• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.491-501
• /
• 2019

In side-channel analysis, which exploit physical leakage from a cryptographic device, deep learning based attack has been significantly interested in recent years. However, most of the state-of-the-art methods have been focused on classifying side-channel information in a profiled scenario where attackers can obtain label of training data. In this paper, we propose a new method based on deep learning to improve non-profiling side-channel attack such as Differential Power Analysis and Correlation Power Analysis. The proposed method is a signal preprocessing technique that reduces the noise in a trace by modifying Auto-Encoder framework to the context of side-channel analysis. Previous work on Denoising Auto-Encoder was trained through randomly added noise by an attacker. In this paper, the proposed model trains Auto-Encoder through the noise from real data using the noise-reduced-label. Also, the proposed method permits to perform non-profiled attack by training only a single neural network. We validate the performance of the noise reduction of the proposed method on real traces collected from ChipWhisperer board. We demonstrate that the proposed method outperforms classic preprocessing methods such as Principal Component Analysis and Linear Discriminant Analysis.

• The Korean Journal of Archival Studies
• /
• no.56
• /
• pp.81-112
• /
• 2018

Government publications at public institutions are data that are intended to convey the purpose of an institution or the performance of its business to the public or inside the institution. The management of government publications has become increasingly important under the framework of laws and systems, but matters concerning the nature and value of government publications have not been carried out at records management sites. The Act focused on the archives of the six metropolitan government, and presented issues and improvement measures for efficient management of government publications. To that end, the government should maintain a consistent payment system for publications. As payment method and payment book data in government publications are presented differently by law, a system for integrated management should be established to provide brief information and original information. Second, it is necessary to establish an administrative system that meets the storage environment. The publication registration and payment book system presented by the government's publication guidelines is the central system of the National Archives and Records Service, so it is not an efficient system in the agency archives. Third, support should be provided to recognize the value of government publications and to preserve and manage them in the long term. To dispose of the government publications, a realistic classification method, integrated and controlled program should be presented, and criteria for users using the service should be provided. Fourth, it is the establishment of an integrated management system for government publications. The National Archives Service, the National Central Library, and the National Assembly Library should simultaneously build an abstract of information and original information so that they can be managed systematically and efficiently.

• Korean Journal of Applied Biomechanics
• /
• v.29 no.3
• /
• pp.157-166
• /
• 2019

Objective: This study examined the effects of stimulating fingertip temperature on the patterns of force sharing and stability properties during multi-finger force production tasks. Method: 9 adult subjects (male: 3, female: 6, age: $26.11{\pm}4.01yrs$, height: $169.22{\pm}5.97cm$, weight: $61.44{\pm}11.27kg$) participated in this study. The experiment consisted of three blocks: 1) maximal voluntary contraction (MVC) task, 2) single-finger ramp task to quantify enslaving (i.e., unintended force production by non-task fingers), and 3) 12 trials of multi-finger steady-state force production task at 20% MVC. There were three temperature conditions including body-temperature (i.e., control condition), $40^{\circ}C$, and $43^{\circ}C$, and the stimulation was given to the index finger only for all experimental conditions. Results: There were no significant differences in the MVC forces, enslaving, and the accuracy of performance during the steady-state task between the conditions. However, the share of stimulated index finger force increased with the index fingertip temperature, while the share of middle finger force decreased. Also, the coefficient of variation of both index and middle finger forces over repetitive trials increased with the index fingertip temperature. Under the framework of the uncontrolled manifold (UCM) hypothesis used to quantify indices of multi-finger synergies (i.e., stability property) stabilizing total force during the steady-state task, the two variance components within the UCM analysis increased together with the fingertip temperature, while no changes in the synergy indices between the conditions. Conclusion: The current results showed that fingertip temperature stimulation only to index finger does not affect to muscle force production capability of multi-finger, independence of individual fingers, and force production accuracy by the involvement of all four fingers. The effect of fingertip temperature on the sharing pattern and force variation may be due to diffuse reflex effects of the induced afferent activity on alpha-motoneuronal pools. However, the unchanged stability properties may be the reflection of the active error compensation strategies by non-stimulated finger actions.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.21-29
• /
• 2018

In the era of the 4-th industrial revolution, the concept of smart factory is emerging. There are efforts to predict the occurrences of facility errors which have negative effects on the utilization and productivity by using data analysis. Data composed of the situation of a facility error and the type of the error, called the facility error log, is required for the prediction. However, in many manufacturing companies, the types of facility error are not precisely defined and categorized. The worker who operates the facilities writes the type of facility error in the form with unstructured text based on his or her empirical judgement. That makes it impossible to analyze data. Therefore, this paper proposes a framework for constructing a phrase network to support the identification and classification of facility error types by using facility error logs written by operators. Specifically, phrase indicating the types are extracted from text data by using dictionary which classifies terms by their usage. Then, a phrase network is constructed by calculating the similarity between the extracted phrase. The performance of the proposed method was evaluated by using real-world facility error logs. It is expected that the proposed method will contribute to the accurate identification of error types and to the prediction of facility errors.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.89-100
• /
• 2021

The National Cyber Capability Assessment(NCCA) could be used as meaningful information for improving national cyber security policy because it provides information on the elements necessary for strengthening national cyber capabilities and the level of each country. However, there were few studies on improving cyber capabilities using the NCCA result in Korea. Therefore, we analyzed the result of National Cyber Power Index(NCPI) conducted by Belfer Center of Harvard Univ. by applying modified-IPA method to derive cybersecurity policy agendas for Korea. As a result, the need to set agendas on surveillance and offensive cyber capability and improve the effectiveness of policy implementation for intelligence and defense was drawn. Moreover, we suggested need for in-depth study of each policy agenda deduced from preceding research data as a future tasks. And it is expected to increase practical use of NCCA for domestic policy analysis by developing and using our own NCCA model which considered analysis framework proposed in this study.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.59-67
• /
• 2022

In this study, the monthly airborne chlorides flying into the offshore bridges were investigated depending on the sea level. The target structures were 9 bridges located on the western and southern coast of South Korea. The airborne chlorides were measured at different sea levels on each bridge every month during 1 year. The results showed that the strongest seasonal wind from the northwest in winter expecially have led increase of the airborne chlorides, and its effect was more significant in the western coast than the southern coast. It was also found that the airborne chlorides declined with the increase of sea level. Three types of curves were suggested for analyzing the decrease trend with the sea level, based on the airborne chlorides at the lowest measurement height of main tower. The trend was varied depending on the sea area, and even in the same sea area, the local topographic condition affected the airborne chlorides. It means that the location and local topography should be considered simultaneously for durability management in the framework of the chloride source, and then the influence of the chloride source should be classified, e.g. safe and dangerous. From these results, it is expected that it could be used as baseline data for the evaluation of the deterioration environment in the Detailed guidelines for safety and maintenance of facilities [Performance evaluation]_Bridge.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.325-335
• /
• 2021

Chronic diseases have been increasing recently as the average life expectancy of humans has been extended, and this trend has caused problems such as the widespread demand for health and rehabilitation services and rising medical costs. In order to solve this problem, the community-based rehabilitation has been developed and strengthened in Korea and gradually promoted since 2019. It is important to secure access to clients who want to use services to revitalize community-based rehabilitation. So in this study, as part of the community-based rehabilitation, intends to devise smartphone applications designs and develop a prototype to secure access to community-based occupational therapy services based on occupation and activities. For Occupational Therapy Practice Framework (OTPF), International Classification of Functioning, Disability and Health (ICF), and Allen Diagnostic Module-2 (ADM-2) were used to devise and categorize occupation and activity based application content, and link OTPF, ICF, and ADM-2 through prior research analysis and expert meetings. The derived content was visualized through literature review and activity analysis, and was implemented to enable direct playback within the application using the YouTube API, and finally developed a prototype application. The Android Studio 3.5.2 for Windows 64-bit was used to build the application prototype. In further research, converging various digital technologies for user convenience and additionally researching community-based occupational therapy service providers opinions and service user satisfaction will improve accessibility to community-based occupational therapy services for clients who have difficulty occupational performance in the community.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.2
• /
• pp.11-20
• /
• 2021

The purpose of this study is to propose a documentary plan for the 7th Gyeongbuk Intangible Cultural Property, Andong-Notdaribapgi. Most of the records of Andong-Notdaribapgi. are produced centering on play. Thus this study aims to the method of recording it so that it can be accessed and utilized in the long term. This is a study at the beginning stage for documenting the Andong-Notdaribapgi. First of all, at the stage of the basic framework, the concept and characteristics of the recording of the Andong-Notdaribapgi were derived, and the meaning and necessity of recording was raised. In addition, the entire category of records was set through the analysis of the behavior process of Andong-Notdaribapgi, and the occurrence records and the contents of the records were organized focusing on the behavior processes occurring in various forms through the analysis of the recording target. In addition, materials that can be used are organized by focusing on the details and contents, including related records, and records that can be produced in the course of action are organized by type characteristics. Lastly, record analysis was based on performance behavior, and management functions were organized based on producers. The management of the records is to make it easier for users with various purposes to access the Intangible Cultural Property, the Andong-Notdaribapgi, and it is expected that it will provide directions and guidelines that can be applied to the recording plan in fields with similar characteristics.