• Journal of the Korean Society of Radiology
• /
• v.14 no.7
• /
• pp.991-1001
• /
• 2020

Supervised deep learning technologies for improving the image quality of computed tomography (CT) need a lot of training data. When input images have different characteristics with training images, the technologies cause structural distortion in output images. In this study, an imaging model based on the deep reinforcement learning (DRL) was developed for overcoming the drawbacks of the supervised deep learning technologies and reducing noise in CT images. The DRL model was consisted of shared, value and policy networks, and the networks included convolutional layers, rectified linear unit (ReLU), dilation factors and gate rotation unit (GRU) in order to extract noise features from CT images and improve the performance of the DRL model. Also, the quality of the CT images obtained by using the DRL model was compared to that obtained by using the supervised deep learning model. The results showed that the image accuracy for the DRL model was higher than that for the supervised deep learning model, and the image noise for the DRL model was smaller than that for the supervised deep learning model. Also, the DRL model reduced the noise of the CT images, which had different characteristics with training images. Therefore, the DRL model is able to reduce image noise as well as maintain the structural information of CT images.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.5
• /
• pp.109-119
• /
• 2004

The home network environment can be defined as a network environment, connecting digital home devices such as computer systems, digital appliances, and mobile devices. In this kind of home network environments, there will be numerous local/remote interactions to monitor and control the home network devices and the home gateway. Such an environment may result in communication bottleneck. By applying the mobile agents that can migrate among the computing devices autonomously and work on behalf of the user, remote interactions and network traffics can be reduced enormously. The mobile agent authentication is necessary to apply mobile agent concept to the home network environments, as a prerequisite technology for authorization or access control to the home network devices and resources. The existing mobile agent systems have mainly used the public key based authentication scheme, which is not suitable to the home network environments, composed of digital devices of limited computation capability. In this paper, we propose a shared key based mobile agent authentication scheme for single home domain and expand the scheme to multiple domain environments with the public key based authentication scheme. Application of the shared key encryption scheme to the single domain mobile agent authentication enables to authenticate the mobile agent with less overhead than the public key based authentication scheme.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.17 no.1
• /
• pp.11-20
• /
• 2007

A fast Montgomery multiplication occupies important to the design of RSA cryptosystem. Montgomery multiplication consists of two addition, which calculates using CSA or RBA. In terms of CSA, the multiplier is implemented using 4-2 CSA o. 5-2 CSA. In terms of RBA, the multiplier is designed based on redundant binary system. In [1], A new redundant binary adder that performs the addition between two binary signed-digit numbers and apply to Montgomery multiplier was proposed. In this paper, we reconstruct the logic structure of the RBA in [1] for reducing time and space complexity. Especially, the proposed RB multiplier has no coupler like the RBA in [1]. And the proposed RB multiplier is suited to binary exponentiation as modified input and output forms. We simulate to the proposed NRBA using gates provided from SAMSUNG STD130 $0.18{\mu}m$ 1.8V CMOS Standard Cell Library. The result is smaller by 18.5%, 6.3% and faster by 25.24%, 14% than 4-2 CSA, existing RBA, respectively. And Especially, the result is smaller by 44.3% and faster by 2.8% than the RBA in [1].

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.4
• /
• pp.33-41
• /
• 2006

RSA cryptosystem is of great use in systems such as IC card, mobile system, WPKI, electronic cash, SET, SSL and so on. RSA is performed through modular exponentiation. It is well known that the Montgomery multiplier is efficient in general. The critical path delay of the Montgomery multiplier depends on an addition of three operands, the problem that is taken over carry-propagation makes big influence at an efficiency of Montgomery Multiplier. Recently, the use of the Carry Save Adder(CSA) which has no carry propagation has worked McIvor et al. proposed a couple of Montgomery multiplication for an ideal exponentiation, the one and the other are made of 3 steps and 2 steps of CSA respectively. The latter one is more efficient than the first one in terms of the time complexity. In this paper, for faster operation than the latter one we use binary signed-digit(SD) number system which has no carry-propagation. We propose a new redundant binary adder(RBA) that performs the addition between two binary SD numbers and apply to Montgomery multiplier. Instead of the binary SD addition rule using in existing RBAs, we propose a new addition rule. And, we construct and simulate to the proposed adder using gates provided from SAMSUNG STD130 $0.18{\mu}m$ 1.8V CMOS Standard Cell Library. The result is faster by a minimum 12.46% in terms of the time complexity than McIvor's 2 method and existing RBAs.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.625-633
• /
• 2021

This paper describes a scalable architecture for flexible hardware implementation of Montgomery modular multiplication. Our scalable modular multiplier architecture, which is based on a one-dimensional array of processing elements (PEs), performs word parallel operation and allows us to adjust computational performance and hardware complexity depending on the number of PEs used, N_PE. Based on the proposed architecture, we designed a scalable Montgomery modular multiplier (sMM) core supporting eight field sizes defined in SEC2. Synthesized with 180-nm CMOS cell library, our sMM core was implemented with 38,317 gate equivalents (GEs) and 139,390 GEs for N_PE=1 and N_PE=8, respectively. When operating with a 100 MHz clock, it was evaluated that 256-bit modular multiplications of 0.57 million times/sec for N_PE=1 and 3.5 million times/sec for N_PE=8 can be computed. Our sMM core has the advantage of enabling an optimized implementation by determining the number of PEs to be used in consideration of computational performance and hardware resources required in application fields, and it can be used as an IP (intellectual property) in scalable hardware design of elliptic curve cryptography (ECC).

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.127-134
• /
• 2022

In this study, RCPTs (Rapid Chloride Penetration Test) were performed for fly ash concrete with curing age of 4 ~ 6 years. The concrete mixtures were prepared with 3 levels of water to binder ratio (0.37, 0.42, and 0.47) and 2 levels of substitution ratio of fly ash (0 and 30%), and the improved passed charges of chloride ion behavior were quantitatively analyzed. Additionally, the results were trained through the univariate time series models consisted of GRU (Gated Recurrent Unit) algorithm and those from the models were evaluated. As the result of the RCPT, fly ash concrete showed the reduced passed charges with period and an more improved resistance to chloride penetration than OPC concrete. At the final evaluation period (6 years), fly ash concrete showed 'Very low' grade in all W/B (water to binder) ratio, however OPC concrete showed 'Moderate' grade in the condition with the highest W/B ratio (0.47). The adopted algorithm of GRU for this study can analyze time series data and has the advantage like operation efficiency. The deep learning model with 4 hidden layers was designed, and it provided a reasonable prediction results of passed charge. The deep learning model from this study has a limitation of single consideration of a univariate time series characteristic, but it is in the developing process of providing various characteristics of concrete like strength and diffusion coefficient through additional studies.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.2
• /
• pp.15-26
• /
• 2021

Recently, as the introduction of cloud, mobile, and IoT has become active, there is a growing need for technology development that can supplement the limitations of traditional security solutions based on fixed perimeters such as firewalls and Network Access Control (NAC). In response to this, SDP (Software Defined Perimeter) has recently emerged as a new base technology. Unlike existing security technologies, SDP can sets security boundaries (install Gateway S/W) regardless of the location of the protected resources (servers, IoT gateways, etc.) and neutralize most of the network-based hacking attacks that are becoming increasingly sofiscated. In particular, SDP is regarded as a security technology suitable for the cloud and IoT fields. In this study, a new access control system was proposed by combining SDP and hash tree-based large-scale data high-speed signature technology. Through the process authentication function using large-scale data high-speed signature technology, it prevents the threat of unknown malware intruding into the endpoint in advance, and implements a kernel-level security technology that makes it impossible for user-level attacks during the backup and recovery of major data. As a result, endpoint security, which is a weak part of SDP, has been strengthened. The proposed system was developed as a prototype, and the performance test was completed through a test of an authorized testing agency (TTA V&V Test). The SDP-based access control solution is a technology with high potential that can be used in smart car security.

• 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.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.553-564
• /
• 2021

This study was conducted to understand the effects of participation perception, self-efficacy, self-esteem, and empowerment on self-support intention of self-support work project participants. For this study, a survey was conducted on participants in the self-support work project within the G-gu area. As a result of the study, it was found that the participation perception, self-efficacy, and empowerment of participants in the self-support project had a positive (+) effect on the self-support will. Also, in the process where participants' perceptions of participation, self-efficacy, and self-esteem affect the will to self-support, it was found that empowerment partially mediated participation perception and self-efficacy and fully mediated self-esteem. Based on these results, the following are practical suggestions for improving self-support project participants' will to self-support as follows. First, systematic training courses are needed in the application and selection of recipients, establishment of self-support plans, and gateway training courses so that participants in self-support projects can correctly recognize self-support projects. Second, it is necessary to systematize the case management system provided by the self-help center and re-establish the role in order to strengthen the participants' hope for self-reliance. Third, it is necessary to identify the strengths of the participants in the self-support project, create results for self-support, and operate a program that strengthens the latent motivation to solve their own problems and change their behavior. Fourth, the empowerment of participants and professional ability of practitioners should be strengthened so that participants can solve the alienation and social exclusion experienced in the process of participating in the project.