• Journal of the Korea Society for Simulation
• /
• v.30 no.4
• /
• pp.9-19
• /
• 2021

Electronic voting has been recognized as an alternative to complement the limitations of existing paper voting. At the same time, security concerns are being raised. This paper presents a blockchain-based electronic voting and survey system that can guarantee reliability. Our smart contract was created using Solidity on Ethereum which is a blockchain-based distributed computing platform, and the system was implemented in connection with the Javascript based user interface. In addition, in order to protect the personal information of participants, the system is generating hash of the personal data and storing the hash of users for the contract data. Since we exploited different kinds of languages for the system, we derived items of functionality testing and presented the functionality testing result. Moreover, we made use of the Chrome's performance evaluation functionality to see the response time of the blockchain-based system. In addition, we compared the performance with the system which has the same functionality on database. The contribution of this research is design and implementation of blockchain-based electronic voting system and presentation of the functionality and performance simulation result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.319-325
• /
• 2021

With the advancement of wireless technology and the rapid growth of the infrastructure of mobile communication technology, systems applying AI-based platforms are drawing attention from users. In particular, the system that understands users' tastes and interests and recommends preferred items is applied to advanced e-commerce customized services and smart homes. However, there is a problem that these recommendation systems are difficult to reflect in real time the preferences of various users for tastes and interests. In this research, we propose a Fuzzy-AHP-based movies recommendation system using the Gated Recurrent Unit (GRU) language model to address a problem. In this system, we apply Fuzzy-AHP to reflect users' tastes or interests in real time. We also apply GRU language model-based models to analyze the public interest and the content of the film to recommend movies similar to the user's preferred factors. To validate the performance of this recommendation system, we measured the suitability of the learning model using scraping data used in the learning module, and measured the rate of learning performance by comparing the Long Short-Term Memory (LSTM) language model with the learning time per epoch. The results show that the average cross-validation index of the learning model in this work is suitable at 94.8% and that the learning performance rate outperforms the LSTM language model.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.2
• /
• pp.83-107
• /
• 2022

The local bookstore direct loan service for users' requests in public libraries, which was launched in Gyeonggi Province, is a creative new service that has led to the revitalization of the local economy through the rise in sales of local bookstores and high user satisfaction. However, it is a service in which positive and negative reactions coexist as negative opinions are presented on the deterioration of the quality of public library books due to overlapping needs for desired books by users. Therefore, several ways of improving for local bookstore loan service in public libraries through a survey of public libraries, local bookstores, and users were suggested in this study. The local bookstore direct loan service for users' requests, which is a creative cooperation plan between public libraries and local bookstores, needs to constantly improve its services by increasing book purchase cost, organizing a steering committee for continuous communication and collecting plans through research on the book purchase cost. Also, it is necessary to improve its services by enacting regulations expanding reading culture services expanding the number of healthy users and fostering various local bookstores.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.337-345
• /
• 2022

For data such as rainfall and soil moisture, it is important to obtain the values of all points required as geostatistical data. Spatial interpolation is generally performed in this process, and commercial software such as ArcGIS is often used. However, commercial software has fatal drawbacks due to its high expertise and cost. In this study, R, an open source-based environment with ArcGIS, a commercial software, was used to compare the differences according to the processing environment when performing spatial interpolation. The data for spatial interpolation was weather forecast data calculated through Land-Atmosphere Modeling Package (LAMP)-WRF model, and soil moisture data calculated for each cumulative rainfall scenario. There was no difference in the output value in the two environments, but there was a difference in user interface and calculation time. The results of spatial interpolation work in the test bed showed that the average time required for R was 5 hours and 1 minute, and for ArcGIS, the average time required was 4 hours and 40 minutes, respectively, showing a difference of 7.5%. The results of this study are meaningful in that researchers can derive the same results in a commercial software environment and an open source-based environment, and can choose according to the researcher's environment and level.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.4
• /
• pp.151-174
• /
• 2022

Archival descriptions are significant in utilizing archives, as they are important tools for archival research and use. Meanwhile, content services are key services in modern society, where the use of archives and the importance of content are increasing. In this study, archival descriptions and content services were not viewed as different areas but as a relationship that could advance complementarily. This is because if archival descriptions are rich and well-prepared, high-quality content can be produced based on them, and archival descriptions can be enriched if well-made content is supplemented or linked to the descriptions again. This study intends to reveal the complementary relationship between archival descriptions and content services and propose an advancement plan based on this relationship. As such, the current status and problems of the archival descriptions and content services of the National Archives of Korea and the Presidential Archives website were analyzed, and the UK's National Archives (TNA), the USA's National Archives and Records Administration (NARA), the Seoul Metropolitan Archives, and the Korea Democracy Foundation's Open Archives were selected as exemplary cases for comparison. Based on the implications of the six analyzed institutions, an advancement plan for archival descriptions and content services, as well as a complementary development plan, was proposed. Through this study, it is expected that archival descriptions and content services will develop in a mutually complementary direction.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.869-877
• /
• 2022

This study aims to analyze the factors affecting the re-subscription period upon initial termination of the reverse mortgage subscription. The study utilized the Korea Housing Finance Corporation's database to extract the information regarding re-subscribers of the reverse mortgage from July 2007 to June 2021. The ordered logit model was employed and found that a set of user (subscriber) characteristics are influential towards the re-subscription period. Among the individual characteristics, changes in age group, marital status from married to single-living, maintaining single-living, and the initial subscription period were found statistically significant, highlighting that the increase in the initial subscription period decreased the re-subscription period. Among the housing (home equity) characteristics, changes in housing price and ownership type (single and partial ownership) were statistically significant, indicating that the change in ownership type decreases the re-subscription period. Lastly, the variables related to loan terms were found significant, revealing that changes in payout method and schedule were both increasing factors of the re-subscription period. Based on the findings, necessary policy implications can be considered to secure the returning subscribers of the reverse mortgage effectively.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.31-38
• /
• 2022

An electrocardiogram(ECG) is a recoding of electrical signals of the heart's cyclic activity and an important body information for diagnosing myocardial rhythm. Large amount of information are generated continuously and a significant period of cumulative signal is required for the purpose of diagnosing a specific disease. Therefore, research on compression including clinically acceptable lossy technique has been developed to reduce the amount of information significantly. Recently, wearable smart heart monitoring devices that can transmit electrocardiogram(ECG) are being developed. The use of electrocardiogram, an important personal information for healthcare service, is rapidly increasing. However, devices generally have limited capability and power consumption for user convenience, and it is often difficult to apply the existing compression method directly. It is essential to develop techniques that can process and transmit a large volume of signals in limited resources. A method for compressing and transmitting the ECG signals efficiently by using the cumulative average (template) of the unit waveform is proposed in the paper. The ECG is coded lovelessly using template matching. It is analyzed that the proposed method is superior to the existing compression methods at high compression ratio, and its complexity is not relatively high. And it is also possible to apply compression methods to template matching values.

• Knowledge Management Research
• /
• v.23 no.3
• /
• pp.259-284
• /
• 2022

In order to help the understanding of web novel users, this study was intended to quantitatively verify the user's behavioral types according to the characteristics of web novels. For this purpose, the direction of the study proceeded as follows. First, the motives of web novel users were investigated by referring to the motives of other digital content users. In addition, specific behavioral types of users were also collected. As a result, the motivation for using web novels was found to be 'interpersonal relationships and information acquisition with others', 'leisure activities', and 'escape from reality/relieve tension'. After that, the groups were classified as to whether there was a difference between groups according to the motives of use. As a result, the 'hobbies' type, a group with a particularly high motivation for using leisure activities, the 'stress relief' type, a group with very high escapism and tension relief characteristics, and a group with high interpersonal relationships and information acquisition with others The 'communication' type was classified as a 'multipurpose' type with high overall motivation characteristics. Then, in order to find out the specific characteristics between the types, personas were constructed based on the different behavior type data. Through this, the theoretical contribution of this study is meaningful in that it revealed the motives of web novel users. As a practical contribution, the persona was formed by combining the users' motives and behavioral patterns and visualized to be close to the actual representative users. These results are expected to help improve the web novel service by providing useful indicators for actual writers, platform managers, and users.