• Journal of the Korean Data and Information Science Society
• /
• 제14권3호
• /
• pp.715-723
• /
• 2003

A tandem network in which all nodes have the same load is considered. We derive bounds on the probability that the total population of the tandem network exceeds a large value by using its relation to the stationary distribution. These bounds imply a stronger asymptotic limit than that in the large deviation theory.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.41.5-41
• /
• 2001

A novel method is introduced for determining the weights of a regularization network which approximates one-to-many mapping. A conventional neural network will converges to the average value when outputs are multiple for one input. The capability of proposed network is demonstrated by an example of learning inverse mapping.

• 한국정보통신학회논문지
• /
• 제24권4호
• /
• pp.515-521
• /
• 2020

최근 데이터 트래픽은 다양한 산업 발전으로 인해 폭발적으로 증가하여 기존 네트워크의 효율성 감소, 과부화 등의 문제를 야기한다. 이러한 문제를 해결하기 위해 가상화 기법을 이용하며 다양한 서비스에 최적화된 네트워크를 제공하는 네트워크 슬라이싱이 주목받고 있다. 본 논문에서는 credit value를 이용하여 자원할당을 하는 방안에 대해 제안한다. 기존 클러스터링 기법을 이용한 방안에서는 다양한 서비스에 대한 할당 요청이 들어올 때마다 클러스터 선정하기 위한 연산이 수행된다. 반면에 제안 방안에서는 클러스터의 잔여 사용량과 balancing을 이용하여 credit value를 설정하여 클러스터 선정에 필요한 연산을 수행하지 않고 slice request를 처리할 수 있도록 하였다. 제안 방안을 검증하기 위해 processing time과 balancing simulation을 진행하였다. 그 결과, 제안된 방안의 processing time 및 오차율은 clustering 기법만 사용한 방안보다 각각 약 13.72%, 약 7.96% 감소하였다.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2002년도 가을학술발표대회 디자인학 연구
• /
• pp.118-119
• /
• 2002

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.982-986
• /
• 1997

A method using cutting force signal and neural network for detection tool damage is proposed. Cutting force signal is gained by tool dynamometer and the signal is prepocessed to normalize. Cutting force signal is changed by tool state. When tool damage is occurred, cutting force signal goes up in comparison with that in normal state. However,the signal goes down in case of catastrophic fracture. These features are memorized in neural network through nomalizing couse. A new nomalizing method is introduced in this paper. Fist, cutting forces are sumed up except data smaller than threshold value, which is the cutting force during non-cutting action. After then, the average value is found by dividing by the number of data. With backpropagation training process, the neural network memorizes the feature difference of cutting force signal between with and without tool damage. As a result, the cutting force can be used in monitoring the condition of cutting tool and neural network can be used to classify the cutting force signal with and without tool damage.

• 디지털콘텐츠학회 논문지
• /
• 제6권1호
• /
• pp.7-12
• /
• 2005

논문은 IEEE 표준인 SCI(Scalable Coherent Interface)에 근거한 degree 2의 ICR(Interleaved Cyclic Ring) 네트워크의 신뢰도를 연구하였고 대표적인 링 네트워크들과 비교하였다. ICR 네트워크의 신뢰도 연구에 있어서 두 노드가 동시에 통신 할 수 있는 신뢰도를 계산하였다. ICR 네트워크의 신뢰도 연구에서 실패율(failure rate)의 변화에 신뢰도의 반응을 연구하였고 적은 노드에 대하여 정확한 신뢰도를 구하고 노드 수가 증가한 경우에는 최대 최소 경계를 계산하여 평균치 일반식을 구하였다. ICR 네트워크의 사이클의 변화에 따라 ICR 네트워크의 신뢰도를 다른 링 네트워크와 비교하였다.

• 한국가시화정보학회지
• /
• 제20권2호
• /
• pp.78-85
• /
• 2022

In these days, the rapid development in prediction technology using artificial intelligent is being applied in a variety of engineering fields. Especially, dimensionality reduction technologies such as autoencoder and convolutional neural network have enabled the classification and regression of high-dimensional data. In particular, pixel level prediction technology enables semantic segmentation (fine-grained classification), or physical value prediction for each pixel such as depth or surface normal estimation. In this study, the pressure distribution of the ship's surface was estimated at the pixel level based on the artificial neural network. First, a potential flow analysis was performed on the hull form data generated by transforming the baseline hull form data to construct 429 datasets for learning. Thereafter, a neural network with a U-shape structure was configured to learn the pressure value at the node position of the pretreated hull form. As a result, for the hull form included in training set, it was confirmed that the neural network can make a good prediction for pressure distribution. But in case of container ship, which is not included and have different characteristics, the network couldn't give a reasonable result.

• 인터넷정보학회논문지
• /
• 제25권1호
• /
• pp.49-56
• /
• 2024

There have been emerging many use-cases applying recommendation systems especially in online platform. Although the performance of recommendation systems is affected by a variety of factors, selecting appropriate features is difficult since most of recommendation systems have sparse data. Conventional matrix factorization (MF) method is a basic way to handle with problems in the recommendation systems. However, the MF based scheme cannot reflect non-linearity characteristics well. As deep learning technology has been attracted widely, a deep neural network (DNN) framework based collaborative filtering (CF) was introduced to complement the non-linearity issue. However, there is still a problem related to feature embedding for use as input to the DNN. In this paper, we propose an effective method using singular value decomposition (SVD) based feature embedding for improving the DNN performance of recommendation algorithms. We evaluate the performance of recommendation systems using MovieLens dataset and show the proposed scheme outperforms the existing methods. Moreover, we analyze the performance according to the number of latent features in the proposed algorithm. We expect that the proposed scheme can be applied to the generalized recommendation systems.

• 품질경영학회지
• /
• 제43권2호
• /
• pp.185-200
• /
• 2015

Purpose: Present study was designed to examine the casual relationships among tourism information service quality, value, user satisfaction, and reuse intention in social network service(SNS). Also, we intended to testify the mediating role of value in causal model. We applied path analysis model in order to test the hypotheses and research model. Methods: Survey tool, that is, questionnaire has obtained validity through literature survey, exploratory survey and pretest and sample 272 was selected. For statistical treatment of pretest and main analysis, SPSS18.0 and AMOS18.0 were employed and structural equation model was employed as analysis method. Results: Result of this study shows as follows. Two factors(ease of understanding and structure) have an effect on user satisfaction and reuse intention, and we found that value played a significant and important role in causal relationship. Therefore, value was empirically confirmed as t he import ant fact or preceding user satisfaction and reuse intention. Conclusion: Present study shows that two factors(ease of understanding and structure) in via of value, were important factors that related business companies have to emphasize to raise performance. However, present study has some limitations to additionally research in the future.

• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.153-174
• /
• 2016

On account of multiple causes, including prolonged global economic crisis, addressing environmental pollution and the advent of hyper-connected society, a new paradigm called 'sharing economy' has rapidly emerged. Many startups have attempted to build promising business model based on the sharing economy concept. Nevertheless, successful cases are still very rare in the global level, except for Uber and Airbnb cases. Therefore, this study analyzes necessary causes and sufficient causes for successful settlements in the market through a comparative case analysis on digital matching firms in the sharing economy businesses. For the case study, we compare five successful cases (Uber, Airbnb, Kickstarter, TaskRabbit and DogVacay), three failure cases (Homejoy, Ridejoy and Tuterspree) and a platform cooperativism case (Juno) in accordance with six value attributes of business model including value proposition, market segment, value chain, cost structure and profit potential, value network and competitive strategy. We apply Boolean method to support controlled comparison and eliminate unnecessary attributes. The Boolean analysis result shows that value proposition, cost structure and profit potential, value network and competitive strategy are the essential attributes. Furthermore, the result indicates that each attribute is a necessary condition, where all four conditions should be met simultaneously in order to be successful. With this result, we discuss essential consideration for those who are planning startup based on the sharing economy business model.