• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.254-259
• /
• 2013

The choice of labeled data in semi-supervised learning algorithm can result in effects on the performance of the resultant classifier. In order to select labeled data required for the training of a semi-supervised learning algorithm, VCNN(Vector Centroid Neural Network) is proposed in this paper. The proposed selection method of label data is evaluated on UCI dataset and caltech dataset. Experiments and results show that the proposed selection method outperforms conventional methods in terms of classification accuracy and minimum error rate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.411-416
• /
• 2002

Recently, the trial and success of malicious cyber attacks has been increased rapidly with spreading of Internet and the activation of a internet shopping mall and the supply of an online internet, so it is expected to make a problem more and more. Currently, the general security system based on Internet couldn't cope with the attack properly, if ever, other regular systems have depended on common softwares to cope with the attack. In this paper, we propose the positive selection mechanism and negative selection mechanism of T-cell, which is the biological distributed autonomous system, to develop the self/non-self recognition algorithm, the anomalous behavior detection algorithm, and AIS (Artificial Immune System) that is easy to be concrete on the artificial system. The proposed algorithm can cope with new intrusion as well as existing one to intrusion detection system in the network environment.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.26 no.4
• /
• pp.402-409
• /
• 2017

Selection of optimal cutting conditions is important for improving productivity and implementing efficient process control in metal machining. In this study, improvement of cutting conditions in machining using end-mills is studied by using deep-layered neural networks, which comprise an input layer, output layer, and two hidden layers. System networks are designed with inputs as cutting conditions, and they output the cutting force. A pseudo-inverse network is designed that has the adjustable cutting condition as output and cutting force and other cutting conditions as input. The combination of the system network and pseudo-inverse network enables selection or improvement of cutting conditions that results in the expected cutting force.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.11
• /
• pp.2143-2159
• /
• 2011

The hybrid architecture of content delivery networks (CDN) and peer-to-peer overlay networks (P2P) is a promising technology enables effective real-time streaming services. It complements the advantages of quality control and reliability in a CDN, and the scalability of a P2P system. With real-time streaming services, however, high connection setup and media delivery latency are becoming the critical issues in deploying the CDN-P2P system. These issues result from biased peer selection without location awareness or content awareness, and can lead to significant service disruption. To reduce service disruption latency, we propose a group-based CDN-P2P hybrid architecture (iCDN-P2P) with a location/content-aware selection of peers. Specifically, a SuperPeer network makes a location-aware peer selection by employing a content addressable network (CAN) to distribute channel information. It also manages peers with content awareness, forming a group of peers with the same channel as the sub-overlay. Through a performance evaluation, we show that the proposed architecture outperforms the original CDN-P2P hybrid architecture in terms of connection setup delay and media delivery time.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.297-307
• /
• 2022

The simple procedural segment selection algorithm commonly used in Dynamic Adaptive Streaming over HTTP (DASH) reveals severe weakness to provide high-quality streaming services in the integrated mobile networks of various wired and wireless links. A major issue could be how to properly cope with dynamically changing underlying network conditions. The key to meet it should be to make the segment selection algorithm much more adaptive to fluctuation of network traffics. This paper presents a system architecture that replaces the existing procedural segment selection algorithm with a deep reinforcement learning algorithm based on the Asynchronous Advantage Actor-Critic (A3C). The distributed A3C-based deep learning server is designed and implemented to allow multiple clients in different network conditions to stream videos simultaneously, collect learning data quickly, and learn asynchronously, resulting in greatly improved learning speed as the number of video clients increases. The performance analysis shows that the proposed algorithm outperforms both the conventional DASH algorithm and the Deep Q-Network algorithm in terms of the user's quality of experience and the speed of deep learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.652-655
• /
• 2017

As maritime information and communication technology has been developing and the demands for various kinds of application services has been increasing nowadays, the multi-band maritime networks combining available multiple radio networks has been introduced. We have previously proposed a multi-band network selection(MNS) system which operates in the middleware layer and selects the best available network seamlessly. In this paper we develop MNS server software, network interfaces, and application program. The functionalities of the MNS system, including updating network status, connecting to heterogeneous networks, and communicating in the best network are also verified via indoor test.

• International journal of advanced smart convergence
• /
• v.5 no.1
• /
• pp.66-72
• /
• 2016

In this paper, we proposed the clustering algorithm using fuzzy inference system for improving adaptability the cluster head selection of TEEN. The stochastic selection method cannot guarantee available of cluster head. Furthermore, because the formation of clusters is not optimized, the network lifetime is impeded. To improve this problem, we propose the algorithm that gathers attributes of sensor node to evaluate probability to be cluster head.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.142-144
• /
• 2004

To provide more qualified data service on the HFC(Hybrid-Fiber Coaxial) access network, the channel characteristics of upstream transmission band should be carefully investigated and analysed. It will be easier to do network management if the monitoring system for noise measurement in the network is available, In this paper, noise analysis method and the frequency selection method in the upstream band for duplex transmission are suggested. And, Data aquisition device for the signal measurement Is implemented. With this network monitoring system, field test and the result from the collected data are described.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.5 no.1
• /
• pp.39-45
• /
• 2010

As wireless sensor network are being deployed in a wide variety of application areas, the number of sensor nodes in a sensor filed becomes larger and larger. In the past, ISP (In-System Programming) method have been generally used for code update but the large number of sensor nodes requires a new code update method called network reprogramming. There are many challenging issues for network reprogramming since it can make an impact on the network lifetime. In this paper, a new sender selection scheme for network reprogramming protocol is proposed to decrease energy consumption for code update by minimizing overlapped area between sender nodes and reducing data contention. Simulation results show that the proposed scheme can reduce the amount of message traffic and the overall data transmission time.

• 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.