• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Journal of Communications and Networks
• /
• v.14 no.4
• /
• pp.374-384
• /
• 2012

Utilizing artificial noise (AN) is a good means to guarantee security against eavesdropping in a multi-inputmulti-output system, where the AN is designed to lie in the null space of the legitimate receiver's channel direction information (CDI). However, imperfect CDI will lead to noise leakage at the legitimate receiver and cause significant loss in the achievable secrecy rate. In this paper, we consider a delayed feedback system, and investigate the impact of delayed CDI on security by using a transmit beamforming and AN scheme. By exploiting the Gauss-Markov fading spectrum to model the feedback delay, we derive a closed-form expression of the upper bound on the secrecy rate loss, where $N_t$ = 2. For a moderate number of antennas where $N_t$ > 2, two special cases, based on the first-order statistics of the noise leakage and large number theory, are explored to approximate the respective upper bounds. In addition, to maintain a constant signal-to-interferenceplus-noise ratio degradation, we analyze the corresponding delay constraint. Furthermore, based on the obtained closed-form expression of the lower bound on the achievable secrecy rate, we investigate an optimal power allocation strategy between the information signal and the AN. The analytical and numerical results obtained based on first-order statistics can be regarded as a good approximation of the capacity that can be achieved at the legitimate receiver with a certain number of antennas, $N_t$. In addition, for a given delay, we show that optimal power allocation is not sensitive to the number of antennas in a high signal-to-noise ratio regime. The simulation results further indicate that the achievable secrecy rate with optimal power allocation can be improved significantly as compared to that with fixed power allocation. In addition, as the delay increases, the ratio of power allocated to the AN should be decreased to reduce the secrecy rate degradation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5B
• /
• pp.385-394
• /
• 2012

The tactical mobile communication network, which comprises a part of the next-generation Tactical Information and Communication Network (TICN), provides means of communication and control for Tactical Multi-Functional Terminals (TMFT) belonging to a Mobile Subscriber Access Point (MSAP). The next-generation of MSAP is capable of constructing a backbone network via LCTR and HCTR directional antennas. At the same time, WMN modules are used to create and manage a wireless mesh backbone. When directional antennas are used in mobile environments, seamless services cannot be efficiently supported as the movement of the node prevents the angle of the antenna to constantly match. Therefore, data communication through the wireless mesh networks is required to provide direct communication between mobile MSAPs. Accordingly, mutual authentication and data encryption mechanisms are required to provide reliable data transmission in this environment. To provide efficient mutual authentication between MSAP devices, the process of verifying a certificate of the other MSAP device through its own authentication server is required. This paper proposes mutual authentication mechanisms where the MSAP requiring authentication and the MSAP that permits it initiates low-cost and efficient authentication in a distributed way. More specifically, we propose a method of applying EAP-ELS (Extensible Authentication Protocol-Transport Layer Security) in the next-generation TICN.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.29-38
• /
• 2019

With the advancement of information and communication technology, tactical networks are continuously being converted to All-IP future tactical networks that integrate all application services based on Internet protocol. Futuristic tactical mesh network is built with tactical WAN (wide area network) nodes that are inter-connected by a mesh structure. In order to guarantee QoS (quality of service) of application services, tactical service mesh (TSM) is suggested as an intermediate layer between infrastructure and application layers for futuristic tactical mesh network. The tactical service mesh requires dynamic QoS monitoring and control for intelligent QoS coordination. However, legacy networking nodes used for existing tactical networks are difficult to support these functionality due to inflexible monitoring support. In order to resolve such matter, we propose a tactical mesh WAN node as a hardware/software co-designed networking node in this paper. The tactical mesh WAN node is conceptually designed to have multi-access networking interfaces and virtualized networking switches by leveraging the DANOS whitebox server/switch. In addition, we explain how to apply eBPF-based traffic monitoring to the tactical mesh WAN node and verify the traffic monitoring feasibility for supporting QoS coordination of tactical-mesh traffic.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.04a
• /
• pp.41-41
• /
• 2008

In general, polyimides (PIs) are used in alignment layers in liquid crystal displays (LCDs). The rubbing alignment technique has been widely used to align the LC molecules on the PI layer. Although this method is suitable for mass production of LCDs because of its simple process and high productivity, it has certain limitations. A rubbed PI surface includes debris left by the cloth, and the generation of electrostatic charges during the rubbing induces local defects, streaks, and a grating-like wavy surface due to nonuniform microgrooves that degrade the display resolution of computer displays and digital television. Additional washing and drying to remove the debris, and overwriting for multi-domain formation to improve the electro-optical characteristics such as the wide viewing angle, reduce the cost-effectiveness of the process. Therefore, an alternative to non-rubbing techniques without changing the LC alignment layer (i.e, PI) is proposed. The surface of LC alignment layers as a function of the ion beam (IE) energy was modified. Various pretilt angles were created on the IB-irradiated PI surfaces. After IB irradiation, the Ar ions did not change the morphology of the PI surface, indicating that the pretilt angle was not due to microgrooves. To verify the compositional behavior for the LC alignment, the chemical bonding states of the ill-irradiated PI surfaces were analyzed in detail by XPS. The chemical structure analysis showed that ability of LCs to align was due to the preferential orientation of the carbon network, which was caused by the breaking of C=O double bonds in the imide ring, parallel to the incident 18 direction. The potential of non-rubbing technology for fabricating display devices was further conformed by achieving the superior electro-optical characteristics, compared to rubbed PI.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.7-14
• /
• 2010

In this paper, we introduce a hierarchical internet application traffic classification system based on SVM as an alternative overcoming the uppermost limit of the conventional methodology which is using the port number or payload information. After selecting an optimal attribute subset of the bidirectional traffic flow data collected from the campus, the proposed system classifies the internet application traffic hierarchically. The system is composed of three layers: the first layer quickly determines P2P traffic and non-P2P traffic using a SVM, the second layer classifies P2P traffics into file-sharing, messenger, and TV, based on three SVDDs. The third layer makes specific classification of the entire 16 application traffics. By classifying the internet application traffic finely or coarsely, the proposed system can guarantee an efficient system resource management, a stable network environment, a seamless bandwidth, and an appropriate QoS. Also, even a new application traffic is added, it is possible to have a system incremental updating and scalability by training only a new SVDD without retraining the whole system. We validate the performance of our approach with computer experiments.

• Composites Research
• /
• v.19 no.5
• /
• pp.28-33
• /
• 2006

In this paper, we have studied the complex permittivities and their influence on the design of microwave absorbers of E-glass fabric/epoxy composite laminates containing three different types of carbon-based nano conductive fillers such as carbon black (CB), carbon nano fiber (CNF) and multi-wall nano tube (MWNT). The measurements were performed fur permittivities at the frequency band of 0.5 GHz$\sim$18.0 GHz using a vector network analyzer with a 7 mm coaxial air line. The experimental results show that the complex permittivities of the composites depend strongly on the natures and concentrations of the conductive fillers. The real and imaginary parts of the complex permittivities of the composites were proportional to the filler concentrations. But, depending on the types of fillers and frequency band, the increasing rates of the real and imaginary parts with respect to the filler concentrations were all different. These different rates can have an effect on the thickness in designing the single layer microwave absorbers. The effect of the different rates at 10 GHz was examined by using Cole-Cole plot; the plot is composed of a single layer absorber solution line and measured permittivities from these three types of composites. Single layer absorbers of 3 different thicknesses using carbon nano materials were fabricated and the -10 dB band of absorbing performances were all about 3 GHz.

• Journal of the Korean Geotechnical Society
• /
• v.15 no.1
• /
• pp.99-112
• /
• 1999

By using 92 values of lateral earth pressure coefficient(K) measured in Korea, the tendency of K with varying depth is analyzed and compared with the range of K defined by Hoek and Brown. The horizontal stress is generally larger than the vertical stress in Korea : About 84 % of K values are above 1. In this study, the theory of elasto-plasticity is applied to analyze the variation of K values, and the results are compared with those of numerical analysis. This reveals that the erosion, sedimentation and weathering of earth crust are important factors in the determination of K values. Surface erosion, large lateral pressure and good rock mass increase the K values, but sedimentation decreases the K values. This study enable us to analyze the effects of geological processes on the K values, especially at shallow depth where underground excavation takes place. A neural network expert system using multi-layer back-propagation algorithm is developed to predict the K values. The neural network model has a correlation coefficient above 0.996 when it is compared with measured data. The comparison with 9 measured data which are not included in the back-propagation learning has shown an average inference error of 20% and the correlation coefficient above 0.95. The expert system developed in this study can be used for reliable determination of K values.

• Progress in Medical Physics
• /
• v.20 no.3
• /
• pp.132-138
• /
• 2009

Studies on target motion in 4-dimensional radiotherapy are being world-widely conducted to enhance treatment record and protection of normal organs. Prediction of tumor motion might be very useful and/or essential for especially free-breathing system during radiation delivery such as respiratory gating system and tumor tracking system. Neural network is powerful to express a time series with nonlinearity because its prediction algorithm is not governed by statistic formula but finds a rule of data expression. This study intended to assess applicability of neural network method to predict tumor motion in 4-dimensional radiotherapy. Scaled Conjugate Gradient algorithm was employed as a learning algorithm. Considering reparation data for 10 patients, prediction by the neural network algorithms was compared with the measurement by the real-time position management (RPM) system. The results showed that the neural network algorithm has the excellent accuracy of maximum absolute error smaller than 3 mm, except for the cases in which the maximum amplitude of respiration is over the range of respiration used in the learning process of neural network. It indicates the insufficient learning of the neural network for extrapolation. The problem could be solved by acquiring a full range of respiration before learning procedure. Further works are programmed to verify a feasibility of practical application for 4-dimensional treatment system, including prediction performance according to various system latency and irregular patterns of respiration.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.904-911
• /
• 2003

In this paper, we propose an effective method for the distinction between machine-printed and handwritten Korean address images. It is important to know whether an input image is handwritten or machine-printed, because methods for handwritten image are quite different from those of machine-printed image in such applications as address reading, form processing, FAX routing, and so on. Our method consists of three blocks: valid connected components grouping, feature extraction, and classification. Features related to width and position of groups of valid connected components are used for the classification based on a neural network. The experiment done with live Korean address images has demonstrated the superiority of the proposed method. The correct classification rate for 3,147 testing images was about 98.85%.