• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.11-18
• /
• 2023

In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained. Consequently, Informer has improved prediction accuracy compared with other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.67-75
• /
• 2023

In this paper, we analyze the problem of the user authentication scheme that provides dynamic ID in a multi-server environment proposed by Andola et al. and propose an improved authentication one to solve this problem. As a result of analyzing the authentication scheme of Andrea et al. in this paper, it is not safe for smart card loss attack, and this attack allows users to guess passwords, and eventually, the attacker was able to generate session key. This paper proposed an improved authentication scheme to solve these problems, and as a result of safety analysis, it was safe from various attacks such as smart card loss attack, password guess attack, and user impersonation attack. Also the improved authentication scheme not only provides a secure dynamic ID, but is also effective in terms of the computational complexity of the hash function. In addition, the improved authentication scheme does not significantly increase the amount of transmission, so it can be said to be an efficient authentication scheme in terms of transmission cost.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.503-508
• /
• 2023

Tryptane derivatives are substances that treat acute migraines, and many studies have been conducted on analysis methods such as chromatography, electrochemistry, spectroscopy, and capillary electrophysiology. Recently, analytical chemists have become more interested in drug analysis and solving fundamental problems of biological importance. Therefore, in this study, the chemical properties of each derivative were investigated by calculating the total energy, band gap, electrostatic potential, and charge of Sumatriptan, Lizatriptan, Naratriptan, and Eletriptan using HyperChem8.0's semi-empirical PM3 method. As a result of this study, in the case of Sumatriptan, Naratriptan, and Eletriptan, chemical reactions are expected to proceed centering on oxygen and nitrogen atoms bonded to sulfur atoms. In addition, in the case of Rizatriptan without a sulfur atom, it was shown that the chemical reaction proceeds at the 17th and 19th nitrogens of the 5-membered heterocyclic compound.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.639-647
• /
• 2023

A variety of communications are developed and advanced by integration of wireless and wire connections with heterogeneous system. Traditional technologies are mainly focus on information technology based on computer techniques in the field of industry, manufacture and automation fields. As new technologies are developed and enhanced with traditional techniques, a lot of new applications are emerged and merged with existing mechanism and skills. The representative applications are IoT(Internet of Things) services and applications. IoT is breakthrough technologies and one of the innovation industries which are called 4 generation industry revolution. Due to limited resources in IoT such as small memory, low power and computing power, IoT devices are vulnerable and disclosed with security problems. In this paper, we reviewed and analyzed security challenges, threats and requirements under IoT service.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.105-112
• /
• 2023

This study is an example of a Cinema Therapy class through the movie Life of Pi (2013). Cinema Therapy proceeds through the process of identification, empathy, projection, and observational learning through the cinema. Through research, students objectively examine the situation of the characters in the movie, identify themselves, and empathize with them. Students evaluate the situation of the character in the movie, and indirectly experience the hardships facing the character in the movie through the answer to "What would you do if I were the main character?" and think about what they would do. I admire the outstanding points of the main character and reflect on my life. Through this process, students examine the situation of their emotions and problems and specifically suggest ways to solve them. In the end, students' emotions can be fully healed through the movie. Healing through the cinema should start with the selection of the cinema in consideration of the healer's client. It is also necessary to sufficiently present a specific method of applying this. It is expected that the cinema healing plan will be able to develop further by presenting various healing methods in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.57-65
• /
• 2023

Various studies to enhance the accuracy of rice production forecasting are focused on improving the accuracy of the models. In contrast, there is a relative lack of research regarding the data itself, which the prediction models are applied to. When applying the same dependent variable and prediction model to two different sets of rice production data composed of distinct features, discrepancies in results can occur. It is challenging to determine which dataset yields superior results under such circumstances. To address this issue, by identifying potential influential features within the data before applying the prediction model and centering the modeling around these, it is possible to achieve stable prediction results regardless of the composition of the data. In this study, we propose a method to adjust the composition of the data's features in order to select optimal base variables, aiding in achieving stable and consistent predictions for rice production. This method makes use of the Korea Meteorological Administration's ASOS data. The findings of this study are expected to make a substantial contribution towards enhancing the utility of performance evaluations in future research endeavors.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.51-57
• /
• 2022

Recently, the concept of zero trust has been introduced, and it is necessary to strengthen the security elements required for the next-generation security control system. Also, the security paradigm in the era of the 4th industrial revolution is changing. Cloud computing and the cybersecurity problems caused by the dramatic changes in the work environment due to the corona 19 virus continue to occur. And at the same time, new cyber attack techniques are becoming more intelligent and advanced, so a future security control system is needed to strengthen security. Based on the core concept of doubting and trusting everything, Zero Trust Security increases security by monitoring all communications and allowing strict authentication and minimal access rights for access requesters. In this paper, we propose a security enhancement plan in the security control field through a zero trust security model that can understand the problems of the existing security control system and solve them.

• Convergence Security Journal
• /
• v.22 no.1
• /
• pp.39-54
• /
• 2022

Recently, the importance of collecting, analyzing, and real-time sharing of various cybersecurity data has emerged in order to effectively respond to intelligent and advanced cyber threats. To cope with this situation, Korea is making efforts to expand its cybersecurity data sharing system, but many private companies are unable to participate in the cybersecurity data sharing system due to a lack of budget and professionals to collect cybersecurity data. In order to solve such problems, this paper analyzes the research and development trends of existing domestic and foreign cyber security data sharing systems, and based on that, propose a cybersecurity data sharing system model with a hierarchical structure that considers the size of the organization and a step-by-step security policy that can be applied to the model. In the case of applying the model proposed in this paper, it is expected that various private companies can expand their participation in cybersecurity data sharing systems and use them to prepare a response system to respond quickly to intelligent security threats.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.

• Journal of the Korean Society for information Management
• /
• v.39 no.4
• /
• pp.241-268
• /
• 2022

Records related to a certain cultural heritage are concrete evidence that prove the value of the cultural heritage and become a criterion for long-term preservation of its records. The value of the records is as important as cultural heritage value. In the case of specific cultural heritage with national or socially important values, various studies are conducted on cultural heritage as one theme, and various programs about cultural heritage are developed. However, it is difficult to grasp the scope, record types, and contents of the records because they have been distributed and managed in many institutes. They also appear in various forms. As a solution to these problems, this study collected records of a major cultural heritage with social and historical values such as Hwangnyongsa from 11 public institutions and web services and analyzed the types of records, activities related to the records, and metadata. Through data analysis, an ontology that can understand the range and relationship of the entire record was suggested so that the record can be understood with a focus on specific cultural heritage.