• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• Convergence Security Journal
• /
• v.15 no.2
• /
• pp.63-68
• /
• 2015

Current ICT(Information & Communication Technology) infrastructures (Internet and server/client communication) are struggling for a wide variety of devices, services, and business and technology evolution. Cloud computing originated simply to request and execute the desired operation from the network of clouds. It means that an IT resource that provides a service using the Internet technology. It is getting the most attention in today's IT trends. In the distributed cloud environments, management costs for the network and computing resources are solved fundamentally through the integrated management system. It can increase the cost savings to solve the traffic explosion problem of core network via a distributed Micro DC. However, traditional flooding methods may cause a lot of traffic due to transfer to all the neighbor DCs. Restricted Path Flooding algorithms have been proposed for this purpose. In large networks, there is still the disadvantage that may occur traffic. In this paper, we developed Lightweight Path Flooding algorithm to improve existing flooding algorithm using hop count restriction.

• Convergence Security Journal
• /
• v.19 no.4
• /
• pp.87-96
• /
• 2019

Recently, with the rapid development of video equipment and technology, tremendous video information is produced and utilized in military domain to acquire battlefield information or for effective command control. Note that the video playback devices currently used in the military domain ranges from low-performance tactical multi-functional terminals (TMFT) to high-performance video servers and the networks where the video information is transmitted also range from the low speed tactical information and communication network (TICN) to ultra-high speed defense broadband converged networks such as M-BcN. Therefore, there is a need for an efficient streaming technique that can efficiently transmit defense video information in heterogeneous communication equipment and network environments. To solve the problem, this paper proposes a Scalable Video Coding (SVC) and balanced selection algorithm based Peer-to-Peer (P2P) streaming technique and the feasibility of the proposed technique is verified by simulations. The simulation results based on our BitTorrent simulator show that the proposed balanced selection scheme outperforms the sequential or rarest selection algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.21-29
• /
• 2010

In Ad-Hoc Networks, the limited energy is the key issue for longer network operation time. To solve this problem, various energy-aware routing techniques have been proposed including PSR (Power-aware Source Routing), HPSR (Hirachical Power-aware Source Routing), and etc. Those techniques generally select the most adequate route considering the energy consumption so that the energy efficiency can be improved. However, There are problems in those techniques that traffic can be concentrated in some specific area in a network. In this paper, a new energy aware routing technique called MPSR is proposed to achieve longer network lifetime and fewer rerouting attempts.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.95-106
• /
• 2017

In this paper, we investigate the conventional topological interference management (TIM) with proposed network topology such as 8 trigram (8 user networks). The key observation is that optimal symmetric degree of freedom (DoF) can be achieved for 8 user network with different channel coherence times by adaptively selecting the interference alignment scheme via controlling the alignment feasibility of the transmitted signals. However, this yields a very complex problem, for which we use the combination of different schemes such as interference avoidance and repetition coding. In addition to the above schemes, we propose a triangular transmit cooperation (TTC) algorithm for 8 user networks to achieve the optimal symmetric DoF. And We apply the principle of complementarity of 8 trigram to remove the interferences, and correspond the concepts of win-win and conflict to direct and indirect signals of transmit and receive respectively. We find that the principle of complementarity comes out from the trigram of I Ching. That is, we apply the relation of confrontation and coexistence to 8 transmitters and receivers, and get the results of symmetric DoF of 4/3.

• Convergence Security Journal
• /
• v.16 no.5
• /
• pp.11-16
• /
• 2016

In modern society, the development of Information and Communication Technology has given people a lot of opportunities. But on the other side cyber attack also gives enormous damage to people. Recently Korea has become the target of cyber attack. The threat of it is growing. Especially North Korea has committed hostile actions against South Korea. North Korea has recently attacked the computer networks of South Korea's important national facilities. The types of North Korea's cyber attacks include the followings. First, if we see it with the viewpoint of software, it tries to destroy or control the Internet, infects the networks with viruses, worms, Trojan Horse and Distributed Denial of Service. I suggest the following to solve the problem. First, South Korea should unify the organizations to respond to the attacks of North Korea, as North Korea has a unified organization for the cyber attack. Second, they should think about the establishment of "Cyber Terrorism Prevention Act" to systematically respond to the software attacks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.8
• /
• pp.643-650
• /
• 2014

Recently, the wireless communication applications are studied in various environment by the development of short range communication system like wireless sensor networks. This paper presents the analysis of localization schemes for ship application using received signal strength. The localization schemes using received signal strength from wireless networks are classified under two methods, which are Range based method and Range free method. Range based methods estimate the location with least square estimation based on estimated distance using path-loss model. Range free methods estimated the location with the information of anchor nodes linked to target. Simulation results show the appropriate localization scheme for each cabin environments based on the empirical path-loss model in warship's internal space.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.1
• /
• pp.55-61
• /
• 2011

In this paper, the outage probability of device-to-device (D2D) uplink communication underlaying cellular networks is analyzed over Rayleigh fading. We assume that a D2D pair and M cellular user equipments share the same frequency resources. To prevent any harmful interference from a D2D transmitter to the BS, the maximum transmit power of the D2D transmitter is strictly limited. Under these assumptions, the outage probability is represented as a function of the interference-to-signal ratio from M cellular user equipments to a D2D receiver and the number of cellular user equipments, M. In addition, the interference-to-signal ratio is represented as a function of distances among D2D equipments, cellular user equipments and the BS. Simulation results validate these analytical results.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.157-165
• /
• 2015

With the ever-improving performance of smartphone cameras and the universal dissemination of cloud services, users can now record and store the events in their daily lives more easily and conveniently. The advent of lifelogging technology has been changing the uses as well as the paradigm of internet services, and emphasizing the importance of services being personalization. As the amount of lifelog data becomes vast, it requires an efficient way to manage and store such vast information. In this paper, we propose an low power lifelog management scheme based on user movement behaviors in wireless networks. In order to reduce the power consumption of a smartphone, in our proposal, frequency of data collection and transfer can be dynamically adjusted based on a user's movement pattern. The analytical results show that our approach achieves better performance than that of the existing lifelog management scheme.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.81-88
• /
• 2018

Spectrum sensing, the key technology of the cognitive radio networks, is used by a secondary user to determine the frequency state of a primary user. The energy detection in the spectrum sensing determines the presence or absence of a primary user according to the intensity of the allocated channel signal. Since this technique simply uses the strength of the signal for spectrum sensing, it is difficult to detect the signal of a primary user in the low SNR band. In this paper, we propose a way to combine spectrum sensing and support vector machine using wavelet packet decomposition to overcome performance degradation in low SNR band. In our proposed scheme, the sensing signals were extracted by wavelet packet decomposition and then used as training data and test data for support vector machine. The simulation results of the proposed scheme are compared with the energy detection using the AUC of the ROC curve and the accuracy according to the SNR band. With simulation results, we demonstrate that the proposed scheme show better determining performance than one of energy detection in the low SNR band.