• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2835-2842
• /
• 2013

In this paper, service differentiation scheme using optical buffer that is reduced in size with slow-light technology in optical burst switching networks is presented. In suggested scheme, each outport has buffer to store high-class burst only in case that all its wavelengths are occupied. When all wavelengths are being used, a new arriving high-class burst goes into the buffer and waits until a burst is serviced. As soon as a burst is serviced with a wavelength, the high-class burst at buffer is allocated to the free wavelength. In case that low-class burst is arriving under the same situation, it is not stored at the buffer but discarded. An analytical model is derived to analyze the performance of the suggested scheme and compare its performance with the conventional scheme such as preemption and deflection as well as no service differentiations.

• Journal of KIISE:Information Networking
• /
• v.29 no.4
• /
• pp.386-396
• /
• 2002

This paper presents a neural network-based near-optimal routing algorithm. It employs a modified Hopfield Neural Network (MHNN) as a means to solve the shortest path problem. It uses every piece of information that is available at the peripheral neurons in addition to the highly correlated information that is available at the local neuron. Consequently, every neuron converges speedily and optimally to a stable state. The convergence is faster than what is usually found in algorithms that employ conventional Hopfield neural networks. Computer simulations support the indicated claims. The results are relatively independent of network topology for almost all source-destination pairs, which nay be useful for implementing the routing algorithms appropriate to multi -hop packet radio networks with time-varying network topology.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.11
• /
• pp.495-502
• /
• 2013

In this paper, we present an anonymous authentication and location assurance protocol for secure location-aware services over vehicular ad hoc networks (VANETs). In other to achieve our goal, we propose the notion of a location-aware signing key so as to strongly bind geographic location information to cryptographic function while providing conditional privacy preservation which is a desirable property for secure vehicular communications. Furthermore, the proposed protocol provides an efficient procedure based on hash chain technique for revocation checking to effectively alleviate communication and computational costs on vehicles in VANETs. Finally, we demonstrate comprehensive analysis to confirm the fulfillment of the security objectives, and the efficiency and effectiveness of the proposed protocol.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.401-406
• /
• 2021

Recently, mean-teacher models based on convolutional recurrent neural networks are popularly used in audio event detection. The mean-teacher model is an architecture that consists of two parallel CRNNs and it is possible to train them effectively on the weakly-labelled and unlabeled audio data by using the consistency learning metric at the output of the two neural networks. In this study, we tried to improve the performance of the mean-teacher model by using additional derivative features of the log-mel spectrum. In the audio event detection experiments using the training and test data from the Task 4 of the DCASE 2018/2019 Challenges, we could obtain maximally a 8.1% relative decrease in the ER(Error Rate) in the mean-teacher model using proposed derivative features.

• Journal of Convergence for Information Technology
• /
• v.11 no.12
• /
• pp.106-114
• /
• 2021

The needs in terms of wireless communications are growing up both for civil and military applications. Therefore a constant improvement of this technology is required to meet customer wishes. One of its main shortcomings is the inefficient use of the spectrum in which a large part of the allocated bands of frequencies is unused. Since communication is crucial, spectrum shortage problems can lead a multi-national and coalition operation to failure. Cognitive Radio Networks (CRNs) are a promising technology which continuously analyses the spectrum searching for available frequencies. It can solve this spectrum issue by avoiding interferences, improving system-wide spectral efficiency, robustness to dynamic conditions and allowing more spectrum flexibility This paper specifically analyzed and presented the application of the CRNs in the military operational environment, and presented the appropriate method applicable to each actual operational situation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.149-160
• /
• 2021

In this study, artificial intelligence-based algorithms were proposed, which included a fuzzy search for matching suspects between current and historical crimes in order to obtain related cases in criminal history, as well as conditional generative adversarial networks for crime prediction system (CPS) using Timor-Leste as a case study. By comparing the data from the criminal records, the built algorithms transform witness descriptions in the form of sketches into realistic face images. The proposed algorithms and CPS's findings confirmed that they are useful for rapidly reducing both the time and successful duties of police officers in dealing with crimes. Since it is difficult to maintain social safety nets with inadequate human resources and budgets, the proposed implemented system would significantly assist in improving the criminal investigation process in Timor-Leste.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.1-7
• /
• 2019

Recently, multimedia streaming service has been activated, and the demand for high-quality multimedia convergence contents services is predicted to increase significantly in the future. The issues of the increasing network load due to the rise of multimedia streaming traffic must be addressed in order to provide QoS guaranteed services. To do this, an efficient network resource management and mobility support technologies are needed through seamless mobility support for heterogeneous networks. Therefore, in this paper, an MIH technology was used to recognize the network situation information in advance and reduce packet loss due to handover delays, and an ACLMIH-FHPMIPv6 is designed that can provide an intelligent interface through introducing a hierarchical mobility management technique in FPMIPv6 integrated network.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.195-200
• /
• 2021

With the development of transportation and mobiles demand for tourism travel is increasing and related industries are also developing significantly. The combination of augmented reality and tourism contents one of the areas of digital media technology, is also actively being studied, and artificial intelligence is already combined with the tourism industry in various directions, enriching tourists' travel experiences. In this paper, we propose a system that scans miniature models produced by reducing tourist areas, finds the relevant tourist sites based on models learned using deep learning in advance, and provides relevant information and 3D models as AR services. Because model learning and object detection are carried out using YOLOv3 neural networks, one of various deep learning neural networks, object detection can be performed at a fast rate to provide real-time service.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.50-55
• /
• 2021

Multi-path system is a system in which utilizes various networks simultaneously. It is expected that multi-path system can enhance communication speed, reliability, security of network. In this paper, we focus on path selection in multi-path system. To select optimal path, we propose deep reinforcement learning algorithm which is rewarded by the round-trip-time (RTT) of each networks. Unlike multi-armed bandit model, deep Q learning is applied to consider rapidly changing situations. Due to the delay of RTT data, we also suggest compensation algorithm of the delayed reward. Moreover, we implement testbed learning server to evaluate the performance of proposed algorithm. The learning server contains distributed database and tensorflow module to efficiently operate deep learning algorithm. By means of simulation, we showed that the proposed algorithm has better performance than lowest RTT about 20%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1183-1194
• /
• 2021

Traditionally, electric power systems have been known as the centralized structures, which is organized into placing customers at the end of the supply chain. However, recent decades have witnessed the emergence of distributed energy resources(:DERs) such as rooftop solar, farming PV system, small wind turbines, battery energy storage systems and smart home appliances. With the emergence of distributed energy resources, the role of distributed system operators(:DSOs) will expand. The increasing penetration of DERs could lead to a less predictable and reverse flow of power in the system, which can affect the traditional planning and operation of distribution and transmission networks. This raises the need for a change in the role of the DSOs that have conventionally planned, maintained and managed networks and supply outages. The objective of this research is to designed the future distribution operation system with multi-DERs and the proposed distribution system model is implemented by hardware-in-the-loop simulation(HILS). The test results show the normal operation domain and reduction of distribution line loss.