• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.37-44
• /
• 2008

Data stream has the tendency to change in Patterns over time. Also known as concept drift, such problem can reduce the predictive performance of a classification model CVFDT and IOLIN tried to solve the problem of a concept drift through incremental classification model updates. The local changes in patterns. however was revealed to be unable to resolve the problems of local concept drift that occurs by influencing on total classification results. In this paper, we propose adapted IOLIN system that improves system's predictive performance by detecting the local concept drift. The experimental result shows that adaptive IOLIN, the Proposed method, is about 2.8% in accuracy better than IOLIN and about 11.2% in accuracy better than CVFDT.

• Journal of Korea Game Society
• /
• v.18 no.3
• /
• pp.71-78
• /
• 2018

Screen-based games often go to many places to install. In this case, there may be a change in the sensor or a difficulty in installation due to a difference in space configuration. Also, it is meaningful to experience the same thing as a real game, but there are cases where it is necessary to control the degree of difficulty to make it feel more fun. In this paper In the process of developing a screen archery game, which is a sensible game similar to screen golf, we will introduce a technique that facilitates installation according to changes in space. And we will explain how to control game difficulty automatically according to user's skill. And we will show you the results of the experiment.

• Proceedings of the KIEE Conference
• /
• 2005.04a
• /
• pp.191-193
• /
• 2005

This paper presents Hybrid PI controller of IPMSM drive using fuzzy adaptive mechanism(FAM) control. To increase the robustness, fixed gam PI controller, Hybrid PI controller proposes a new method based self tuning PI controller. Hybrid PI controller is developed to minimize overshoot and settling time following sudden parameter changes such as speed, load torque, inertia, rotor resistance and self inductance. The results on a speed controller of IPMSM are presented to show the effectiveness of the proposed gain tuner. And this controller is better than the fixed gains one in terms of robustness, even under great variations of operating conditions and load disturbance.

• Journal of Communications and Networks
• /
• v.13 no.4
• /
• pp.319-326
• /
• 2011

Beamforming techniques have been successfully utilized for traffic channels in order to solve the interference problem. However, their use for control channels has not been sufficiently investigated. In this paper, a (semi-) centralized beamforming strategy that adaptively changes beam patterns and controls the total transmit power of cells is proposed for the performance enhancement of the common channel in hierarchical cell structure (HCS) networks. In addition, some examples of its practical implementation with low complexity are presented for two-tier HCS networks consisting of macro and pico cells. The performance of the proposed scheme has been evaluated through multi-cell system-level simulations under optimistic and pessimistic interference scenarios. The cumulative distribution function of user geometry or channel quality has been used as a performance metric since in the case of common control channel the number of outage users is more important than the sum rate. Simulation results confirm that the proposed scheme provides a significant gain compared to the random beamforming scheme as well as conventional systems that do not use the proposed algorithm. Finally, the proposed scheme can be applied simultaneously to several adjacent macro and pico cells even if it is designed primarily for the pico cell within macro cells.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.686-699
• /
• 2020

In this paper, we propose a supervised-learning-based spatial performance prediction (SLPP) framework for next-generation heterogeneous communication networks (HCNs). Adaptive asset placement, dynamic resource allocation, and load balancing are critical network functions in an HCN to ensure seamless network management and enhance service quality. Although many existing systems use measurement data to react to network performance changes, it is highly beneficial to perform accurate performance prediction for different systems to support various network functions. Recent advancements in complex statistical algorithms and computational efficiency have made machine-learning ubiquitous for accurate data-based prediction. A robust network performance prediction framework for optimizing performance and resource utilization through a linear discriminant analysis-based prediction approach has been proposed in this paper. Comparison results with different machine-learning techniques on real-world data demonstrate that SLPP provides superior accuracy and computational efficiency for both stationary and mobile user conditions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.131-133
• /
• 2014

본 논문에서는 서비스업의 매장에 설치된 POS(Point of sale) 또는 Smart device를 이용하여 빈 방 또는 빈 테이블 등의 서비스 가능 공간 수에 따라 실시간으로 가격이 변동되는 시스템을 제안한다. 고객 입장에서는 보다 싼 가격으로 서비스를 이용할 수 있으며, 매장주 입장에서는 한산한 시간에 경쟁력 있는 가격으로 고객을 유치할 수 있도록 도움을 준다. 고객은 애플리케이션에 접속하여 위치기반서비스를 통해 이용하고자하는 서비스 매장을 선택하여 실시간으로 변동되는 서비스 가격을 확인할 수 있으며, 예약 및 결제를 한 후, 일정 시간 내에 해당 매장에 가서 서비스를 이용할 수 있다. 매장주는 POS 또는 Smart device를 통해 자동 또는 수동으로 서비스 가격을 변동시킬 수 있다.

• Journal of Positioning, Navigation, and Timing
• /
• v.5 no.1
• /
• pp.1-9
• /
• 2016

Range-based wireless localization system must measure accurate range between a mobile node (MN) and reference nodes. However, non-line-of-sight (NLOS) error caused by the spatial structures disturbs the localization system obtaining the accurate range measurements. Localization methods using the range measurements including NLOS error yield large localization error. But filter-based localization methods can provide comparatively accurate location solution. Motivated by the accuracy of the filter-based localization method, a filter residual-based NLOS error estimation method is presented in this paper. Range measurement-based residual contains NLOS error. By considering this factor with NLOS error properties, NLOS error is mitigated. Also a process noise covariance matrix tuning method is presented to reduce the time-delay estimation error caused by the single dynamic model-based filter when the speed or moving direction of a MN changes, that is the used dynamic model is not fit the current dynamic of a MN. The presented methods are evaluated by simulation allowing direct comparison between different localization methods. The simulation results show that the presented filter is more accurate than the iterative least squares- and extended Kalman filter-based localization methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.3
• /
• pp.489-497
• /
• 2009

Most of existent blind watermarking methods in frequency domain use coefficient relationship to detect the watermark without original image. But the change in coefficient values occurred when the original image was attacked by lossy JPEG compression or noise addition. So robustness of watermark detection was weaken. In order to solve these problems, this paper presents a robust watermarking method, which enables multiple watermark insertion. Also, in order to reduce errors in the detected value of watermarks according to small changes in the coefficient relationship when detecting watermarks, it set the change guard value for variation of the coefficients. The experimental results show that the proposed method has good image quality and is robust to various attacks such as the JPEG lossy compression, noise addition, etc.

• Journal of Sensor Science and Technology
• /
• v.20 no.2
• /
• pp.118-123
• /
• 2011

Heart related diseases mainly caused by heavy work load and increasing stress in human daily life. Therefore, researches on mobile healthcare monitoring for daily life has been carried out. Notably, wearable healthcare monitoring system which has least restriction has been tried to provide an emergency alert of abnormal heart rate. In this study, we developed chair type unconstrained BCG measurement system which able to perform continuous heart status monitoring at the office and daily life in the unconstrained way. Furthermore, adaptive threshold is used to detect the heart rate from BCG signals. The HRV(heart rate variability) is calculated from heart rate interval. ECG signal measured using conventional method and BCG signal measured using unconstraint system are carried out simultaneously for the purpose of performance evaluation. From the comparison result, BCG signal shows a similar heart beat characteristic as ECG signal. This proves the possibility of practical implementation of unconstraint healthcare monitoring system. In addition, medical examination like valsalva maneuver is performed to observe the changes in HRV due to stress. By performing valsalva maneuver, heart is said to be placed under an artificial physical stress condition. Under this artificial physical stress condition, the time and frequency domain of HRV parameters are evaluated.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.55-60
• /
• 2016

Mobility of the sensor networks proposed a new way to the efficient design of sensor networks and improvement of network system performance. Mobility results in a number of functional changes in the MAC protocol and routing protocol. Especially, the mobility of the nodes may occur the increase of the overhead of transmission or disconnection of the link. Therefore, the study of the energy efficient transmission is very important in mobile sensor networks. This paper proposed adaptive transmission mechanism on the distance-based power control. The proposed mechanism was analyzed better than conventional method in the average energy consumption and network life by simulation results.