• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1515-1521
• /
• 1996

Object-oriented and distributed processing methods are adopted next -generation telecommunications management architecture. In this paper, we design and implement gradual federation function on connection management system providing connection services to transport network for interworking and encapsulated trader and gateway function for testing interoperability of these service objects between distributed processing environments. These techniques are practically applicable to support interworking between heterogeneous management network systems according to a tendency of integrating telecommunications management systems.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.1
• /
• pp.59-64
• /
• 2016

This paper suggests heuristic algorithm with O(mn) polynomial time complexity using Excel for partially survivable networks optimization problem of cellular telecommunication systems with m cells and n hubs. This problem only can be get the solution using linear programming or LINGO software package. The proposed algorithm connects the cell to hubs in ring network with minimum cost as the connection diversity of each cell. If the traffic of ring network (T) is T>2K for ring capacity (K), we adjust the maximum cost hub to MTSO that has a ascending order of (D/DC)/${\Delta}^+$ cell with each cell traffic demand (D) and ${\Delta}^+$=(MTSO cost-maximum cost hub) than we get the $T{\leq}2K$. Finally, we adjust MTSO to the removed maximum cost hub for the cell with 2K-$T{\geq}$(D/DC) and $_{max}{\Delta}^-$. While we using like this simple method, the proposed algorithm can be get the same optimal solution for experimental data as linear programing and LINGO software package.

• The KIPS Transactions:PartC
• /
• v.13C no.1 s.104
• /
• pp.11-18
• /
• 2006

In the field of network defense, a lot of researches are directed toward locating the source of network attacks. When an intruder launches attack not from their own computer but from intermediate hosts that they previously compromised, and these intermediate hosts are called stepping-stones. There we two kinds of traceback technologies : IP packet traceback and connection traceback. We focused on connection traceback in this paper This paper classifies process structures of detoured attack type in stepping stone, designs an algorithm for traceback agent, and implements the traceback system based on the agent

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Management & Information Systems Review
• /
• v.30 no.3
• /
• pp.153-167
• /
• 2011

This study conducts to examine the effect of purchase intention on social shopping by connection density and centrality which is a structural characteristic of social network. Furthermore, this study suggests and analyses the difference of social shopping purchase intention between online community which focuses on a group and SNS(social network service) which focuses on an individual. To examine these reason, this study proposes hypotheses that reflects structural characteristic then analyses them. The result of analysis shows that the purchase intention on social shopping seems to be high when the density of connection is high and the purchase intention seems to be high when the centrality is high as well. Moreover, there is difference in the purchase intention on social shopping between online community and SNS and it is found that both cases where the connection density is high in the online community and the connection centrality is high in SNS have significant impact on the purchase intention. Based on these results, this study provides an implication on the importance on network structure in social network and social shopping and to increase the purchase intention of social shopping, this study suggests the implication on the importance and direction which understands the structure of social network type.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.635-639
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the modeling of chaotic nonlinear systems. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the modeling performance for chaotic nonlinear systems and compare it with those of the FNN and the WFM.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.1
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1421-1425
• /
• 1999

A restoration scheme is presented when a failure occurs at nodes or links on the ATM network. Each node on the network contains the same topology information for resources on the network by Exchanging NSE(Network State Element) which has the network state information through RCC(Routing Control Channel). We also propose a new establishing algorithm that set up a new alternate path reflecting the state of the network changed dynamically at the source node. In the result of applying our scheme, the rates of restoration can be improved and the number of messages decreased so that fast recovering could be possible by reducing traffics on the network by lowering the rates of the call-setup failure at the stage of CAC(Connection Admission Control).

• The KIPS Transactions:PartC
• /
• v.9C no.2
• /
• pp.227-234
• /
• 2002

MPLS which integrates routing of layer 3 and switching of layer 2, enables support for fast forwarding, traffic engineering and virtual private network services. GSMP is open interface protocol between a label switch and a controller, and it provides connection, configuration, event, performance management and synchronization. In the GSMP open interface, the functions of network management can be located either in the controller or in the label switch. To simplify the label switch and enhance the efficiency of resources, we adopt the network management model, in which the SNMP agent is located in the controller and is interworked with the GSMP. We presented the interworking scenrios between the GSMP and the network management of MPLS. We implemented the controller to verify the realization of our adopted network management model, and measured the connection setup delay of the provisioned connection.

• IE interfaces
• /
• v.18 no.3
• /
• pp.253-267
• /
• 2005

Customer satisfaction becomes one of the important managerial concerns associated with corporate competency in current competitive environment for Internet communication service companies. Hence, it is demanding to improve a company's customer satisfaction through the total quality management perspective. In practice, engineers as well as the management hope to find major quality characteristics with Internet communication network that is closely related to customer satisfaction, consequently aiming to the raise of their company's customer satisfaction. This paper presents an empirical relationship analysis between network quality characteristics and customer satisfaction on Internet communication. Methodologically, the relationship analysis framework is based on the regression variable selection procedures. In this framework, it is implemented that; 1) iterative model building; and 2) consistent criteria application to statistical tests for selecting significant variables. A case study shows that; 1) the customer satisfaction on the network connection seems to be more closely related to the network quality characteristics compared with the customer satisfaction on the network speed; and 2) the download disconnection rate has relatively evident relationship with the customer satisfaction on the network connection.