• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.378-390
• /
• 2022

With the recent development of deep composite multiplication neural network learning, deep learning techniques applied to single-image super-resolution have shown good results, and the strong expression ability of deep networks has enabled complex nonlinear mapping between low-resolution and high-resolution images. However, there are limitations in applying it to real-time or low-power devices with increasing parameters and computational amounts due to excessive use of composite multiplication neural networks. This paper uses blocks that extract hierarchical characteristics little by little using information distillation and suggests the Recursive Distillation Super Resolution Network (RDSRN), a lightweight network that improves performance by making more accurate high frequency components through high frequency residual purification blocks. It was confirmed that the proposed network restores images of similar quality compared to RDN, restores images 3.5 times faster with about 32 times fewer parameters and about 10 times less computation, and produces 0.16 dB better performance with about 2.2 times less parameters and 1.8 times faster processing time than the existing lightweight network CARN.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.361-368
• /
• 2010

It is general that mostly congested sections of national backbone networks have been improved based on the national network expansion plan. However, in case of intermodal terminals which are origins of logistics, it is still so congested that travel time between origin and destination is long. Therefore, intermodal transportation systems plan of major intermodal terminals for the intermodal connector networks between intermodal terminal and national backbone network or intermodal terminal was established. With the limitation of priority methodology applying to intermodal connector facility under existing methodology, this study suggests an improved priority methodology. This study includes characteristics of terminal on the hierarchical structure and assessment list, but it does not concentrate on the specific terminal type through survey. To avoid a certain concentration, budget constraint for each terminal type was considered ahead of priority. Finally priority methodology was developed with two-step assessment under consideration that specific terminal is not involved in intermodal connector facility project. As a result of calculating weights by survey, effects such as d/c and accessibility fluctuations index through project implementation gain high weight, and degree of region underdevelopment gets next. Although the methodology in this study could not yields the priority by assessment list, it will be useful for setting the direction on policy related to intermodal connector facility projects.

• The Korean Journal of Community Living Science
• /
• v.27 no.4
• /
• pp.831-850
• /
• 2016

The ratio of suicide among the elderly in Korea has nearly tripled within the last 20 years. With this in mind, this study examined the effects of social exclusion on depression and suicidal ideation among the elderly living in elderly-only households with a focus on gender differences. Social exclusion is composed of economic, health, housing, education, social participation, and relational aspects. For this study, data were gathered from 527 participants aged 65 years and over. The statistical methods used for data analysis were descriptive statistics, chi-square test, t-test, and hierarchical regression analysis with the SPSS Win 20.0 program. The results of this study are summarized as follows: First, more than 80% of the elderly experienced social exclusion. Women were shown to be more vulnerable than men in terms of housing exclusion, educational exclusion, health exclusion, and multiple exclusion, whereas men were more vulnerable than women in terms of social participation exclusion. Second, social exclusion had significant effects on suicidal ideation among the Korean elderly. We also observed gender differences in the results. Regression analysis of suicidal ideation showed that relational exclusion had a significant effect on suicidal ideation in men, whereas health exclusion had a significant effect on suicidal ideation in women. Results of the study show that stronger social support networks and policies focusing on the elderly are needed in order to reduce elderly suicide in Korea.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1431-1439
• /
• 2016

In this paper, we propose a new location service and location-based routing for data dissemination from a source to a mobile group sink in less energy consumption of the sensor node. Unlike the existing protocols, the proposed protocol uses a leader sink instead of a group area as the location information to represent a mobile sink group. The proposed protocol also uses grid leaders on virtual grid structure to support sink mobility in location service. By using a leader sink as a representative and grid leaders for mobility supporting, the proposed protocol can exploit an efficient hierarchical location service and data dissemination method without using flooding. Accordingly, the proposed protocol carries out upper layer location services and data dissemination between a leader sink and a source and lower layer location services and data dissemination between the leader sink and member sinks. Simulation results demonstrate that the proposed protocol achieves energy-efficiency.

• Journal of Korea Multimedia Society
• /
• v.8 no.3
• /
• pp.372-378
• /
• 2005

When a mobile node changes a sub network using Mobile IP, it must register its current location to the home agent. If a mobile node is far from its home network, the Binding Update (BU) time delay is longer and affects its connection state. To solve such a BU delay problem, a new component in HMIPv6, called MAP, supports the mobility of mobile node to reduce the signaling delay in handover However, in hierarchical MAP architecture, the register concentration to a specific MAP may be occurred, which affects the network management wholly. In this paper, we propose a MAP selection scheme based on ioad balancing by the mobility factor and the traffic property. By the mobility factor and the traffic property, a mobile node can select a adequate MAP on its mobility factor and traffic characteristic.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.5
• /
• pp.942-948
• /
• 2016

WSN based on wireless sensor nodes, Sensor nodes can not be reassigned and recharged if they once placed. Each sensor node comes into being involved to a communication network with its limited energy. But the existing proposed clustering techniques, being applied to WSN environment with irregular dispersion of sensor nodes, have the network reliability issues which bring about a communication interruption with the local node feature of unbalanced distribution in WSN. Therefore, the communications participation of the sensor nodes in the suggested algorithm is extended by 25% as the sensor field divided in the light of the non-uniformed distribution of sensor nodes and a static or a dynamic clustering algorithm adopted according to its partition of sensor node density in WSN. And the entire network life cycle was extended by 14% to ensure the reliability of the network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.1
• /
• pp.67-74
• /
• 2009

This paper presents a method of improving the service availability by distributing the traffic of voice/data calls over the multi-layer cells in a mobile communication network. The traffic model is described and the call handling performance is analyzed. In our method, a fast moving call is moved to and serviced in the upper layer cell. A call is also moved upward when an overflow occurs. But unlike other methods, the call that is moved upward in the overflow case is the one which has the longest sojourn time in the cell. Moreover, when the call that was moved upward due to overflow condition stays longer than a certain period of time in the upper layer cell, the system moves the call back to the lower layer in order to save the more expensive resources of the upper layer cell. Call handling performance of this method evaluated from M/M/C/K models shows clear improvement with respect to call blocking probability and forced termination probability.

• The KIPS Transactions:PartB
• /
• v.18B no.2
• /
• pp.67-72
• /
• 2011

Single nucleotide polymorphisms (SNPs) are a very important tool for the study of human genome structure. Cluster analysis of the large amount of gene expression data is useful for identifying biologically relevant groups of genes and for generating networks of gene-gene interactions. In this paper we compared the clusters of SNPs within asthma group and normal control group obtained by using hierarchical cluster analysis method with entropy distance. It appears that the 5-cluster collections of the two groups are significantly different. We searched the best set of SNPs that are useful for diagnosing the two types of asthma using representative SNPs of the clusters of the asthma group. Here support vector machines are used to evaluate the prediction accuracy of the selected combinations. The best combination model turns out to be the five-locus SNPs including one on the gene ALOX12 and their accuracy in predicting aspirin tolerant asthma disease risk among asthmatic patients is 66.41%.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1643-1656
• /
• 2010

It is necessary to develop a system to judge inferiority of goods to minimize the loss at small factories in which produces various kinds of goods with small amounts. That system can be developed based on HTM theory. HTM is a model to apply the operation principles of the neocortex in human brain to the machine learning. We have to build the trained HTM network to use the HTM-based machine learning system. It requires the knowledge for the HTM theory. This paper presents the design and implementation of the training system to support the development of HTM networks which recognize the molding parts to judge its badness. This training system allows field technicians to train the HTM network with high accuracy without the knowledge of the HTM theory. It also can be applied to any kind of the HTM-based judging systems for molding parts.

• Journal of Advanced Navigation Technology
• /
• v.13 no.4
• /
• pp.551-558
• /
• 2009

Most of clustering schemes focusing on the energy efficiency have only a cluster head in each cluster, thus the energy consumption of cluster head in a cluster can rapidly increase. To reduce the energy consumption, recently, the dual-layered clustering which is separated a cluster ranges into two parts, i.e., data aggregation layer and data transmission layer, based on a sensor equipped with geographical positioning system (GPS), was proposed. However, the logical regions existing within the dual-layered clustering range can not distinguish efficiently. This scheme leads to many messages collision and transmission delay among member nodes. In this paper, to solve these problems, we propose a separated dual-layered routing scheme using the position information and the cluster radius. Proposed scheme clearly distinguish the dual-layered clustering range and gets the balanced number of member nodes in each cluster. Therefore, the proposed routing scheme could prolong the overall network life time about 10% compared to the previous two layered clustering scheme and LEACH.