• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• 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
• /
• 제43권5호
• /
• 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
• /
• 제17권4호
• /
• 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)
• /
• 제16권5호
• /
• 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.

• 한국콘텐츠학회논문지
• /
• 제21권3호
• /
• pp.616-625
• /
• 2021

심층신경망은 임의의 함수를 근사화하는 방법으로 선형모델로 근사화한 후에 비선형 활성함수를 이용하여 추가적 근사화를 반복하는 근사화 방법이다. 이 과정에서 근사화의 성능 평가 방법은 손실함수를 이용한다. 기존 심층학습방법에서는 선형근사화 과정에서 손실함수를 고려한 근사화를 실행하고 있지만 활성함수를 사용하는 비선형 근사화 단계에서는 손실함수의 감소와 관계가 없는 비선형변환을 사용하고 있다. 본 연구에서는 기존의 활성함수에 활성함수의 크기를 변화시킬 수 있는 크기 파라메터와 활성함수의 위치를 변화시킬 수 있는 위치 파라미터를 도입한 파라메트릭 활성함수를 제안한다. 파라메트릭 활성함수를 도입함으로써 활성함수를 이용한 비선형 근사화의 성능을 개선시킬 수 있다. 각 은닉층에서 크기와 위치 파라미터들은 역전파 과정에서 파라미터들에 대한 손실함수의 1차 미분계수를 이용한 학습과정을 통해 손실함수 값을 최소화시키는 파라미터를 결정함으로써 심층신경망의 성능을 향상시킬 수 있다. MNIST 분류 문제와 XOR 문제를 통하여 파라메트릭 활성함수가 기존의 활성함수에 비해 우월한 성능을 가짐을 확인하였다.

• 인터넷정보학회논문지
• /
• 제8권1호
• /
• pp.125-132
• /
• 2007

본 논문은 가중 퍼지소속함수 기반 신경망(neural network with weighted fuzzy membership functions, NEWFM)을 이용하여 심전도(ECG) 신호로부터 조기심실수축(premature vedtricular contractions, PVC)을 자동 탐지하는 방안을 제시하고 있다. NEWFM은 MIT-BIH 데이터베이스의 부정맥 심전도를 웨이블릿 변환(wavelet transform, WT)한 계수로부터 학습하여 정상 파형과 PVC 파형을 구분한다. 비중복면적 분산 측정법을 적용하여 중요도가 가장 높은 웨이블릿 변환의 d3과 d4의 8개 계수를 추출하였다. 이들 특징입력을 3개의 실험군에 사용하여 각각 99.80%, 99.21%, 98.78%의 신뢰성 있는 전체분류율을 나타내었고, 이는 각 실험군에 대한 특징입력의 종속성이 적음을 보여준다. 추출된 8개 계수의 ECG 신호 구간과 퍼지소속함수를 제시함으로써 특징입력에 대한 명시적인 해석을 가능하게 하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• 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.

• 산업공학
• /
• 제14권1호
• /
• 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
• /
• 제19권1호
• /
• 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.

• 한국환경복원기술학회지
• /
• 제18권5호
• /
• 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.