http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 최지석 (검색결과 29 건)
- 무료
- 기관 내 무료
- 유료
-
-
9축 IMU기반 자세 추정을 위한 순환 신경망: 교란조건에서의 3차원 자세 추정 성능
최지석,이정근 제어·로봇·시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.12
The estimation of 3D orientation based on nine-axis inertial measurement unit (IMU) is an essential technology in various applications, from unmanned aerial vehicle to human motion tracking. Various sensor fusion filter algorithms such as Kalman filter (KF) or complementary filter (CF) have been proposed for accurate 3D orientation estimation. However, the degradation of estimation performance due to disturbance components such as magnetic distortion and external acceleration is still a critical issue. An alternative approach for the orientation estimation task is to train a neural network end-to-end with a variety of massive experimental datasets consisting of the raw IMU signals and the ground truth orientations. This paper proposes a recurrent neural network (RNN) for robust IMU-based 3D orientation estimation. Overall, this paper is an extension of the previous work by Weber et al., where the RNN model was used to estimate the quaternion, but only the attitude estimation performance was investigated without considering the heading estimation. The proposed RNN receives a nine-dimensional sensor signal as an input and outputs a unit quaternion representing 3D orientation, and it can robustly estimate the orientation across various motion characteristics and magnetic environments without needing an additional filter algorithm. Verification results showed that the proposed method outperformed the conventional CF and KF algorithms. In particular, in magnetically disturbed conditions, the averaged root mean square error of the proposed RNN approach was reduced by 41.4% and 60.3%, respectively, when compared to the CF and the KF algorithm. .
-
IMU 기반 자세 추정 칼만필터에서 공분산 모델링이 추정 정확도에 미치는 영향
최지석,이정근 한국센서학회 2020 센서학회지 Vol.29 No.6
A well-known difficulty in attitude estimation based on inertial measurement unit (IMU) signals is the occurrence of external acceleration under dynamic motion conditions, as the acceleration significantly degrades the estimation accuracy. Lee et al. (2012) designed a Kalman filter (KF) that could effectively deal with the acceleration issue. Ahmed and Tahir (2017) modified this method by adjusting the acceleration-related covariance matrix because they considered covariance modeling as a pivotal factor in the estimation accuracy. This study investigates the effects of covariance modeling on estimation accuracy in an IMU-based attitude estimation KF. The method proposed by Ahmed and Tahir can be divided into two: one uses the covariance including only diagonal components and the other uses the covariance including both diagonal and off-diagonal components. This paper compares these three methods with respect to the motion condition and the window size, which is required for the methods by Ahmed and Tahir. Experimental results showed that the method proposed by Lee et al. performed the best among the three methods under relatively slow motion conditions, whereas the modified method using the diagonal covariance with a high window size performed the best under relatively fast motion conditions.
-
관성센서 기반 상대위치 추정 시 연조직 변형 보상을 위한 인공신경망 적용
최지석,이정근 한국정밀공학회 2022 한국정밀공학회지 Vol.39 No.3
Relative position estimation between body segments is one essential process for inertial sensor-based human motion analysis. Conventionally, the relative position was calculated through a constant segment to joint (S2J) vector and the orientation of the segment, assuming that the segment was rigid. However, the S2J vector is deformed by soft tissue artifact (STA) of the segment. In a previous study, in order to handle the above problem, Lee and Lee proposed the relative position estimation method using time-varying S2J vectors based on inertial sensor signals. Here, time-varying S2J vectors were determined through the joint flexion angle using regression. However, it was not appropriate to consider only the flexion angle as a deformation-related variable. In addition, regression has limitations in considering complex joint motion. This paper proposed artificial neural network models to compensate for the STA by considering all three-axis motion of the joint. A verification test was conducted for lower body segments. Experimental results showed that the proposed method was superior to the previous method. For pelvis-to-foot relative position estimation, averaged root mean squared error of the previous method was 17.38 mm, while that of the proposed method was 12.71 mm.
-
-
순환 신경망을 이용한 착용형 관성센서기반 하지 관절 역학 추정
최지석,이창준,이정근 한국정밀공학회 2023 한국정밀공학회지 Vol.40 No.8
Recently, the estimation of joint kinetics such as joint force and moment using wearable inertial sensors has received great attention in biomechanics. Generally, the joint force and moment are calculated though inverse dynamics using segment kinematic data, ground reaction force, and moment. However, this approach has problems such as estimation error of kinematic data and soft tissue artifacts, which can lead to inaccuracy of joint forces and moments in inverse dynamics. This study aimed to apply a recurrent neural network (RNN) instead of inverse dynamics to joint force and moment estimation. The proposed RNN could receive signals from inertial sensors and force plate as input vector and output lower extremity joints forces and moments. As the proposed method does not depend on inverse dynamics, it is independent of the inaccuracy problem of the conventional method. Experimental results showed that the estimation performance of hip joint moment of the proposed RNN was improved by 66.4% compared to that of the inverse dynamics-based method.
-
자속유도기의 두께 및 위치 변화에 따른 자동차용 BALL STUD의 고주파열처리 경화 깊이에 관한 연구
최지석,이무연,이상호 한국품질경영학회 2018 한국품질경영학회 학술대회 Vol.2018 No.-
자속유도기는 자장을 차단하는 연자성 분말을 소결 가공한 차폐재로, 고주파 열처리 코일에 부착하면 부착 부위의 자장을 차단하게 되고 개방된 부분에 자장을 집중시키는 역할을 한다. 이를 통해 고주파 열처리 코일에서 발생하는 전자력선을 제어할 수 있는데, 자속유도기에 대한 국내 연구가 미흡하며, 코일 제작시 시행착오를 통한 현장맞춤식 설계로 코일을 제작하고 있는 실정으로 효과적인 자속유도기 설계 기준이 요구되고 있다. 본 연구는 고주파 열처리 산업의 주요 구성요소인 고주파열처리 코일의 자속유도기의 두께 및 위치 변화에 따른 자동차용 BALL STUD의 고주파열처리 경화 깊이를 비교 분석해 보고, 전자력선의 정밀한 제어를 통해 BALL STUD 고주파 열처리시 품질관리가 용이하도록 자속유도기 설계기준을 제시하고자 한다. 실험은 자동차 서스펜션 시스템에 사용되는 SCM435소재 BALL STUD의 구와 목 부위를 고주파 열처리하는 코일을 대상으로 선정하여 주파수 100Khz 고주파설비에서 가열시간을 4초로 동일하게 수행하였다. BALL STUD와 코일간의 간극은 2mm로 제작, 설치하였다. 첫 번째로 자속유도기의 두께를 1~10mm로 부착하여 열처리했을 때 각 조건별 샘플 10ea의 경화 깊이를 측정하고 두 번째로 자속유도기의 부착 위치마다 두께 1~10mm로 달리하여 열처리했을 때 각 조건별 샘플 10ea의 경화 깊이를 측정하였다. 본 연구는 100Khz 고주파 설비에서 고주파열처리 코일에 자속유도기 부착시 전자력선 조정에 효과적인 두께와 부착위치를 제시한다. 또한, 자속유도기 두께와 부착위치에 따른 고주파열처리 경화 깊이 데이터를 통해, 하나의 고주파열처리 코일에 자속유도기 부착을 달리하여 각각 다른 형상의 BALL STUD를 고주파열처리 할 수 있는 공용 코일의 설계 기준을 제시한다.
-
최지석 ( Ji Seok Choi ) 한국동굴학회 2008 동굴 Vol.84 No.-
Jeju Island is formed by lava flow streams with the Mt. Halla in the center. The Mt. Halla`s crater or other parasitic volcano produced lava flows creating lava plateau in this area. There are one thousand volcano caves in the world, and 50% of them are located in the west coast of United States. There are 186 volcano caves in Italy, 100 in Mt. Fuji, Japan, and 70 in Jeju Island. Jeju Island`s east-west axis four sides are world-renown volcano zones with basalt strata that feature low viscosity and fluidity.
-
최지석(Ji Seok Choi),이정근(Jung Keun Lee) Korean Society for Precision Engineering 2022 한국정밀공학회지 Vol.39 No.2
Relative position estimation between body segments is one essential process for inertial sensor-based human motion analysis. Conventionally, the relative position was calculated through a constant segment to joint (S2J) vector and the orientation of the segment, assuming that the segment was rigid. However, the S2J vector is deformed by soft tissue artifact (STA) of the segment. In a previous study, in order to handle the above problem, Lee and Lee proposed the relative position estimation method using time-varying S2J vectors based on inertial sensor signals. Here, time-varying S2J vectors were determined through the joint flexion angle using regression. However, it was not appropriate to consider only the flexion angle as a deformation-related variable. In addition, regression has limitations in considering complex joint motion. This paper proposed artificial neural network models to compensate for the STA by considering all three-axis motion of the joint. A verification test was conducted for lower body segments. Experimental results showed that the proposed method was superior to the previous method. For pelvis-to-foot relative position estimation, averaged root mean squared error of the previous method was 17.38 mm, while that of the proposed method was 12.71 mm.
-
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
