• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.11-19
• /
• 2019

In this paper, a new Scene-based Nonuniformity Correction (SBNUC) method is proposed by applying Image Roughness-like and Spatial Noise cost functions on deep neural network structure. The classic approaches for nonuniformity correction require generally plenty of sequential image data sets to acquire accurate image correction offset coefficients. The proposed method, however, is able to estimate offset from only a couple of images powered by the characteristic of deep neural network scheme. The real world SWIR image set is applied to verify the performance of proposed method and the result shows that image quality improvement of PSNR 70.3dB (maximum) is achieved. This is about 8.0dB more than the improved IRLMS algorithm which preliminarily requires precise image registration process on consecutive image frames.

• ETRI Journal
• /
• v.43 no.5
• /
• pp.932-940
• /
• 2021

Currently, research on network functions virtualization focuses on using microservices in cloud environments. Previous studies primarily focused on communication between nodes in physical infrastructure. Until now, there is no sufficient research on group key management in virtual environments. The service is composed of microservices that change dynamically according to the virtual service. There are dependencies for microservices on changing the group membership of the service. There is also a high possibility that various security threats, such as data leakage, communication surveillance, and privacy exposure, may occur in interactive communication with microservices. In this study, we propose an ID-based group key exchange (idGKE) mechanism between microservices as one group. idGKE defines the microservices' schemes: group key gen, join group, leave group, and multiple group join. We experiment in a real environment to evaluate the performance of the proposed mechanism. The proposed mechanism ensures an essential requirement for group key management such as secrecy, sustainability, and performance, improving virtual environment security.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.801-817
• /
• 2021

Network virtualization technologies have played efficient roles in deploying cloud, Internet of Things (IoT), big data, and 5G network. We have conducted a survey on network virtualization technologies, such as software-defined networking (SDN), network functions virtualization (NFV), and network virtualization overlay (NVO). For each of technologies, we have explained the comprehensive architectures, applied technologies, and the advantages and disadvantages. Furthermore, this paper has provided a summarized view of the latest research works on challenges and solutions of security issues mainly focused on DDoS attack and encryption.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.616-625
• /
• 2021

Deep neural networks are an approximation method that approximates an arbitrary function to a linear model and then repeats additional approximation using a nonlinear active function. In this process, the method of evaluating the performance of approximation uses the loss function. Existing in-depth learning methods implement approximation that takes into account loss functions in the linear approximation process, but non-linear approximation phases that use active functions use non-linear transformation that is not related to reduction of loss functions of loss. This study proposes parametric activation functions that introduce scale parameters that can change the scale of activation functions and location parameters that can change the location of activation functions. By introducing parametric activation functions based on scale and location parameters, the performance of nonlinear approximation using activation functions can be improved. The scale and location parameters in each hidden layer can improve the performance of the deep neural network by determining parameters that minimize the loss function value through the learning process using the primary differential coefficient of the loss function for the parameters in the backpropagation. Through MNIST classification problems and XOR problems, parametric activation functions have been found to have superior performance over existing activation functions.

• Journal of Internet Computing and Services
• /
• v.8 no.1
• /
• pp.125-132
• /
• 2007

This paper presents an approach to detect premature ventricular contractions(PVC) using the neural network with weighted fuzzy membership functions(NEWFM), NEWFM classifies normal and PVC beats by the trained weighted fuzzy membership functions using wavelet transformed coefficients extracted from the MIT-BIH PVC database. The eight most important coefficients of d3 and d4 are selected by the non-overlap area distribution measurement method. The selected 8 coefficients are used for 3 data sets showing reliable accuracy rates 99,80%, 99,21%, and 98.78%, respectively, which means the selected input features are less dependent to the data sets. The ECG signal segments and fuzzy membership functions of the 8 coefficients enable input features to interpret explicitly.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.4
• /
• pp.815-821
• /
• 2005

Among the various artificial neural networks the backpropagation network (BPN) has become a standard one. One of the components in a neural network is an activating function or a transfer function of which a representative function is a sigmoid. We have discovered that by updating the slope parameter of a sigmoid function simultaneous with the weights could improve performance of a BPN.

• IE interfaces
• /
• v.14 no.1
• /
• pp.30-38
• /
• 2001

Logistics network management has become one of the most important sources of competitive advantage regarding logistics cost and customer service in numerous business segments. Logistics network simulation is a powerful analysis method for designing and planning the logistics network optimally in an integrated way. This paper introduces a logistics network simulator, LONSIM, developed by author. LONSIM deploys a mix of simulation and optimization functions to model and analysis logistics network issues such as facility location, inventory policy, manufacturing policy, transportation mode, warehouse assignment, supplier assignment, order processing priority rule, and vehicle routes. LONSIM is built with AweSim 2.1 and Visual Basic 6.0, and executed in windows environment.

• Asia Marketing Journal
• /
• v.19 no.1
• /
• pp.19-34
• /
• 2017

Despite the importance of the impact of network structure on the relationships between firms and firm performance, few studies have investigated these effects. This study investigates how network openness influences the relationships between TSI, opportunism, technological uncertainty, and supplier performance. We also try to figure out how network openness functions as a governance mechanism.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.5
• /
• pp.13-26
• /
• 2015

Urban park and green space provide various functions. Among the functions, human benefit and increase of biodiversity are known to be important. Therefore, it is important to consider human and biotic aspect in the process of selecting suitable site for park and green space. However, there is insufficient research on both aspects. In this study, we used green network to analyze human and biotic aspect to select suitable site for park and green space in Seongnam City in Korea. To analyze the green network, we used accessibility for human aspect and used dispersal distance and habitat size for biotic aspect. We conducted least-cost path modelling using movement cost. In case of biotic aspect, GFS (generic focal species) is used to estimate habitat size and dispersal distance. To find out suitable site for park and green space, we used an overlay analysis method. As the result, old residential areas are shown have insufficient green network which needs park and green space. Furthermore, the green network for biotic aspect is insufficient in old residential areas comapred to green network for human aspect. The result of this study could contribute in planning of park and green space to maximize their functions.