• Korean Journal of Agricultural Science
• /
• v.46 no.4
• /
• pp.843-856
• /
• 2019

Real-time flood prediction has an important role in significantly reducing potential damage caused by floods for urban residential areas located downstream of river basins. This paper presents an effective approach for flood forecasting based on the construction of a deep neural network (DNN) model. In addition, this research depends closely on the open-source software library, TensorFlow, which was developed by Google for machine and deep learning applications and research. The proposed model was applied to forecast the flowrate one, two, and three days in advance at the Son Tay hydrological station on the Red River, Vietnam. The input data of the model was a series of discharge data observed at five gauge stations on the Red River system, without requiring rainfall data, water levels and topographic characteristics. The research results indicate that the DNN model achieved a high performance for flood forecasting even though only a modest amount of data is required. When forecasting one and two days in advance, the Nash-Sutcliffe Efficiency (NSE) reached 0.993 and 0.938, respectively. The findings of this study suggest that the DNN model can be used to construct a real-time flood warning system on the Red River and for other river basins in Vietnam.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.147-147
• /
• 2018

In this article, we use an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The proposed model based on a deep neural network model, LSTM (Long Short-Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. For LSTM modeling, the input data is hourly water level data for 15 years from 2002 to 2016 at 4 stations includes 3 upstream stations (Sutong, Hotan, and Songcheon) and the forecasting-target station (Okcheon). The data are subdivided into three purposes: a training data set, a testing data set and a validation data set. The model was formulated to predict Okcheon Station water level for many cases from 3 hours to 12 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation, the prediction is very stable and reliable up to 9 hours of lead time with the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm. The result indicated that the method is able to produce the river water level time series and be applicable to the practical flood forecasting instead of hydrologic modeling approaches.

• Journal of the Korean Society of Systems Engineering
• /
• v.16 no.2
• /
• pp.38-46
• /
• 2020

The accurate measurement of critical heat flux (CHF) in flow boiling is important for the safety requirement of the nuclear power plant to prevent sharp degradation of the convective heat transfer between the surface of the fuel rod cladding and the reactor coolant. In this paper, a System Engineering approach is used to develop a model that predicts the CHF using machine learning. The model is built using artificial neural network (ANN). The model is then trained, tested and validated using pre-existing database for different flow conditions. The Talos library is used to tune the model by optimizing the hyper parameters and selecting the best network architecture. Once developed, the ANN model can predict the CHF based solely on a set of input parameters (pressure, mass flux, quality and hydraulic diameter) without resorting to any physics-based model. It is intended to use the developed model to predict the DNBR under a large break loss of coolant accident (LBLOCA) in APR1400. The System Engineering approach proved very helpful in facilitating the planning and management of the current work both efficiently and effectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.161-164
• /
• 2022

Homomorphic Encryption (HE) schemes have been recently growing as a reliable solution to preserve users' information owe to maintaining and operating the user data in the encrypted state. In addition to that, several Neural Networks models merged with HE schemes have been developed as a prospective tool for privacy-preserving machine learning. Those mentioned works demonstrated that it is possible to match the accuracy of non-encrypted models but there is always a trade-off in the computation time. In this work, we evaluate the implementation of CKKS HE scheme operations over the layers of a LeNet5 convolutional inference model, however, owing to the limitations of the evaluation environment, the scope of this work is not to develop a complete LeNet5 encrypted model. The evaluation was performed using the MNIST dataset with Microsoft SEAL (MSEAL) open-source homomorphic encryption library ported version on Python (PyFhel). The behavior of the encrypted model, the limitations faced and a small description of related and future work is also provided.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.55-64
• /
• 2021

Public libraries are a space where residents learn a wide range of knowledge and ideologies, and as they are directly connected to life, various related studies have been conducted. In most previous studies, variables such as population, traffic accessibility, and environment were found to be highly relevant to library use. In this study, it can be said that the difference from previous studies is that the book borrow demand and relevance were analyzed by reflecting the variables of cultural characteristics based on the book borrow history (1,820,407 cases) and member information (297,222 persons). As a result of the analysis, it was analyzed that as the increase in borrows for social science and literature books compared to technical science books, the demand for book borrows increased. In addition, various descriptive statistical analyzes were used to analyze the characteristics of library book borrow demand, and policy implications and limitations of the study were also presented based on the analysis results. and considering that cultural characteristics change depending on the location and time of day, it is believed that related research should be continued in the future.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.2
• /
• pp.25-44
• /
• 2021

In a situation where OA papers are increasing, POI, which indexes how open the research activities of individual researchers are, is drawing attention. This study investigated the existence of OA papers and the OA method published in international academic journals by domestic LIS researchers, and derived the researchers' POI based on this. In addition, by examining the relationship between the POI index and the researcher's amount of research papers, the research sub field, and the foreign co-authors, it was analyzed whether these factors are relevant to the researcher's POI. As a result, there were 492 papers by 82 researchers whose OA status and method were normally identified through Unpaywall. Second, only 20.7% of papers published in international journals were open accessed, and almost cases were gold and green methods. Third, there were many papers in text mining in medical journals, and the papers opened in the green method are open in institutional repositories of foreign co-authors or transnational subject repositories such as PMC. Third, the POI index was relatively higher for researchers in the field of informetrics, machine learning than other fields. In addition, it was analyzed that the presence or absence of overseas co-authors is related to OA.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.2
• /
• pp.305-332
• /
• 2022

This preliminary study examined the degree programs in data science at the School of Information in the States. The focus of this study was the data science degrees offered at the School of Information awarded by the 64 Library and Information Science (LIS) programs accredited by the American Library Association (ALA) in 2022. In addition, this study examined the degrees, majors, minors, specialized tracks, and certificates in data science, as well as the potential careers after earning a data science degree. Overall, eight Schools of Information (iSchools) offered 12 data science degrees. Data science courses at the School of Information focus on topics such as introduction to data science, information retrieval, data mining, database, data and humanities, machine learning, metadata, research methods, data analysis and visualization, internship/capstone, ethics and security, user, policy, and curation and management. Most schools did not offer traditional LIS courses. After earning the data science degree in the School of Information, the potential careers included data scientists, data engineers and data analysts. The researcher hopes the findings of this study can be used as a starting point to discuss the directions of data science programs from the perspectives of the information field, specifically the degrees, majors, minors, specialized tracks and certificates in data science.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.440-445
• /
• 2017

Due to the advance of e-commerce systems, the number of people using online shopping and products has significantly increased. Therefore, the need for an accurate recommendation system is becoming increasingly more important. Recurrent neural network is a deep-learning algorithm that utilizes sequential information in training. In this paper, an evaluation is performed on the application of recurrent neural networks to recommendation systems. We evaluated three recurrent algorithms (RNN, LSTM and GRU) and three optimal algorithms(Adagrad, RMSProp and Adam) which are commonly used. In the experiments, we used the TensorFlow open source library produced by Google and e-commerce session data from RecSys Challenge 2015. The results using the optimal hyperparameters found in this study are compared with those of RecSys Challenge 2015 participants.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.57-64
• /
• 2023

In this study, we analyzed how to steal the target model without training data. Input data is generated using the generative model, and a similar model is created by defining a loss function so that the predicted values of the target model and the similar model are close to each other. At this time, the target model has a process of learning so that the similar model is similar to it by gradient descent using the logit (logic) value of each class for the input data. The tensorflow machine learning library was used as an experimental environment, and CIFAR10 and SVHN were used as datasets. A similar model was created using the ResNet model as a target model. As a result of the experiment, it was found that the model stealing method generated a similar model with an accuracy of 86.18% for CIFAR10 and 96.02% for SVHN, producing similar predicted values to the target model. In addition, considerations on the model stealing method, military use, and limitations were also analyzed.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.45-55
• /
• 2020

Due to the development of information and communication technology, the number of new / variant malicious codes is increasing rapidly every year, and various types of malicious codes are spreading due to the development of Internet of things and cloud computing technology. In this paper, we propose a malware analysis method based on string information that can be used regardless of operating system environment and represents library call information related to malicious behavior. Attackers can easily create malware using existing code or by using automated authoring tools, and the generated malware operates in a similar way to existing malware. Since most of the strings that can be extracted from malicious code are composed of information closely related to malicious behavior, it is processed by weighting data features using text mining based method to extract them as effective features for malware analysis. Based on the processed data, a model is constructed using various machine learning algorithms to perform experiments on detection of malicious status and classification of malicious groups. Data has been compared and verified against all files used on Windows and Linux operating systems. The accuracy of malicious detection is about 93.5%, the accuracy of group classification is about 90%. The proposed technique has a wide range of applications because it is relatively simple, fast, and operating system independent as a single model because it is not necessary to build a model for each group when classifying malicious groups. In addition, since the string information is extracted through static analysis, it can be processed faster than the analysis method that directly executes the code.