• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1707-1720
• /
• 2023

With the increase in satellite time series data, the utility of remote sensing data is growing. In the analysis of time series data, the relative positional accuracy between images has a significant impact on the results, making image registration essential for correction. In recent years, research on image registration has been increasing by applying deep learning, which outperforms existing image registration algorithms. To train deep learning-based registration models, a large number of image pairs are required. Additionally, creating a correlation map between the data of existing deep learning models and applying additional computations to extract registration points is inefficient. To overcome these drawbacks, this study developed a data augmentation technique for training image registration models and applied it to OffsetNet, a registration model that predicts the offset amount itself, to perform image registration for KOMSAT-2, -3, and -3A. The results of the model training showed that OffsetNet accurately predicted the offset amount for the test data, enabling effective registration of the master and slave images.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.38-44
• /
• 2020

Due to the high dependence on electric energy, electric fires make up a significant portion of fires in Korea. Electric arcs by short circuits or poor contact cause three of four electrical fires. An electric arc is a discharge phenomenon of electrical current between the insulators, which instantaneously produces high temperature. In order to reduce the fire due to electric arc, this study aims to predict the electric arc risk. We collected arc data from the arc detectors and converted into graphs based on temporal arc data. We used machine learning for training converted graph with different number of temporal arc data. To measure the performance of the learning model, we use the test data. In the results, when the number of temporal arc data was 20, the prediction rate was high as 86%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.52-56
• /
• 2004

The Information of classification and estimate about KOSPI200 index`s up and down in the stock market becomes an important standard of decision-making in designing portofolio in futures and option market. Because the coming trend of time series patterns, an economic indicator, is very subordinate to the most recent economic pattern, it is necessary to study the recent patterns most preferentially. This paper compares classification and estimated performance of SVM(Support Vector Machine) and Fuzzy SVM model that are getting into the spotlight in time series analyses, neural net models and various fields. Specially, it proves that Fuzzy SVM is superior by presenting the most suitable dimension to fuzzy membership function that has time series attribute in accordance with learning Data Base.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.225-230
• /
• 2021

The purpose of this study is to understand the mediating effect of grit in the relationship between academic achievement satisfaction and Academic Engagement of middle school students. To this end, a survey was conducted on 575 middle school students in Changwon, Gyeongsangnam-do, on academic achievement satisfaction, Academic Engagement, and grit. This research was carried out by hierarchical regression analysis was conducted to understand the correlation analysis and mediating effect between major variables, and The significance of the mediating effect was verified by the Sobel test. As a result of the study, First, correlation analysis revealed a positive correlation between academic achievement satisfaction, grit, and Academic Engagement. Second, regression analysis showed that both consistency of interest and perseverance of effort were partially mediated between academic achievement satisfaction and Academic Engagement. This means that academic achievement satisfaction not only directly affects middle school students' Academic Engagement, but also has an indirect effect through grit. Finally, In order to increase the academic enthusiasm of middle school students, learning counseling plans such as education and counseling plans to improve academic interest and develop various learning motivation improvement programs were discussed.

• Journal of the Korea Society for Simulation
• /
• v.30 no.4
• /
• pp.1-8
• /
• 2021

Deep learning is one of the most widely accepted methods for the forecasting of time series data which have the complexity and non-linear behavior. In this paper, we investigate the modification of a state-of-art WaveNet deep learning architecture and walk forward validation (WFV) in order to forecast electric power consumption data 24-hour-ahead. WaveNet originally designed for raw audio uses 1D dilated causal convolution for long-term information. First of all, we propose a modified version of WaveNet which activates real numbers instead of coded integers. Second, this paper provides with the training process with tuning of major hyper-parameters (i.e., input length, batch size, number of WaveNet blocks, dilation rates, and learning rate scheduler). Finally, performance evaluation results show that the prediction methodology based on WFV performs better than on the traditional holdout validation.

• 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.

• Korean Journal of Cognitive Science
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2007

In a goal-oriented dialogue, speakers' intentions can be represented by domain actions that consist of pairs of a speech act and a concept sequence. Therefore, if we plan to implement an intelligent dialogue system, it is very important to correctly infer the domain actions from surface utterances. In this paper, we propose a statistical model to determine speech acts and concept sequences using conditional random fields at the same time. To avoid biased learning problems, the proposed model uses low-level linguistic features such as lexicals and parts-of-speech. Then, it filters out uninformative features using the chi-square statistic. In the experiments in a schedule arrangement domain, the proposed system showed good performances (the precision of 93.0% on speech act classification and the precision of 90.2% on concept sequence classification).

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.100-106
• /
• 2014

URI spotting (탐지) 문제는 텍스트에 있는 단어열 중에서 URI로 대표되는 개체(entity)에 해당되는 것을 탐지하는 것이다. 이 문제는 두 개의 작은 문제를 순차적으로 해결하는 과제이다. 즉, 첫째는 어느 단어열이 URI에 해당하는 개체인가를 인식하는 것이고, 둘째는 개체 중의성 해소 문제로서 파악된 개체가 복수의 URI에 해당할 수 있는 의미적 모호성이 있을 때 그 URI중 하나를 선택하여 모호성을 해소하는 것이다. 이 논문은 디비피디아 URI를 대상으로 한다. URI 탐지 문제는 개체명 인식 문제와 비슷하나, URI(예를 들어 디비피디아 URI, 즉 Wikipedia 등재어)에 매핑될 수 있는 개체로 한정되므로 일반적인 개체명 인식 문제에서 단어열의 품사열이 기계학습의 자질로 들어가는 방법론과는 다른 자질을 사용할 수 있다. 이 논문에서는 한국어 텍스트를 대상으로 한국어 디비피디아 URI 탐지문제로서 SVM을 이용한 개체경계 인식 방법을 제시하여, 일반적 개체명 인식에서 나타나는 품사태거의 오류파급효과를 없애고자 한다. 또한 개체중의성 해소 문제는 의미모호성이 주변 문장들의 토픽에 따라 달라지므로, LDA를 활용하며 이를 영어 디비피디아 URI탐지에서 쓰인 방법들과 비교한다.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.217-224
• /
• 2022

Since online shopping has become common, people can easily buy fashion goods anytime, anywhere. Therefore, consumers quickly respond to various environmental variables such as weather and sales prices. Therefore, utilizing big data for efficient inventory management has become very important in the fashion industry. In this paper, the changes in sales volume of fashion goods due to changes in temperature is analyzed via the proposed big data analysis algorithm by utilizing actual big data from Korean fashion company 'A'. According to the simulation results, it was confirmed that Bidirectional-LSTM(Bi-LSTM) compared to LSTM(Long Short-Term Memory) takes more simulation time about more than 50%, but the prediction accuracy of non-periodic time series data such as clothing product sales data is the same.