• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.37-50
• /
• 2009

In this paper, we proposed a mechanism for effective cooperation in sensor network. There are a few mechanism like RBS, TPSN, FPSN for sensor network. However these are supporting synchronization among nodes without global state. Therefore, we proposed SGSM(Simple Global State Management) to maintain global state among sensor nodes. As experimental results, we confirmed loss rate is within 1% as maintaining global state with SGSM mechanism. In this paper, we defined global state in sensor network and introduced SGSM for improving timming accuracy in sensor environment.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.315-316
• /
• 2023

본 논문에서는 딥러닝을 활용하여 KBO (Korea Baseball Organization)의 다음 시즌 플레이오프 진출 확률을 예측하는 Deep Neural Network (DNN) 시스템을 설계하고 구현하는 방법을 제안한다. 연구 방법으로 KBO 각 시즌별 데이터를 1999년도 데이터부터 수집하여 분석한 결과, 각 시즌 데이터 중 경기당 평균 득점, 타자 OPS, 투수 WHIP 등이 시즌 결과에 유의미한 영향을 끼치는 것을 확인하였다. 모델 설계는 linear, softmax 함수를 사용하는 것보다 relu, tanh, sigmoid 함수를 사용했을 때 더 높은 정확도를 얻을 수 있었다. 실제 2022 시즌 결과를 예측한 결과 88%의 정확도를 도출했다. 폭투의 수, 피홈런 등 가중치가 높은 변수의 값이 우수할 경우 시즌 결과가 좋게 나온다는 것이 증명되었다. 본 논문에서 설계한 이 시스템은 KBO 구단만이 아닌 모든 야구단에서 선수단을 구성하는데 활용 가능하다고 사료된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5B
• /
• pp.491-497
• /
• 2004

In this Paper, we W a Hovel global traffic control architecture to isolate malicious network attacks and protect network infrastructure in Internet backbone networks. Unlike existing methods based on individual packets or flows, since the proposed detection and control methods are operated on the aggregate traffic level, the computational complexity can k significantly reduced, and they are applicable to develop a global defense architecture against network attack. Experimental results show that the proposed scheme can detect the network attack symptoms very exactly and quickly and protect the network resources as well as the normal traffic flows very efficiently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.3
• /
• pp.135-149
• /
• 2008

Traditional attack detection schemes based on packets or flows have very high computational complexity. And, network based anomaly detection schemes can reduce the complexity, but they have a limitation to figure out the pattern of the distributed global scale network attack. In this paper, we propose an efficient and fast method for detecting distributed global-scale network attack symptoms in high-speed backbone networks. The proposed method is implemented at the aggregate traffic level. So, our proposed scheme has much lower computational complexity, and is implemented in very high-speed backbone networks. In addition, the proposed method can detect attack patterns, such as attacks in which the target is a certain host or the backbone infrastructure itself, via collaboration of edge routers on the backbone network. The effectiveness of the proposed method are demonstrated via simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06d
• /
• pp.315-318
• /
• 2011

In this work, a VN-based IPTV service delivery network containing a novel VNT was designed, This VN-based IPTV service delivery network utilizes current resources that can be easily obtained by IPTV providers and organizes these resources in a more efficient manner, We also developed a three-stage VN allocation scheme to reduce the complexity of topology design and allocation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.63-66
• /
• 2018

Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

• Journal of Information Technology Services
• /
• v.11 no.1
• /
• pp.305-323
• /
• 2012

This study examines online social media diffusion across different countries that will help to provide a picture of current global online social network services (SNSs). Analyzing country-level data drawn from 78 nations, we find that non-technological factors such as culture and language as well as technological factors including Internet penetration rate and smartphone adoption rate have significant effects on online social media diffusion. These findings, derived from a broad range of different countries, not only provide theoretical insights into understanding critical factors that enable successful global expansion of online social media services but also help practitioners plan their marketing strategies more effectively in a global context.

• The Journal of Society for e-Business Studies
• /
• v.5 no.1
• /
• pp.93-104
• /
• 2000

Domestic automotive industry is also facing the moment it should be with a competitively priced and highly qualified automotive ta compete with worldwide automotive makers of world market through global marketing and global sourcing. At this point, weve been studying xNX model of USA, Japan and Europe with OEMs, suppliers and KAMA(Korea Automotive Manufacturers Association) to give a network infrastructure of guaranteed service quality network performance, reliability, security and trouble handling. We hope all efforts above mentioned will make the whole industry more competitive and powerful.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.22-25
• /
• 2020

본 논문에서는 큰 크기의 심층 신경망을 압축하기위해 네트워크 수준의 가중치 공유방법인 Global Weight 패러다임을 최초로 제시한다. 기존의 가중치 공유방법은 계층별로 가중치를 공유하는 것이 대부분이었다. Global Weight 는 기존 방법과 달리 전체 네트워크에서 가중치를 공유하는 효율적인 방법이다. 우리는 Global Weight 를 사용하여 학습되는 새로운 컨볼루션 연산인 Global Weight Convolution(GWConv)연산과 GWConv를 적용한 Global Weight Networks(GWNet)을 제안한다. CIFAR10 데이터셋에서 실험한 결과 2.18 배 압축에서 85.64%, 3.41 배 압축에서 85.46%의 정확도를 보였다. Global Weight 패러다임은 가중치 공유가 궁극적으로 풀고자 했던 중복되는 가중치를 최소화하는 획기적인 방법이며, 추후 심도 있는 연구가 수행될 수 있음을 시사한다.