http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
스케일 불변 특징을 이용한 이동 로봇의 위치 추정 및 매핑
이종실,신동범,권오상,이응혁,홍승홍,Lee, Jong-Shill,Shen, Dong-Fan,Kwon, Oh-Sang,Lee, Eung-Hyuk,Hong, Seung-Hong 한국전기전자학회 2005 전기전자학회논문지 Vol.9 No.1
로봇이 자율주행을 하는데 있어 중요한 요소는 로봇 스스로 위치를 추정하고 동시에 주위 환경에 대한 지도를 작성하는 것이다 본 논문에서는 스케일 불변 특정을 이용한 비전 기반 위치 추정 및 매핑 알고리즘을 제안한다. 로봇에 어안렌즈가 부착된 카메라를 천정을 바라볼 수 있도록 부착하여 스케일 불변 특정을 갖는 고급의 영상 특정을 구하여 맹 빌딩과 위치 추정을 수행한다. 먼저, 전처리 과정으로 어안렌즈를 통해 입력된 영상을 카메라 보정을 행하여 축방향 왜곡을 제거하고 레이블링과 컨벡스헐을 적용하여 천정영역과 벽영역으로 분할한다 최초 맵 빌딩시에는 분할된 영역에 대해 특정점을 구하고 맵 데이터베이스에 저장한다. 맵 빌딩이 종료될 때까지 연속하여 입력되는 영상에 대해 특정점들을 구하고 이미 작성된 맵과 매칭되는 점들을 찾고 매칭되지 않은 점들에 대해서는 기존의 맴에 추가하는 과정을 반복한다. 위치 추정은 맵 빌딩과정에서 매칭되는 점들을 찾을 때 동시에 수행되어 진다. 그리고 임의의 위치에서 기존의 작성된 맵과 매칭되는 점들을 찾음으로서 위치 추정이 행해지며 동시에 기존의 맵 데이터베이스의 특정점들을 갱신하게 된다. 제안한 방법은 $50m^2$의 영역에 대해 맵 빌딩을 2 분내에 수행할 수 있었으며, 위치의 정확도는 ${\pm}13cm$, 위치에 대한 로봇의 자세(각도)는 ${\pm}3$도의 오차를 갖는다. A key component of an autonomous mobile robot is to localize itself accurately and build a map of the environment simultaneously. In this paper, we propose a vision-based mobile robot localization and mapping algorithm using scale-invariant features. A camera with fisheye lens facing toward to ceiling is attached to the robot to acquire high-level features with scale invariance. These features are used in map building and localization process. As pre-processing, input images from fisheye lens are calibrated to remove radial distortion then labeling and convex hull techniques are used to segment ceiling region from wall region. At initial map building process, features are calculated for segmented regions and stored in map database. Features are continuously calculated from sequential input images and matched against existing map until map building process is finished. If features are not matched, they are added to the existing map. Localization is done simultaneously with feature matching at map building process. Localization. is performed when features are matched with existing map and map building database is updated at same time. The proposed method can perform a map building in 2 minutes on $50m^2$ area. The positioning accuracy is ${\pm}13cm$, the average error on robot angle with the positioning is ${\pm}3$ degree.
의복형 초소형 발광모듈을 이용한 신경근육 자극 시스템 개발 및 임상적 효과 검증
박세형,이종실,김인영,김선일,Park, Se-Hyeong,Lee, Jong-Shill,Kim, In-Young,Kim, Sun-I. 대한의용생체공학회 2009 의공학회지 Vol.30 No.1
It can be used easily to reduce rehabilitation and treatment time if diagnostic and therapeutic devices are attached to cloth or body. Therefore we developed neuromuscular wearable ultra-miniature lighting modules which can improve the neuromuscular function and verified its clinical effectiveness. The system is based on the ultra-miniature lighting treatment module and there are two types of systems. One of them is designed as an attached type and the other type is combined with clothing. The wearable ultra-miniature lighting module is composed of controller (battery, MCU, bidirectional transmitter and receiver), cable, treatment medium generating device and other peripheral devices. To verify the clinical effectiveness of this device, we observed the difference of the strength of a muscle before and after 650nm and 25mW laser irradiation on the reflex point for 1 to 4 seconds. Among 48 patients having the degenerative osteoarthritis, the muscle strength before and after irradiation of laser was $21.8{\pm}7.99$ and $27.3{\pm}8.43$. According to the result, the muscle strength after treatment was significantly increased (p<0.01). To whom having difficulty in visiting to OPD(Out-Patient Department), doctors medically examine the patients and find the therapeutic point, attachment of this wearable ultra-miniature lighting module can function as self treatment (treating instrument) and treatment assist at home. If doctor can remotely control the patient and take part in treatment, the therapeutic device could contribute to prevention and care device.
혈압측정시 가압 단계에서 목표압력 및 측정 종료압력 추정
오홍식,이종실,김영수,신동범,김인영,지영준,Oh, Hong-Sic,Lee, Jong-Shill,Kim, Young-Soo,Shen, Dong-Fan,Kim, In-Young,Chee, Young-Joan 대한의용생체공학회 2008 의공학회지 Vol.29 No.5
In blood pressure measurement, the oscillometric method detects and analyzes the pulse pressure oscillation while deflating the cuff around the arm. For its principle, one has to inflate cuff pressure above the subject's systolic pressure and deflate below the diastolic pressure. Most of the commercialized devices inflate until the fixed target pressure and deflate until the fixed completion pressure because there is no way to know the systolic and diastolic pressure before measurement. Too high target pressure makes stress to the subject and too low target pressure makes big error or long measurement time because of re-inflation. There are similar problems for inadequate completion pressure. In this study, we suggest new algorithm to set proper target and completion pressure for each subject by analyzing pressure waveform while inflating period. We compared our proposed method and auscultation method to see the errors of estimation. The differences between the two measurements were -4.02$\pm$4.80mmHg, -10.50$\pm$10.57mmHg and -0.78$\pm$5.l7mmHg for mean arterial pressure, systolic pressure and diastolic pressure respectively. Consequently, we could set the target pressure by 30 mmHg higher than our estimation and we could stop at 20mmHg lower than our estimated diastolic pressure. Using this method, we could reduce the measurement time.
특징점 선택방법과 SVM 학습법을 이용한 당뇨병 데이터에서의 당뇨병성 신장합병증의 예측
조백환,이종실,지영준,김광원,김인영,김선일,Cho, Baek-Hwan,Lee, Jong-Shill,Chee, Young-Joan,Kim, Kwang-Won,Kim, In-Young,Kim, Sun-I. 대한의용생체공학회 2007 의공학회지 Vol.28 No.3
Diabetes mellitus can cause devastating complications, which often result in disability and death, and diabetic nephropathy is a leading cause of death in people with diabetes. In this study, we tried to predict the onset of diabetic nephropathy from an irregular and unbalanced diabetic dataset. We collected clinical data from 292 patients with type 2 diabetes and performed preprocessing to extract 184 features to resolve the irregularity of the dataset. We compared several feature selection methods, such as ReliefF and sensitivity analysis, to remove redundant features and improve the classification performance. We also compared learning methods with support vector machine, such as equal cost learning and cost-sensitive learning to tackle the unbalanced problem in the dataset. The best classifier with the 39 selected features gave 0.969 of the area under the curve by receiver operation characteristics analysis, which represents that our method can predict diabetic nephropathy with high generalization performance from an irregular and unbalanced dataset, and physicians can benefit from it for predicting diabetic nephropathy.
오홍식,이종실,지영준,김인영,Oh, Hong-Sic,Lee, Jong-Shill,Chee, Young-Joon,Kim, In-Young 대한의용생체공학회 2010 의공학회지 Vol.31 No.5
In the automatic non-invasive blood pressure measurement device, the oscillometric method iswidely used. In the oscillometric method, the step-wise deflation has the advantage of the robustness for the motion artifacts than the linear deflation method. But it has the disadvantage of its longer measurement time because we need to detect two or more pulses in a certain cuff pressure step. In this study, we suggest the modified step-wise deflation method to overcome this limitation while maintaining the general concept of step-wise deflation. Using one valid pulse in each step and the deflating valve control during the diastolic period, the measurement time could be reduced. In order to verify the accuracy of the proposed algorithm, we compared the blood pressure values from the suggested method and the blood pressure values from the conventional auscultation method. The mean and standard deviation were -0.50${\pm}$5.3mmHg and 2.08${\pm}$4.75mmHg, for systolic and diastolic blood pressure respectively. The measurement time can be reduced up to the half of conventional step-wise deflation method.
강정훈,조백환,이종실,지영준,김인영,김선일,Kang, Joung-Hoon,Cho, Baek-Hwan,Lee, Jong-Shill,Chee, Young-Joon,Kim, In-Young,Kim, Sun-I. 대한의용생체공학회 2007 의공학회지 Vol.28 No.3
With the convergence of ubiquitous networking and medical technologies, ubiquitous healthcare(U-Healthcare) service has come in our life, which enables a patient to receive medical services at anytime and anywhere. In the u-Healthcare environment, intelligent real-time biosignal aquisition/analysis techniques are inevitable. In this study, we propose a motion artifact cancelation method in portable photoplethysmography(PPG) signal aquisition using an accelerometer and an adaptive filter. A preliminary experiment represented that the component of the pedestrian motion artifact can be found under 5Hz in the spectral analysis. Therefore, we collected PPG signals under both simulated conditions with a motor that generates circular motion with uniform velocity (from 1 to 5Hz) and a real walking condition. We then reduced the motion artifact using a recursive least square adaptive filter which takes the accelerometer output as a noise reference. The results showed that the adaptive filter can remove the motion artifact effectively and recover peak points in PPG signals, which represents our method can be useful to detect heart rate in real walking condition.
계층구조적 분류모델을 이용한 심전도에서의 비정상 비트 검출
이도훈,조백환,박관수,송수화,이종실,지영준,김인영,김선일,Lee, Do-Hoon,Cho, Baek-Hwan,Park, Kwan-Soo,Song, Soo-Hwa,Lee, Jong-Shill,Chee, Young-Joon,Kim, In-Young,Kim, Sun-Il 대한의용생체공학회 2008 의공학회지 Vol.29 No.6
The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.