• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.441-448
• /
• 2019

Previous researches on automatic spacing of Korean sentences has been researched to correct spacing errors by using n-gram based statistical techniques or morpheme analyzer to insert blanks in the word boundary. In this paper, we propose an end-to-end automatic word spacing by using deep neural network. Automatic word spacing problem could be defined as a tag classification problem in unit of syllable other than word. For contextual representation between syllables, Bi-LSTM encodes the dependency relationship between syllables into a fixed-length vector of continuous vector space using forward and backward LSTM cell. In order to conduct automatic word spacing of Korean sentences, after a fixed-length contextual vector by Bi-LSTM is classified into auto-spacing tag(B or I), the blank is inserted in the front of B tag. For tag classification method, we compose three types of classification neural networks. One is feedforward neural network, another is neural network language model and the other is linear-chain CRF. To compare our models, we measure the performance of automatic word spacing depending on the three of classification networks. linear-chain CRF of them used as classification neural network shows better performance than other models. We used KCC150 corpus as a training and testing data.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.1
• /
• pp.37-44
• /
• 2015

In traditional social network analysis, the betweenness centrality measure has been heavily used to identify the relative importance of nodes. Since the time complexity to calculate the betweenness centrality is very high, however, it is difficult to get it of each node in large-scale social network where there are so many nodes and edges. In our past study, we defined a new type of network, called the expanded ego network, which is built only with each node's local information, i.e., neighbor information of the node's neighbor nodes, and also defined a new measure, called the expanded ego betweenness centrality. In this paper, We propose algorithm that quickly computes expanded ego betweenness centrality by exploiting structural properties of expanded ego network. Through the experiment with virtual network used Barab$\acute{a}$si-Albert network model to represent the generic social network and facebook network to represent actual social network, We show that the node's importance rank based on the expanded ego betweenness centrality has high similarity with that the node's importance rank based on the existing betweenness centrality. We also show that the proposed algorithm computes the expanded ego betweenness centrality quickly than existing algorithm.

• Journal of Internet Computing and Services
• /
• v.12 no.1
• /
• pp.55-70
• /
• 2011

In this paper, we propose a policy-driven RFID data management event definition language, which is possibly applicable as a partial standard for SSI (Software System Infrastructure) Part 4 (Application Interface, 24791-4) defined by ISO/IEC JTC 1/SC 31/WG 4 (RFID for Item Management). The SSI's RFID application interface part is originally defined for providing a unified interface of the RFID middleware functionality―data management, device management, device interface and security functions. However, the current specifications are too circumstantial to be understood by the application developers who used to lack the professional and technological backgrounds of the RFID middleware functionality. As an impeccable solution, we use the concept of event-constraint policy that is not only representing semantic contents of RFID domains but also providing transparencies with higher level abstractions to RFID applications, and that is able to provide a means of specifying event-constraints for filtering a huge number of raw data caught from the associated RF readers. Conclusively, we try to embody the proposed concept by newly defining an XML-based RFID event policy definition language, which is abbreviated to rXPDL. Additionally, we expect that the specification of rXPDL proposed in the paper becomes a technological basis for the domestic as well as the international standards that are able to be extensively applied to RFID and ubiquitous sensor networks.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.401-407
• /
• 2019

SDN(Softeware Defined Networking) has emerged to address the rapidly growing demand for cloud computing and to support network virtualization services. Therefor many companies and organizations have taken SDN as a next-generation network technology. However, unlike the wired network where the SDN is originally designed, the SDN in the wireless network has a restriction that it can not provide the mobility of the node. In this paper, we extended existing openflow protocol of SDN and developed SDN-based network platform, which enables the SDN controller to manage the radio resources of its network and support the mobility of the nodes. The mobility support function of this paper has the advantage that a node in the network can move using its two or more wireless interfaces by using the radio resource management function of the SDN controller. In order to test the functions implemented in this paper, we measured parameters related to various transmission performance according to various mobile experiments, and compared parameters related to performance using one wireless interface and two interfaces. The SDN-based network platform proposed in this paper is expected to be able to monitor the resources of wireless networks and support the mobility of nodes in the SDN environment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.10
• /
• pp.89-100
• /
• 2007

Consumer Portal is defined as "a combination of hardware and software that enables two-way communication between energy service provider(ESP, like KEPCO) and equipment within the consumer's premises". The portal provides both a physical link(between wires, radio waves, and other media) and a logical link(translating among language-like codes and etiquette-like protocols) between in-building and wide-area access networks. Thus, the consumer portal is an important, open public shared infrastructure in the future vision of energy services. In this paper, we describe a new methodology for local communication and computer network capacity design of consumer portal, and also presents capacity calculation method using a network system limitation factors. By the approach, we can check into the limitations of existing methods, and propose an improved data processing algorithm that can expand the maximum number of the networked end-use devices up to $30{\sim}40$ times. For validation, we applies the proposed methode to our real system design. Our contribution will help electrical power information network design.

• Smart Media Journal
• /
• v.4 no.4
• /
• pp.24-32
• /
• 2015

Recently, SDN is actively used as datacenter networks and gradually increase its applied areas. Along with this change of networking environment, research of deploying network security systems on SDN becomes highlighted. Especially, systems for detecting network flooding attacks by monitoring every packets through ports of OpenFlow switches have been proposed. However, because of the centralized management of a SDN controller which manage multiple switches, it may be substantial overhead that the attack detection system continuously monitors all the flows. In this paper, a sampling based network flooding attack detection and prevention system is proposed to reduce the overhead of monitoring packets and to achieve reasonable functionality of attack detection and prevention. The proposed system periodically takes sample packets of network flows with the given sampling conditions, analyzes the sampled packets to detect network flooding attacks, and block the attack flows actively by managing the flow entries in OpenFlow switches. As network traffic sampler, sFlow agent is used, and snort, an opensource IDS, is used to detect network flooding attack from the sampled packets. For active prevention of the detected attacks, an OpenDaylight application is developed and applied. The proposed system is evaluated on the local testbed composed with multiple OVSes (Open Virtual Switch), and the performance and overhead of the proposed system under various sampling condition is analyzed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.523-529
• /
• 2020

Power distribution management system is essential for the efficient management and operation of power distribution networks. The power distribution system is a system that manages the distribution network based on IT, and has been evolving along with the development of the power industry. The current power distribution system is designed to operate at a relatively low network transmission speed based on the independent operation of the main equipment. However, due to distributed resources such as photovoltaic or energy storage devices, which are rapidly increasing in popularity in recent years, the operation of future distribution environments is becoming more complex, and various information needs to be collected in real time. In this study, the requirements of the next-generation power distribution system were derived to overcome the limitations of the existing power distribution system, and based on this, the communication network system and performance requirements for the distribution system were defined. In order to verify the performance of the designed system, a software-based terminal device simulator was developed because it takes excessive time and cost to introduce a large-scale system such as a power distribution system. Using the simulator, a test environment similar to the actual operation was established, and the number of terminal devices was increased up to 1,000. The proposed system was shown to satisfy the requirements to support the functions of the next-generation power distribution system, recording less than 10 % of the communication network bandwidth.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.7-20
• /
• 2017

The advancement of cloud and big data and the considerable growth of traffic have increased the complexity and problems in the management inefficiency of existing networks. The software-defined networking (SDN) environment has been developed to solve this problem. SDN enables us to control network equipment through programming by separating the transmission and control functions of the equipment. Accordingly, several studies have been conducted to improve the performance of SDN controllers, such as the method of connecting existing legacy equipment with SDN, the packet management method for efficient data communication, and the method of distributing controller load in a centralized architecture. However, there is insufficient research on the control of SDN in terms of the quality of network-using applications. To support the establishment and change of the routing paths that meet the required network service quality, we require a mechanism to identify network requirements based on a contract for application network service quality and to collect information about the current network status and identify the violations of network service quality. This study proposes a method of identifying the quality violations of network paths through ontology to ensure the network service quality of applications and provide efficient services in an SDN environment.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.