• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.4
• /
• pp.80-88
• /
• 2019

Software Defined Networking (SDN) is the future network paradigm of decoupling control and data functions. In SDN structure, it is hard to address scalability in case of large-scale networks because single controller managed thousands of switches in a centralized fashion. Most of previous studies have focused on horizontal scalability, where distributed controllers are assigned to network devices. However, they have abstracted the control plane and the application plane into a single controller. The layer of the common SDN architecture is divided into data plane, control plane, and application plane, but the control plane and application plane have been modeled as a single controller although they are logically separated. In this paper, we propose a analytical traffic model considering the both application plane and control plane based on queuing theory. This model can be used to address scalability issues such as controller placement problem without complicated simulations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.285-289
• /
• 2020

The configuration of hierarchical wireless networks is provided to support diverse network environments. In the base station, two system state can be basically considered for the operation management so that the state transition may be occurred between active and sleep modes. Hence, to reduce energy consumption the system operation management of the low power should be considered to the base station system. In this paper we consider the analytical model of Discontinuous Reception (DRX) to investigate the system management. We provide the analysis scheme of base station system by the DRX model, and the low power factor would be investigated for the energy consumption. We also use the finite-state Markov system model that in a system state period the wireless resource request and the operation of service call arrival interval is considered to numerically analyze the performance of energy saving operations of base station.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1311-1314
• /
• 2022

DNN을 사용하여 객체 인식 과정에서 객체를 잘 분류하기 위해서는 시각적 설명성이 요구된다. 시각적 설명성은 object class에 대한 예측을 pixel-wise attribution으로 표현해 예측 근거를 해석하기 위해 제안되었다, Scale-invariant한 특징을 제공하도록 설계된 pyramidal features 기반 backbone 구조는 object detection 및 classification 등에서 널리 쓰이고 있으며, 이러한 특징을 갖는 feature pyramid를 trainable attention mechanism에 적용하고자 할 때 계산량 및 메모리의 복잡도가 증가하는 문제가 있다. 본 논문에서는 일반적인 FPN에서 객체 인식 성능과 설명성을 높이기 위한 피라미드-주의집중 계층네트워크 (FPN-Attention Layered Network) 방식을 제안하고, 실험적으로 그 특성을 평가하고자 한다. 기존의 FPN만을 사용하였을 때 객체 인식 과정에서 설명성을 향상시키는 방식이 객체 인식에 미치는 정도를 정량적으로 평가하였다. 제안된 모델의 적용을 통해 낮은 computing 오버헤드 수준에서 multi-level feature를 고려한 시각적 설명성을 개선시켜, 결괴적으로 객체 인식 성능을 향상 시킬 수 있음을 실험적으로 확인할 수 있었다.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.127-136
• /
• 2009

Modeling and Simulation, especially in mobile ad hoc network(MANET), are the most effective way to analyze performance or optimize system parameters without establishing real network environment. Focusing mainly on overall network behaviors in MANET concerns dynamics of network transport operations, which can efficiently be characterized with event based system states rather than execution details of protocols. We thus consider the network as a discrete event system to analyze dynamics of network transport performance. Zeigler's set-theoretic DEVS(Discrete Event Systems Specification) formalism can support specification of a discrete event system in hierarchical, modular manner. The DEVSim++ simulation environment can not only provide a rigorous modeling methodology based on the DEVS formalism but also support modelers to develop discrete event models using the hierarchical composition methodology in object-orientation. This environment however hardly supports to specify connection paths of network nodes, which are continuously altered due to mobility of nodes. This paper proposes a DEVS-based modeling and simulation methodology of enabling node mobility, and develops DEVS models for the mobile ad hoc network. We also simulate developed models with the DEVSim++ engine to verify the proposal.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.147-152
• /
• 2016

One of major issues in machine learning that extracts and acquires knowledge implicit in data is to find an appropriate way of representing it. Knowledge can be represented by a number of structures such as networks, trees, lists, and rules. The differences among these exist not only in their structures but also in effectiveness of the models for their problem solving capability. In this paper, we propose partition utility as a criterion function for clustering that can lead to simplification of the model and thus avoid overfitting problem. In addition, a heuristic is proposed as a way to construct balanced hierarchical models.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.1
• /
• pp.95-105
• /
• 1995

An appendix to the MAP 3.0 specification notes that there are primary advantages to use of fiber optics : noise immunity, ability to run in difficult electrical environments, safety and high data rates. All of these may be quite useful in various manufacturing environments. In this paper, we study on construction schmes for a fiber-based 802.4 MAP system including the use of both bus and star topologies. We suggest passive star network and FDDI network for manufacturing environment. And then, we propose the FDDI protocol including the use a dual ring topology running at 100 Mbps to physical and datalink layer of MAT specification and analysis it's protocol and topology for abilities in manufacturing environments, We evaluate about applications service, time-critical processing and topology of two models in manufacturing environment.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.320-327
• /
• 2015

Although service robots in various fields are being commercialized, most of them have problems that depend on explicit commands by users and have difficulty to generate robust reactions of the robot in the unstable condition using insufficient sensor data. To solve these problems, we modeled mirror neuron and theory of mind systems, and applied them to a robot agent to show the usefulness. In order to implement quick and intuitive response of the mirror neuron, the proposed intention-response model utilized behavior selection networks considering external stimuli and a goal, and in order to perform reactions based on the long-term action plan of theory of mind system, we planned behaviors of the sub-goal unit using a hierarchical task network planning, and controled behavior selection network modules. Experiments with various scenarios revealed that appropriate reactions were generated according to external stimuli.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.7-14
• /
• 2010

In this paper, we introduce a hierarchical internet application traffic classification system based on SVM as an alternative overcoming the uppermost limit of the conventional methodology which is using the port number or payload information. After selecting an optimal attribute subset of the bidirectional traffic flow data collected from the campus, the proposed system classifies the internet application traffic hierarchically. The system is composed of three layers: the first layer quickly determines P2P traffic and non-P2P traffic using a SVM, the second layer classifies P2P traffics into file-sharing, messenger, and TV, based on three SVDDs. The third layer makes specific classification of the entire 16 application traffics. By classifying the internet application traffic finely or coarsely, the proposed system can guarantee an efficient system resource management, a stable network environment, a seamless bandwidth, and an appropriate QoS. Also, even a new application traffic is added, it is possible to have a system incremental updating and scalability by training only a new SVDD without retraining the whole system. We validate the performance of our approach with computer experiments.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Convergence Security Journal
• /
• v.15 no.3_1
• /
• pp.75-82
• /
• 2015

Recently, lot of researches on multi-level protocol have been done to balance the sensor node energy consumption of WSN and to improve the node efficiency to extend the life of the entire network. Especially in multi-hop protocol, a variety of models have been studied to improve energy efficiency and apply it in real system. In multi-hop protocol, we assume that energy consumption can be adjusted based on the distance between the sensor nodes. However, according to the physical property of the actual WSN, it's hard to establish this. In this paper, we propose low-power sub-cluster protocol to improve the energy efficiency based on the spread of distance. Compared with the previous protocols, the proposed protocol is energy efficient and can be effectively used in the wireless sensing network.