• Journal of Radiation Protection and Research
• /
• 제34권3호
• /
• pp.137-143
• /
• 2009

본 연구는 호흡에 따라 움직임이 큰 흉부나 복부 장기의 방사선 수술에 적용되는 사이버나이프 $Synchrony^{TM}$ 호흡 추적장치의 정확성을 평가하였다. $Synchrony^{TM}$ 호흡 추적장치의 정확성 평가를 위해 금침이 삽입된 움직임 Phantom을 이용하였고, Phantom은 아크릴 볼이 들어 있는 정육면체에 Radiochromic 필름을 삽입하여 가상의 치료용적인 아크릴 볼에 21 Gy, 70% 등선량곡선으로 처방하였다. 고정된 Phantom의 금침추적방법과 움직임 Phantom의 $Synchrony^{TM}$ 호흡추적 방법으로 나누어 각각 5회 측정한 정확성 평가는 고정된 Phantom 추적 시 총 에러는 $0.0195{\sim}0.652mm$, 총 에러 평균은 0.3926 mm로 나타났으며, 움직임 Phantom을 이용한 $Synchrony^{TM}$ 호흡 추적 방법의 결과로 총 에러는 $0.4405{\sim}0.7665mm$, 총 에러 평균은 0.5673 mm로 나타나 두 방법에 유의한 차이가 없었다. 본 연구를 통해 사이버나이프 $Synchrony^{TM}$ 호흡 추적 장치의 정확성을 평가하였으며 체부의 방사선 수술 적용 시 그 유용성을 확인할수 있었다.

• 대한전기학회논문지
• /
• 제43권2호
• /
• pp.339-345
• /
• 1994

A new filter-bank is proposed in order to track center frequency of narrow band signal. The two banks are connected in series-parallel. The master filter bank which is made of traditional filter bank detects the center frequency roughly. And the performance for tracking center frequency is greatly improved by the slave filter bank which is based on energy-difference estimator. Computer simulations show that it achieves a good tracking accuracy.

• 한국항공우주학회지
• /
• 제39권1호
• /
• pp.25-32
• /
• 2011

항공관제용 감시자료 처리시스템에 의한 기동 표적 추적에 있어서 레이더의 측정 잡음 분산은 상태 추정기의 입력으로서, 추적 정확도에 영향을 주는 주요한 요소 중 하나이다. 본 연구에서는 레이더의 측정 잡음 분산을 상수가 아닌 변수로 지정하여, 다중 IMM 필터의 우도함수를 통해 매 시간 측정 잡음 분산을 실시간으로 추정하는 알고리즘을 제시하였다. Monte Carlo 시뮬레이션 결과 측정 잡음 분산 값을 실제 값 대비 5% 이내 수준으로 예측함을 확인하였고, 이를 통해 기동 표적 추적 성능을 향상시킬 수 있음을 확인하였다.

• 조명전기설비학회논문지
• /
• 제28권2호
• /
• pp.9-18
• /
• 2014

This paper proposes the fuzzy PI controller for maximum power point tracking(MPPT) control of photovoltaic system. The output characteristics of the solar cell are a nonlinear and affected by a temperature, the solar radiation. The MPPT control is a very important technique in order to increase an output and efficiency of the photovoltaic system. The conventional perturbation and observation(PO) and incremental conductance(IC) are the method which finding maximum power point(MPP) by the continued self-excitation vibration, and uses the fixed step size. If the fixed step size is a large, the tracking speed of maximum power point is faster, but the tracking accuracy in the steady state is decreased. On the contrary, when the fixed step size is a small, the tracking accuracy is increased and the tracking speed is slower. Therefore, this paper proposes the MPPT control using the fuzzy PI controller that can be improve a MPPT control performance. The fuzzy PI controller is adjusted a input of PI controller by fuzzy control and compensated a cumulative error of fuzzy control by PI controller. The fuzzy PI MPPT control is compared to conventional PO and IC MPPT method for various temperature and radiation condition. This paper proves the validity of the fuzzy PI controller using these results.

• 전기학회논문지
• /
• 제61권12호
• /
• pp.1864-1871
• /
• 2012

This paper proposes the hybrid proportional integral(HBPI) controller for maximum power point tracking(MPPT) control of photovoltaic system. The output characteristics of the solar cell are a nonlinear and affected by a temperature, the solar radiation and influence of a shadow. The MPPT control is a very important technique in order to increase an output and efficiency of the photovoltaic system. The conventional constant voltage(CV), perturbation and observation(PO) and incremental conductance(IC) are the method which finding maximum power point(MPP) by the continued self-excitation vibration, and uses the fixed step size. If the fixed step size is a large, the tracking speed of maximum power point is faster, but the tracking accuracy in the steady state is decreased. On the contrary, when the fixed step size is a small, the tracking accuracy is increased and the tracking speed is slower. Therefore, in order to solve these problems, this paper proposes HBPI controller that is adjusted gain of conventional PI control using fuzzy control, and the maximum power point tracks using this controller. The validity of the controller proposed in this paper proves through the results of the comparisons.

• Advances in nano research
• /
• 제12권2호
• /
• pp.223-239
• /
• 2022

Object detection has always been to pursue objects with particular properties or representations and to predict details on objects including the positions, sizes and angle of rotation in the current picture. This was a very important subject of computer vision science. While vision-based object tracking strategies for the analysis of competitive videos have been developed, it is still difficult to accurately identify and position a speedy small ball. In this study, deep learning (DP) network was developed to face these obstacles in the study of tennis motion tracking from a complex perspective to understand the performance of athletes. This research has used CNN-VGG 16 to tracking the tennis ball from broadcasting videos while their images are distorted, thin and often invisible not only to identify the image of the ball from a single frame, but also to learn patterns from consecutive frames, then VGG 16 takes images with 640 to 360 sizes to locate the ball and obtain high accuracy in public videos. VGG 16 tests 99.6%, 96.63%, and 99.5%, respectively, of accuracy. In order to avoid overfitting, 9 additional videos and a subset of the previous dataset are partly labelled for the 10-fold cross-validation. The results show that CNN-VGG 16 outperforms the standard approach by a wide margin and provides excellent ball tracking performance.

• International Journal of Contents
• /
• 제9권3호
• /
• pp.9-14
• /
• 2013

In this paper, we will examine single face tracking algorithms with scaling function in a mobile device. Face detection and tracking either in PC or mobile device with scaling function is an unsolved problem. Standard single face tracking method with particle filter has a problem in tracking the objects where the object can move closer or farther from the camera. Therefore, we create an algorithm which can work in a mobile device and perform a scaling function. The key idea of our proposed method is to extract the average of skin color in face detection, then we compare the skin color distribution between the detected face and the tracking face. This method works well if the face position is located in front of the camera. However, this method will not work if the camera moves closer from the initial point of detection. Apart from our weakness of algorithm, we can improve the accuracy of tracking.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2009년도 춘계학술대회 논문집
• /
• pp.412-415
• /
• 2009

This paper analyzes efficiency of photovoltaic(PV) tracking system using position solar algorithm(PSA). Solar location tracking system is needed for efficiently and intensively using PV system independent of environmental condition. PV tracking system of program method is presented a high tracking accuracy without the wrong operating in rapidly changed insolation by the clouds and atmospheric condition. Therefore, this paper analyzes efficiency of PV system using PSA algorithm for more correct position tracking of solar. Also, controlled altitude angle and azimuth angle by applied algorithm is compared with data of korea astronomy observatory. And this paper analyzes the tracking error and roves the validity of applied algorithm.

• 한국정보통신학회논문지
• /
• 제25권7호
• /
• pp.1000-1003
• /
• 2021

In this paper, we investigate how to track illegal drones by using communication signal received from illegal drones, which is a promising candidate position tracking scheme for anti-drone systems, and is particularly effective in tracking small illegal drones in urban areas. We propose an enhanced tracking scheme using multiple antennas to improve the performance of tracking by reducing the error of position tracking. In the proposed tracking scheme, a tracker is equipped with four receive antennas that are evenly spaced 90 degrees apart, and received signal strength indicators (RSSIs) received by four receive antennas are pre-averaged before being used to calculate the distance between tracker and target. Our numerical results show that the proposed scheme outperforms the conventional scheme in terms of accuracy.

• Journal of Platform Technology
• /
• 제11권4호
• /
• pp.3-12
• /
• 2023

포스트-코로나 시대에는 방역 조치의 중요성이 크게 강조되고 있으며, 이에 맞춰 딥러닝을 이용한 마스크 착용 상태 검출 및 다른 전염병 예방에 관련된 연구가 진행되고 있다. 그러나 질병 확산 방지를 위한 문화시설 관람객 탐지 및 추적 연구도 마찬가지로 중요하므로 이에 대한 연구가 진행되어야 한다. 본 논문에서는 사전 수집된 데이터 셋을 이용하여 컨볼루션 신경망 기반 객체 탐지 모델을 전이 학습시키고, 학습된 탐지 모델의 가중치를 다중 객체 추적 모델에 적용하여 방문객을 모니터링 한다. 방문객 탐지 모델은 Precision 96.3%, Recall 85.2% F1-Score 90.4%의 결과를 보여주었다. 추적 모델의 정량적 결과로 MOTA 65.6%, IDF1 68.3%. HOTA 57.2%의 결과를 보여주었으며, 본 논문의 모델과 다른 다중 객체 추적 모델 간의 정성적 비교에서 우수한 결과를 보여주었다. 본 논문의 연구는 포스트-코로나 시대의 문화시설 내 방역 시스템에 적용될 수 있을 것이다.