• The KIPS Transactions:PartC
• /
• v.13C no.7 s.110
• /
• pp.923-932
• /
• 2006

For the successful promotion about the NGN (Next Generation Network), centralized network control and management technology is required to guarantee QoS and Traffic Engineering. This paper describes SNMP. Web Services and Network Open Interface based connection management scheme which can be used in centralized server based network in which the control plane is separated from transport plane. We also constructed platforms about each of these connection management schemes and performed comparing and analyzing the performance of connection setup delays.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.102-108
• /
• 2018

The existing data transmission technology applied between the non-secure external internet and the secure internal business network has various problems when applied to the building facility management SCADA system control network. Traditional inter-network data transfer technologies involve high complexity and high costs because blacklist-based security techniques are applied to all data. However, whitelist-based security techniques can be applied to data distributed in Building Facility Management SCADA control systems because a small number of structured control data are repeatable and periodic. This simplifies the security technology applied to inter-network data transmission, enabling building facility management SCADA system control network deployment at low cost. In this paper, we proposed building control networks specialized in building facility management SCADA control systems by providing solutions to address and address these problems.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1366-1372
• /
• 2019

In this paper, we designed a revised neural network to remove the Monte Carlo Rendering noise contained in the ray tracing graphics. The Monte Carlo Rendering is the best way to enhance the graphic's realism, but because of the need to calculate more than thousands of light effects per pixel, rendering processing time has increased rapidly, causing a major problem with real-time processing. To improve this problem, the number of light used in pixels is reduced, where rendering noise occurs and various studies have been conducted to eliminate this noise. In this paper, a deep learning is used to remove rendering noise, especially by separating the rendering image into diffuse and specular light, so that the structure of the dual neural network is designed. As a result, the dual neural network improved by an average of 0.58 db for 64 test images based on PSNR, and 99.22% less light compared to reference image, enabling real-time race-tracing rendering.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.255-262
• /
• 2007

This paper proposes an enhanced skin color-based detection method to find a region of human face in color images. The proposed detection method combines three color spaces, RGB, $YC_bC_r$, YIQ and builds color union histograms of luminance and chrominance components respectively. Combined color union histograms are then fed in to the back-propagation neural network for training and Levenberg-Marquadt algorithm is applied to the iteration process of training. Proposed method with Levenberg-Marquadt algorithm applied to training process of neural network contributes to solve a local minimum problem of back-propagation neural network, one of common methods of training for face detection, and lead to make lower a detection error rate. Further, proposed color-based detection method using combined color union histograms which give emphasis to chrominance components divided from luminance components inputs more confident values at the neural network and shows higher detection accuracy in comparison to the histogram of single color space. The experiments show that these approaches perform a good capability for face region detection, and these are robust to illumination conditions.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.1
• /
• pp.51-57
• /
• 2007

In this paper we introduce the concept of MPLS-based VPN and propose a scheme for providing VPN services in MPLS networks. Furthermore, we design the control components and the operational procedures and evaluated the performance of traditional VPN implementation methods and MPLS-based VPN. In this scheme it is possible to solve several problems that IP-based VPN pertains via the allocation of VPN ID and virtual space without tunneling, thereby providing effective VPN services. In other words, the MPLS-based VPN scheme uses MPLS networking technology together with the PSTN which can achieve a perfect segregation of user traffic on per-customer basis in a physical link and can guarantee high reliability and security levels. Specially, in the perspective of customers, it can save networking facilities installation and maintenance costs considerably. On the contrary, it possesses some shortcomings in that its deployment tends to be restricted within an ISP's network boundary and it is vulnerable to external security break-ins when going through public networks such as the Internet due to its lack of data encryption capability.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.6B
• /
• pp.538-547
• /
• 2004

Optical Burst Switched (OBS) networks usually employ one-way reservation by sending a burst control packet (BCP) with a specific offset time, before transmitting each data burst frame (BDF). Therefore, The quality of service may be degraded because contentions may lead to loss of BDFs. Especially, this phenomenon becomes more serious when burst size is longer. This necessitates an effective method of prevention to avoid burst collision in nodes. OBS networks can employ several methods to avoid such burst losses. One is that burst size is cut short to reduce burst loss probability during scheduling time. In this paper, we evaluate the burst generation and transmission using Sub-Carrier Multiplexting (SCM) in OBS networks. We propose an appropriate burst assembly architecture and transmission scheme based on SCM in OBS networks. The performance of SCM in OBS networks is examined in terms of number of Sub-Carriers per wavelength, burst loss probability, throughput, and total bandwidth of an optical fiber.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.9-19
• /
• 1999

An increase of the number of the real time applications and the Internet hosts make the Internet architecture changed. Current Internet architecture has some problems to process the real time traffics. To solve these problem, a new Internet architecture is proposed as the Integrated Service model. In the current Internet, as multicast protocols, the QoS multicast and the best-effort multicast have been studied in their separate network environments. But, the Integrated Service Packet Network is a heterogeneous network composed of the QoS delivery domain and the best-effort delivery domain. Thus, those separated multicast protocols have limitations in an ISPN. In this paper, we propose a multicast protocol for the ISPN with the QoS and the best-effort multicasting, and analyze the performance of this protocol. As a result, we find that the packet losses are same for hybrid multicast and best-effort multicast when the bandwidth is sufficient. But, if there exist some background traffics, the hybrid multicast has less packet loss than of the best-effort multicast.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.40-48
• /
• 2018

This paper proposes a license-plate recognition algorithm for automobile black-box image which is obtained from the camera moving with the automobile. The algorithm intends to increase the overall recognition-rate of the license-plate by increasing the Korean character recognition-rate using multi-stage neural network for automobile black-box image where there are many movements of the camera and variations of light intensity. The proposed algorithm separately recognizes the vowel and consonant of Korean characters of automobile license-plate. First, the first-stage neural network recognizes the vowels, and the recognized vowels are classified as vertical-vowels('ㅏ','ㅓ') and horizontal-vowels('ㅗ','ㅜ'). Then the consonant is classified by the second-stage neural networks for each vowel group. The simulation for automobile license-plate recognition is performed for the image obtained by a real black-box system, and the simulation results show the proposed algorithm provides the higher recognition-rate than the existing algorithms using a neural network.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.7
• /
• pp.33-40
• /
• 2010

The hand over between different radio access networks, especially where their coverage overlaps, suffers various complications since the different access networks provide different service characteristics. In this paper, it is about the system which can control the wireless LAN network management system and the wireless LAN access point of variety vendor which is in different areas. Successful development of mobile sink wireless LAN network management system which supports multi-vendor devices and have center-local interoperability structure. In proposed system, speed of the mobile station give about 10% improvement when the map domain size is 5 than the existing system. Through a data plane and management system of message way, it give a stability system and consistency network.

• Knowledge Management Research
• /
• v.22 no.2
• /
• pp.1-17
• /
• 2021

In this study, we predicted the bitcoin prices of Bithum and Coinbase, a leading exchange in Korea and USA, using ARIMA and Recurrent Neural Networks(RNNs). And we used news articles from each country to suggest a separated RNN model. The suggested model identifies the datasets based on the changing trend of prices in the training data, and then applies time series prediction technique(RNNs) to create multiple models. Then we used daily news data to create a term-based dictionary for each trend change point. We explored trend change points in the test data using the daily news keyword data of testset and term-based dictionary, and apply a matching model to produce prediction results. With this approach we obtained higher accuracy than the model which predicted price by applying just time series prediction technique. This study presents that the limitations of the time series prediction techniques could be overcome by exploring trend change points using news data and various time series prediction techniques with text mining techniques could be applied to improve the performance of the model in the further research.