• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1051-1059
• /
• 2014

In this paper, we propose an intelligent situation recognition model by collecting and analyzing multiple sensor signals. Multiple sensor signals are collected for fixed time window. A training set of collected sensor data for each situation is provided to K2-learning algorithm to generate Bayesian networks representing causal relationship between sensors for the situation. Statistical characteristics of sensor values and topological characteristics of generated graphs are learned for each situation. A neural network is designed to classify the current situation based on the extracted features from collected multiple sensor values. The proposed method is implemented and tested with UCI machine learning repository data.

• Annual Conference of KIPS
• /
• 2014.11a
• /
• pp.173-174
• /
• 2014

Handover is constantly a challenging issue in wireless networks. Most of the existing solutions are host-based, which are implemented on the wireless terminals and leave the decision making to the terminals. This paper studies the problem of network-based handover in the wireless networks with the constraints of low latency as well as low computational time. To address this problem, we employ the software-defined network (SDN) architecture to facilitate handover. According to the operational model of the SDN, we define a workflow for all involved network entities, and then design a framework implementing the workflow as a complete handover system. The proposed framework aims to establish a channel conveying the mobility-related information of devices and the context information of their vicinity from the switches/access routers to the controllers. Based on collected information, the controller can optimally execute the handover.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.4
• /
• pp.126-137
• /
• 1994

Performance management of computer networks is intended to improve a given network performance in order for more efficient information exchange between subsystems of an integrated large-scale system. Importance of perfomance management is growing as many functions of the large- scale system depend on the quality of communication services provided by the network. The role of performance management is to manipulate the adjustable protocol parameters on line so that the network can adapt itself to a dynamic environment. This can be divided into two subtasks : performance evaluation to find how changes in protocol parameters affect the network performance and decision making to determine the magnitude and direction of parameter adjustment. This paper is the first part of the two papers focusing on conceptual design, development, and evaluation of performance management for token bus networks. This paper specifically deals with the task of performance evaluation which utilizes the principle of perturbation analysis of discrete event dynamic systems. The developed algorithm can estimate the network performance under a perturbed protocol parameter setting from observations of the network operations under a nominal parameter setting.

• Annual Conference of KIPS
• /
• 2015.10a
• /
• pp.335-336
• /
• 2015

Seamless mobility is one of the most crucial feature of telecommunication industry. Researches are going on in full swing to deal with this feature in most efficient manner. Software Defined Networking (SDN) is seen as the next generation paradigm which can facilitate seamless mobility across heterogeneous networks by segregating the control plane and data plane functionalities, and logically centralizing the control plane. In this paper, we propose a simplified Layer 2 handover mechanism for enterprise wireless networks, based on SDN framework. We present a network assisted L2 handover method using the IEEE 802.21 Media Independent Handover (MIH) protocol and SDN concepts, to achieve seamless mobility across heterogeneous networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.473-493
• /
• 2019

5G vehicular communication is one of key enablers in next generation intelligent transportation system (ITS), that require ultra-reliable and low latency communication (URLLC). To meet this requirement, a new hybrid vehicular network structure which supports both centralized network structure and distributed structure is proposed in this paper. Based on the proposed network structure, a new vehicular network utility model considering the latency and reliability in vehicular networks is developed based on Euclidean norm theory. Building on the Pareto improvement theory in economics, a vehicular network uplink optimization algorithm is proposed to optimize the uplink utility of vehicles on the roads. Simulation results show that the proposed scheme can significantly improve the uplink vehicular network utility in vehicular networks to meet the URLLC requirements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5449-5464
• /
• 2018

Recent works have validated the possibility of reducing the energy consumption in wireless heterogeneous networks, achieved by switching on/off some base stations (BSs) dynamically. In this paper, to realize energy conservation, the discrete time Markov Decision Process (DTMDP) is developed to match up the BS switching operations with the traffic load variations. Then, an asynchronous decision-making algorithm, which is based on the Bellman equation and the on/off priorities of the BSs, is firstly put forward and proved to be optimal in this paper. Through reducing the state and action space during one decision, the proposed asynchronous algorithm can avoid the "curse of dimensionality" occurred in DTMDP frequently. Finally, numerical simulations are conducted to validate the effectiveness and advantages of the proposed asynchronous on/off strategies.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.400-401
• /
• 2013

Mobility in a network causes link disconnections and link recovery is vital for reliability of a network. A link failure affects all the preceding nodes on a damaged routing path; creates communication delay, throughput degradation, and congestion. This paper proposes link recovery mechanisms in CCN based networks. Packet overhearing is used to update neighboring nodes information. The recovery is done by forwarding node resulting in low control overhead, and better efficiency. The proposed mechanisms increase overall performance of a typical CCN and simulation results show that our proposed scheme works very well in densely populated networks with high mobility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.666-669
• /
• 2020

Energy harvesting sensor networks have the ability to collect energy from the environment to overcome the power limitations of traditional sensor networks. The sensor network, which has a limited transmission range, delivers data to the destination node through a multi-hop method. The routing protocol should consider the power situation of nodes, which is determined by the residual power and energy harvesting rate. At this time, if only considering the magnitude of the power, power imbalance can occur among nodes and it can induce instantaneous power shortages and reduction of network lifetime. In this paper, we designed a routing protocol that considers the balance of power as well as the residual power and energy harvesting rate.

• Electronics and Telecommunications Trends
• /
• v.36 no.6
• /
• pp.13-24
• /
• 2021

Industrial networks has been developing various technologies from fieldbus technology to industrial Ethernet and time-sensitive networking. The industry expects that the 5G mobile network will solve the diverse and highly specific industrial site requirements. Accordingly, 3GPP has been developing standard functions to provide ultra-high reliability, ultra-high speed, ultra-connection, and ultra-low latency services, and 3GPP Rel-16 began developing ultra-low latency and ultra-high reliability communication functions for 5G mobile networks to support vertical industries. In this paper, we show the related standardization trends and requirements to apply industrial IoT service scenarios to 5G mobile networks, and in particular, we introduce 5G system features and extended 5G system architecture to provide time sensitive communication and time synchronization services.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.167-173
• /
• 2023

Hangul is unique compared to other Asian languages because of its simple letter forms that combine to create syllabic shapes. There are 24 basic letters that can be combined to form 27 additional complex letters. This produces 51 graphemes. Hangul optical character recognition has been a research topic for some time; however, handwritten Hangul recognition continues to be challenging owing to the various writing styles, slants, and cursive-like nature of the handwriting. In this study, a dataset containing thousands of samples of 51 Hangul graphemes was gathered from 110 freshmen university students to create a robust dataset with high variance for training an artificial neural network. The collected dataset included 2200 samples for each consonant grapheme and 1100 samples for each vowel grapheme. The dataset was normalized to the MNIST digits dataset, trained in three neural networks, and the obtained results were compared.