), the variable break is modeled stochastically, and then we pre-select candidate units in the unit-selection process. As the experimental results show, it was possible to complement a break prediction error and improve the naturalness of synthetic speech.

• 전자공학회논문지S
• /
• 제34S권9호
• /
• pp.91-98
• /
• 1997

In this paper, a new pixel decimation algorithm for the estimation of motion vector is proposed. In traditional methods, the computational cost can be reduced since only part of the pixels are used for motion vector calculation. But these methods limits the accuracy ofmotion vector because of the same reason. We derive a selection criteria of subsampled pixels that can reduce the probablity of false motion vector detection based on stochastic point of view. By using this criteria, a new pixel decimation algorithm that can reduce the prediction error with similar computational cost is presented. The simulation results applied to standard images haveshown that the proposed algorithm has less mean absolute prediction error than conventional pixel decimation algorithm.