• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.16-21
• /
• 2008

This paper introduces a new type of Hopfield neural network using newly developed single-electron devices. In the electrical model of the Hopfield neural network, a single-electron synapse, used as a voltage(or current)-variable resistor, and two stages of single-electron inverters, used as a nonlinear activation function, are simulated with a single-electron circuit simulator using Monte-Carlo method to verily their operation.

• The Korean Journal of Community Living Science
• /
• v.25 no.4
• /
• pp.511-531
• /
• 2014

This study explores supportive and conflictual network structures of elderly single and couple households and analyzes the effects of supportive and conflictual networks on suicidal thoughts by gender and family type. The analysis considered a sample of 522 individuals over the age of 60 who did not live with their adult children. The statistical methods used to analyze data were descriptive statistics, a t-test, a chi-square test and a regression analysis using SPSS WIN 20.0. The results are as follows. First, men and elderly single households had support networks that were smaller than those of women and elderly couple households. The conflictual network of elderly couples households was larger than that of elderly single households. In addition, the larger the network, the more the conflictual was. Second, elderly single households thought about suicide more often than elderly couple households. Third, economic status, the number of adult children, the size of conflictual network and subjective health had considerable influence on suicidal thoughts of elderly single and couple households. The size of the conflictual network had a greater effect on suicidal thoughts of elderly individuals than that of the supportive network. These results have important policy implications for elderly single and couple households.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.471-475
• /
• 2000

Voice and data are transmitted over a single packetized data communications network which is designed for data communications. The public switched telephone network for voice and the packet data network for data are merging into a single data network to get efficiency and to reduce operational cost. However, integrating voice and data transmission over a single data network is not easy because voice should be transmitted without delay but data should be transmitted without error. Advances in technology begin to overcome basic differences. Several integration methods in voice and data will be examined and reviewed here. Moreover, trends and problems on integration will be also discussed.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.131-135
• /
• 2009

This paper is the introduction of our work on distributed load scheduling in single-level tree network. In this paper, we derive a new calculation model in single-level tree network and show a closed-form formulation of the time for computation system. There are so many examples of the application of this technology such as distributed database, biology computation on genus, grid computing, numerical computing, video and audio signal processing, etc.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.9-17
• /
• 2021

In this paper, we propose a reversely using the "Man In The Middle Attack" attack technique as a way to introduce network security without changing the physical structure and configuration of the existing network, a Virtual Network Overlay is formed with only a single Ethernet Interface. Implementing In-line mode to protect the network from external attacks, we propose an integrated control method through a micro network security sensor and cloud service. As a result of the experiment, it was possible to implement a logical In-line mode by forming a Virtual Network Overlay with only a single Ethernet Interface, and to implement Network IDS/IPS, Anti-Virus, Network Access Control, Firewall, etc.,. It was possible to perform integrated monitor and control in the service. The proposed system in this paper is helpful for small and medium-sized enterprises that expect high-performance network security at low cost, and can provide a network security environment with safety and reliability in the field of IoT and embedded systems.

• Korean Journal of Social Welfare
• /
• v.61 no.4
• /
• pp.61-84
• /
• 2009

This study is to analyze the nature of mentoring network of single mothers with dependent children and to show the mentoring network effect on mentoring function and empowerment applying social network approach. 439 single mothers with dependent children in Busan and Gyeongsangnam-do have been surveyed about mentoring network properties. The results are 1. The mentoring relationships between single mothers have been shown in various size and relationship characters. The out-degree of Their network is low, the range is narrow, and the tie-strength is weak. 2. When the effect of mentoring network characteristics on mentoring function has been analyzed, in career functions, the range of network and the strength of relationships are represented as significant variables among the mentoring network characteristics, in psychosocial functions, the size of network and the strength of relationships are shown as significant variables, and the inverted-U-shaped relationship according to the size of network has not been revealed. In role modeling function only the size of network is represented as a significant variable. 3. The direct effect of mentoring network of single mothers with dependent children has not been much on empowerment and the career related function among mentoring functions has been revealed as the variable, which affect on empowerment. Based on these results the suggestions and implementations are mentioned in this paper.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.151-156
• /
• 2010

In this paper, several computer simulations are investigated to confirm the DVB-H system performance and to find proper single frequency network cell coverage. From the result, we confirm that 2K mode transmission is more robust to Doppler frequency than 8K mode. The result of this paper can be partially applied to the design the single frequency network.