The Effect of BMD & Physical Fitness on Drinking & Cigarette Smoking Habit of Adult Males

Jaehyun Yoo 한국알코올과학회 2010 한국알코올과학회 학술대회 Vol.2010 No.1

Path planning for remotely controlled UAVs using Gaussian process filter

Jaehyun Yoo,H, Jin Kim,Karl H. Johansson 제어로봇시스템학회 2017 제어로봇시스템학회 국제학술대회 논문집 Vol.2017 No.10

Most of the recent results in control of unmanned aerial vehicles (UAVs) have focused on motion stability and navigation in well-structured environments, without considering communication delay influences. In order to deal with time delays and packet losses in networked UAVs, this paper suggests a machine learning based Gaussian process (GP) filter for a path planning problem. The developed GP filter estimates the UAV states accurately given delayed observation by learning the pattern of network-induced effects on UAV maneuvers. We validate that the GP filter produces the lower error rate than Kalman filter by analyzing error covariances. The proposed algorithm is evaluated on a collaborative trajectory tracking task for two networked-UAVs and the better control performance is achieved.

A Study of BMD & Health Related Physical Fitness Induced Drinking Habit on Pre & Post-Menopause of Female

Jaehyun Yoo 한국알코올과학회 2010 한국알코올과학회 학술대회 Vol.2010 No.1

Feature representation ofWi-Fi signal strength for indoor location awareness

Jaehyun Yoo 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10

A Wi-Fi received signal strength indicator (RSSI) collected from indoor area is a basic sensory observation for an indoor localization. One major flaw of the Wi-Fi RSSI indoor localization method is the issue of sparsity, where the majority of the elements in the RSSI database are empty. The main contribution of this paper is to present a feature representation approach to transform the sparse database to a compact database, which improves data-memory efficiency. First, a feature extraction method is developed to remove the meaningless data points by reducing dimensionality. Second, a machine learning algorithm is used to represent a likelihood distribution of the feature data over physical space. The transformed feature database is evaluated by position estimation compared to the original dataset. The experimental results show the better positioning accuracy of the feature data as well as the memory efficiency due to the dramatically reduced size of the database.

Thermocapillary flows on heated substrates with sinusoidal topography

Yoo, Jaehyun,Nam, Jaewook,Ahn, Kyung Hyun Cambridge University Press 2019 Journal of fluid mechanics Vol.859 No.-

<P>Two-dimensional steady thermocapillary flows in a liquid layer over a substrate, which has a uniform temperature and sinusoidal topography, are investigated by asymptotic theory. Here, the buoyancy effect is negligible and the interface is not significantly disturbed under low Marangoni number and low capillary number. A temperature gradient along the gas/liquid interface causes recirculating flows. For a small aspect ratio, which yields a sinusoidal topography with a long wavelength relative to the mean depth of the liquid layer, the second-order solutions are obtained analytically. The basic solutions show vertical diffusion of heat and vorticity from the substrate and interface, respectively. In the second corrections, the horizontal diffusion of heat weakens the overall flow and the convection of heat intensifies it.</P>

Indoor Localization Without a Prior Map by Trajectory Learning From Crowdsourced Measurements

Jaehyun Yoo,Johansson, Karl Henrik,Hyoun Jin Kim Institute of Electrical and Electronics Engineers 2017 IEEE transactions on instrumentation and measureme Vol.66 No.11

<P>Accommodation of a situation when a prior map is not available in an indoor localization system is valuable to cost-effective operations by removing a need for map drawing and map updating. This paper suggests a trajectory learning method using crowdsourced measurements in order to support the absence of map. A localization framework based on a particle filter is formalized by machine-learning-based feature extraction and Gaussian process (GP) regression. The feature extraction algorithm reduces dimensionality of sparse measurement vector, and it is applied to detect floor level and designated landmarks. Also, the combination of the feature extraction and the GP regression is used for modeling nonlinear relationship between location and measurement. By this combination, locations of Wi-Fi access points are not required to be known. From the field experimental results, we confirm that the detections of floor level and landmarks are accurate, the learned trajectories are close to the true map, and positioning accuracy is improved thanks to the learning-aided localization.</P>

Distributed estimation using online semi-supervised particle filter for mobile sensor networks

Yoo, Jaehyun,Kim, Woojin,Kim, Hyoun Jin IET 2015 IET CONTROL THEORY AND APPLICATIONS Vol.9 No.3

<P>This study proposes an improved particle filter by incorporating semi-supervised machine learning for location estimation in mobile sensor networks (MSNs). A time-varying prior model is learned online as the likelihood of particle filter in order to adapt to dynamic characteristics of state and observation. Thanks to semi-supervised learning, the proposed particle filter can improve efficiency and accuracy, where the amount of available labelled training data is limited. The authors compare the proposed algorithm with the particle filter based on supervised learning. The algorithms are evaluated for received signal strength indicator (RSSI)-based distributed location estimation for MSN in which communication bandwidth and accuracy of the range measurement are limited. First, experimental results show that the semi-supervised algorithm can learn suddenly-changed RSSI characteristics while the supervised learning cannot. Second, the proposed particle filter is more accurate and robust against variations of the environment such as new obstacle configurations. Furthermore, the suggested particle filter shows low statistical variability during repeated experiments, confirmed by much smaller error deviation than the compared particle filter.</P>

Effect of initial placement level and wall thickness on maintenance of the marginal bone level in implants with a conical implant-abutment interface: a 5-year retrospective study

Yoo, Jaehyun,Moon, Ik-Sang,Yun, Jeong-Ho,Chung, Chooryung,Huh, Jong-Ki,Lee, Dong-Won Korean Academy of Periodontology 2019 Journal of Periodontal & Implant Science Vol.49 No.3

Purpose: Implant wall thickness and the height of the implant-abutment interface are known as factors that affect the distribution of stress on the marginal bone around the implant. The goal of this study was to evaluate the long-term effects of supracrestal implant placement and implant wall thickness on maintenance of the marginal bone level. Methods: In this retrospective study, 101 patients with a single implant were divided into the following 4 groups according to the thickness of the implant wall and the initial implant placement level immediately after surgery: 0.75 mm wall thickness, epicrestal position; 0.95 mm wall thickness, epicrestal position; 0.75 mm wall thickness, supracrestal position; 0.95 mm wall thickness, supracrestal position. The marginal bone level change was assessed 1 day after implant placement, immediately after functional loading, and 1 to 5 years after prosthesis delivery. To compare the marginal bone level change, repeated-measures analysis of variance was used to evaluate the statistical significance of differences within groups and between groups over time. Pearson correlation coefficients were also calculated to analyze the correlation between implant placement level and bone loss. Results: Statistically significant differences in bone loss among the 4 groups (P<0.01) and within each group over time (P<0.01) were observed. There was no significant difference between the groups with a wall thickness of 0.75 mm and 0.95 mm. In a multiple comparison, the groups with a supracrestal placement level showed greater bone loss than the epicrestal placement groups. In addition, a significant correlation between implant placement level and marginal bone loss was observed. Conclusions: The degree of bone resorption was significantly higher for implants with a supracrestal placement compared to those with an epicrestal placement.

Comparison between Isokinetic Peak Torque and Isotonic 1RM on the Knee Joint

유재현(Jaehyun Yoo) 물리치료재활과학회 2023 Physical therapy rehabilitation science Vol.12 No.2

Objective: Resistance exercise is a necessary element to improve quality of life, and measurement and evaluation of muscle strength provide important information for prescription and management of rehabilitation and exercise programs. This study analyzed the correlation between direct and indirect 1RM for isokinetic maximum torque of the knee joint in order to provide useful information in the field of exercise programs. In addition, the flexion-extension ratio and the difference in left-right deviation were verified. Design: A cross-sectional studyMethods: The subjects of this study were 33 healthy adult men and women without medical problems who participated in the health exercise class program at S University in Seoul. The correlation between isokinetic maximum torque and direct and indirect 1RM was analyzed, and a dependent t-test was performed to analyze the flexion-extension ratio and left-right deviation. Results: There was a high correlation between the isokinetic maximum torque and direct and indirect 1RM, and no statistically significant difference was shown between the test methods in the analysis of the flexion-extension ratio and left-right deviation. Conclusions: Isokinetic muscle function measuring equipment is expensive, so it is difficult to use it in local exercise rehabilitation and training sites. Through this study, it was found that direct and indirect 1RM isokinetic maximum torque showed a high correlation, and there was no difference in evaluating muscle function such as flexion-extension ratio and left-right deviation. Therefore, it is considered that the muscle function evaluation using 1RM in general field can be usefully utilized.

스마트폰 로봇의 위치 인식을 위한 준 지도식 학습 기법

유재현(Jaehyun Yoo),김현진(H. Jin Kim) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.6

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.