• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.67-73
• /
• 2023

Tree routing is one of appropriate routing schemes in wireless sensor network because the complexity of this approach is relatively low. But, congestion at a specific node may happen because a parent node toward a sink node is usually selected in one hop way, specially where large number of node are deployed. As feasible solution for this problem, multiple paths and sinks schemes can be applied. However, the performance of these schemes are not proved and analyzed yet. In this paper, we conduct diverse simulaton scenarios performance evaluation for these cases to identify the improvement and analyze the impact of schemes. The performance is measured in the aspects of packet transmission rate, throughput, and end-to-end delay as a function of amount of network traffic.

• 전기의세계
• /
• v.23 no.3
• /
• pp.43-52
• /
• 1974

The matrix inversion is very inefficient for computing direct solutions of the large spare systems of linear equations that arise in many network problems as a large electrical power system. Optimally ordered triangular factorization of sparse matrices is more efficient and offers the other important computational advantages in some applications with this method. The direct solutions are computed from sparse matrix factors instead of a full inverse matrix, thereby gaining a significant advantage is speed and computer memory requirements. In this paper, it is shown that the sparse matrix method is superior to the inverse matrix method to solve the linear equations of large sparse networks. In addition, it is shown that the sparse matrix method is superior to the inverse matrix method to solve the linear equations of large sparse networks. In addition, it is shown that the solutions may be applied directly to sove the load flow in an electrical power system. The result of this study should lead to many aplications including short circuit, transient stability, network reduction, reactive optimization and others.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1320-1329
• /
• 2022

Currently, advanced national research network groups are continuously conducting R&D for the requirement to provide SDN/NFV-based network automation and intelligence technology for R&E users. In addition, the requirement for providing large-scale data transmission with the high performance networking facility, compared to general network environments, is gradually increasing in the advanced national research networks. Accordingly, in this paper, we propose an open API-based virtual network provisioning automation platform for large data transmission researched and developed to respond to the networking requirements of the national research network and present the implementation results. The platform includes the KREONET-S VDN system that provides SDN-based network virtualization technology, and the Kubernetes system that provides container-oriented server virtualization technology, and the Globus Online, a high-performance data transmission system. In this paper, the environment configurations, the system implemetation results for the interworking between the heterogeneous systems, and the automated virtual network provisioning implementation results are presented.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3602-3620
• /
• 2016

Dynamic topology is one of the main influence factors on network performability. However, it was always ignored by the traditional network performability assessment methods when analyzing large-scale mobile ad hoc networks (MANETs) because of the state explosion problem. In this paper, we address this problem from the perspective of complex network. A two-layer hierarchical modeling approach is proposed for MANETs performability assessment, which can take both the dynamic topology and multi-state nodes into consideration. The lower level is described by Markov reward chains (MRC) to capture the multiple states of the nodes. The upper level is modeled as a small-world network to capture the characteristic path length based on different mobility and propagation models. The hierarchical model can promote the MRC of nodes into a state matrix of the whole network, which can avoid the state explosion in large-scale networks assessment from the perspective of complex network. Through the contrast experiments with OPNET simulation based on specific cases, the method proposed in this paper shows satisfactory performance on accuracy and efficiency.

• Human Ecology Research
• /
• v.51 no.5
• /
• pp.473-481
• /
• 2013

The purpose of this study was to investigate the moderating effects of a size of the friendship network and quality of friendship on the associations between mutual antipathy and maladjustment. The subjects were 678 fifth- and sixth-grade primary school children who were recruited from a public school in Bucheon City. The Peer Nomination Inventory was used to assess mutual antipathy, peer victimization, social withdrawal, aggression, and the friendship network. The children were given a classroom roster and asked to nominate up to three classmates who fit each description. Additionally, the children reported the quality of their friendships using the Friendship Quality Scale. Each child was asked to indicate his or her one best friend and rate how accurately a sentence describe done of their best friends on the scale. The results revealed that the friendship network and friendship quality significantly moderated the relationships between mutual antipathy and social withdrawal, and peer victimization. The magnitude of the association between mutual antipathy and social withdrawal was not significant for large friendship networks and high quality friendships. Although mutual antipathy was significantly associated with peer victimization, the association was stronger at lower levels than at higher levels of the friendship network and quality. However, there was no moderating effect of the friendship network and quality on the association between mutual antipathy and aggression. A large friendship network and high quality friendship could be protective factors among those who have mutual antipathy in peer groups.

• Journal of the Korean Society of Industry Convergence
• /
• v.14 no.3
• /
• pp.121-125
• /
• 2011

EMTP-RV is the very powerful program to analyze the dynamic operation of the power system. To use this package in the large complex power system, it is very important to simplify the power system to simple equivalent network. In our study the 100 MVA STATCOM is placed at 345kV "MIGUM" which is the one of the 345kV substations of the Korean Electric Power System that is consist of more than 1000-bus. MIGUM substation is connected with 7 separated transmission lines to main Korean Electric power system. We developed a new method to simplify the network except the substation that we want to analysis. The power system outside the 345kV substation is modeled into the equivalent network. The loop network outside the substation can be modeled to simplified Thevenin equivalent network. The proposed method is applied to IEEE-14 Reliability Test System and the results shows the effectiveness of the method.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.614-621
• /
• 2018

This paper proposes a method of restoring corrupted depth image captured by depth camera through unsupervised learning using generative adversarial network (GAN). The proposed method generates restored face depth images using 3D morphable model convolutional neural network (3DMM CNN) with large-scale CelebFaces Attribute (CelebA) and FaceWarehouse dataset for training deep convolutional generative adversarial network (DCGAN). The generator and discriminator equip with Wasserstein distance for loss function by utilizing minimax game. Then the DCGAN restore the loss of captured facial depth images by performing another learning procedure using trained generator and new loss function.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.12 no.3
• /
• pp.267-275
• /
• 1987

This paper concerns a study on the theory of tearing which analyzes a large scale network by partitioning it into a number of small subnetworks by cutting through some of the existing nodes and branches in the network. By considering of the relationship its voltage and current of node cutting before and after, the consititutive equations of tearing method is equvalent to renumbering the nodes of untorn network equations. Therefore the analysis of network is conveniently applied as same algorithm that is used in untorn network. Also the proposed nodal admittnace matrix is put in block diagonal form, therefore this method permit parallel processing analysis of subnetworks. 30 nodes network was tested and the effectiveness of the proposed algorithm was proved.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.57-64
• /
• 2018

In recent years, a new approach to cyber security, called the moving target defense, has emerged as a potential solution to the challenge of static systems. In this paper, we design a protected server network with a large number of decoys to anonymize the protected servers that dynamically mutate their IP address and port numbers according to Hidden Tunnel Networking, which is a network-based moving target defense scheme. In the network, a protected server is one-to-one mapped to a decoy-bed that generates a number of decoys, and the decoys share the same IP address pool with the protected server. First, the protected server network supports mutating the IP address and port numbers of the protected server very frequently regardless of the number of decoys. Second, it provides independence of the decoy-bed configuration. Third, it allows the protected servers to freely change their IP address pool. Lastly, it can reduce the possibility that an attacker will reuse the discovered attributes of a protected server in previous scanning. We believe that applying Hidden Tunnel Networking to protected servers in the proposed network can significantly reduce the probability of the protected servers being identified and compromised by attackers through deploying a large number of decoys.