• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3416-3435
• /
• 2023

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.719-728
• /
• 2016

In this paper, we analyzed IoT patent data using the social network analysis of keyword community network in patents related to Internet of Things technology. To identify the difference of IoT patent trends between Korea and USA, 100 Korea patents and 100 USA patents were collected, respectively. First, we first extracted important keywords from IoT patent abstracts using the TF-IDF weight and their correlation and then constructed the keyword network based on the selected keywords. Second, we constructed a keyword community network based on the keyword community and performed social network analysis. Our experimental results showed while Korea patents focus on the core technologies of IoT (such as security, semiconductors and image process areas), USA patents focus on the applications of IoT (such as the smart home, interactive media and telecommunications).

• Journal of the Korean Operations Research and Management Science Society
• /
• v.20 no.1
• /
• pp.35-54
• /
• 1995

Routing in ATM network is set up by combination of both virtual path routing and virtual channel routing. While virtual channel is similar concept to virtual circuit of data networks, virtual path is a special concept which is not used in traditional data networks. Virtual path can rearrange in structure and size by simply changing virtual path routing tables and giving the network the capability to eash allocate network resources according to the demand needs. This paper provides reconfiguration models of virtual path network which give the bandwidth of link and the routing path for each traffic class. The reconfiguration models are network optimization problems of multicommodity network flow type. The numerical examples are also included.

• Korean Management Science Review
• /
• v.23 no.2
• /
• pp.161-174
• /
• 2006

In this paper, we consider a network optimization problem arising from the deployment of BcN access network. BcN convergence services requires that access networks satisfy QoS meausres. BcN services have two types of traffics : stream traffic and elastic traffic. Stream traffic uses blocking probability as a QoS measure, while elastic traffic uses delay factor as a QoS measure. Incorporating the QoS requirements, we formulate the problem as a nonlinear mixed-integer Programming model. The Proposed model seeks to find a minimum cost dimensioning solution, while satisfying the QoS requirement. We propose two local search heuristic algorithms for solving the problem, and develop a network design system that implements the developed heuristic algorithms. We demonstrate the computational efficacy of the proposed algorithm by solving a realistic network design problem.

• Korean Management Science Review
• /
• v.21 no.1
• /
• pp.77-86
• /
• 2004

In this paper, we present a methodology for solving the multicommodity network flow problems using interior point methods. In our method, the minimum cost network flow problem extracted from the given multicommodity network flow problem is solved by primal-dual barrier method in which normal equations are solved partially using preconditioned conjugate gradient method. Based on the solution of the minimum cost network flow problem, a warm-start point is obtained from which Castro's specialized interior point method for multicommodity network flow problem starts. In the computational experiments, the effectiveness of our methodology is shown.

• Korean Management Science Review
• /
• v.32 no.4
• /
• pp.81-96
• /
• 2015

This paper models knowledge diffusion on an inter-organizational network. Based on literatures related to knowledge diffusion, the model considers critical factors that affect diffusion behavior including nodal property, relational property, and environmental property. We examine the relationships among network structure, knowledge search, and diffusion performance. Through a massive simulation runs based on the agent-based model, we find that the average path length of a network decreases a firm's cumulative knowledge stock, whereas the clustering coefficient of a firm has no significant relationship with the firm's knowledge. We also find that there is an interaction effect of network structure and the range of knowledge search on knowledge diffusion. Specifically, in a network of a larger average path length (APL) the marginal effect of search conduct is significantly greater than in that of a smaller APL.

• Bulletin of the Korean Space Science Society
• /
• 2003.10a
• /
• pp.56-56
• /
• 2003

과학위성 1호의 OBC(On-Board Computer)와 Sybsystem 간, Subsystem간, 또는 위성과 지상국간의 통신이 가능해야한다. 그리고 OBC(On-Board-Computer)나 지상국에서의 위성의 모듈들을 명령(Command)을 통하여 제어할 수 있어야 한다. 또한 모듈들을 원격검침(Telemetry)을 통하여 상태를 확인할 수 있어야 한다. 위에서 언급한 기능을 수행하는 모듈이 바로 Network System이다 과학위성1호에는 총 6개의 Network System이 구현되었다. 각각의 Network System들은 여러 Subsystem들과 연결되어있고, Network System간에 또한 연결되어서 Subsystem간의 통신과 Network System에 연결된 모듈들을 제어하고 상태를 수집한다. 본 연구에서는 과학위성1호 Network System의 구조, 기능, Spec 및 연구 개발 내용을 소개한다.

• Korean Management Science Review
• /
• v.19 no.1
• /
• pp.179-188
• /
• 2002

Ventures through technological innovation are increasingly suggested as one of the main engines for economic growth that can help control inflation and black trade balance. The Purpose of this study is to extract the network performance factors for ventures according to ventures life cycle. For the Purpose, the existing studies were examined into start-up company, entrepreneurial firm, smell firms with competitive advantage against large firms, and ventures network activity. And 63 samples from ventures in Korea were taken and analyzed empirically. The analyses and results are (1) the actual conditions of network activity on ventures; (2) the investigation of relationship between network activity and performance of ventures by venture's life cycle through the observations of Korean ventures. From the results, It Is also found that factors such as external environment and a ventures life cycle have been considered as the main influences on the performance of ventures. In addition, limitations and suggestions for further studies are noted.

• Management Science and Financial Engineering
• /
• v.12 no.2
• /
• pp.37-62
• /
• 2006

This paper considers the problem of designing logical tunnels in virtual private networks considering QoS guarantee which restricts the number of tunnel hops for each traffic routing. The previous researches focused on the design of logical tunnel itself and Steiner-tree based solution algorithms were proposed. However, we show that for some objective settings it is not sufficient and is necessary to consider both physical and logical connectivity at the same time. Thereupon, the concept of the layered network is applied to the logical tunnel design problem in virtual private networks. The layered network approach considers the design of logical tunnel as well as its physical routing and we propose a modified branch-and-price algorithm which is known to solve layered network design problems effectively. To show the performance of the proposed algorithm, computational experiments have been done and the results show that the proposed algorithm solves the given problem efficiently and effectively.