http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Mobile Robot Tracking using Kalman Filter-based Gaussian Process in Wireless Sensor Networks
Jinhong Lim,Jae Hyun Yoo,H. Jin Kim 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
RSSI-based localization has a variety of possible applications, and the environment to obtain the required information is well-constructed in these days due to the prevalence of WiFi usage. However, it is difficult to apply this method directly to the real-world positioning, because there are several factors of uncertainty in the signal strength measurements. In this paper, it is proposed to incorporate dead-reckoning using encoder measurement only, and Kalman filter-based Gaussian Process to compensate the uncertainty. As encoder itself is not able to calibrate the accumulating error, and the measured RSSI data has a time-varying error, the defects of respective methods can be complemented by each other using Kalman filter. The performance of the proposed method is evaluated by two different simulations. The location of a mobile robot moving through the exact desired path is estimated first. Then, the result of controlling a mobile robot based on the estimated position is shown.
Tracking of Multiple Moving Targets using Mobile Networks based on Mutual Information
Jinhong Lim,H. Jin Kim 제어로봇시스템학회 2016 제어로봇시스템학회 국제학술대회 논문집 Vol.2016 No.10
Tracking multiple targets is one of the important problems to make unmanned ground or aerial vehicles autonomously perform specific tasks. However, the tracking problem has several challenges due to factors such as limited field of view of sensors, unknown number of targets, and difficulty in predicting future movement of the targets. In this paper, the target tracking and estimation of the number of targets are performed using Gaussian mixture-probability hypothesis density (GM-PHD) filter, enhanced by Gaussian process-based motion model learning to predict movement of targets. Next, autonomous control framework of mobile networks is presented, maximizing mutual information between estimated target positions and measurements from sensors. The Gaussian process-based motion model learning enables more accurate estimation of GM-PHD filter for the targets with unknown dynamics. Besides, the mutual informationbased mobile networks control enables autonomous distribution of sensors to detect maximum number of targets. The performance of the framework is evaluated by simulation in terms of the expected number of targets detected by the mobile networks.
모바일 네트워크를 이용한 상호정보량 기반의 다수 이동 물체 추적 알고리즘 설계
임진홍(Jinhong Lim),김현진(H.Jin Kim) 제어로봇시스템학회 2017 제어·로봇·시스템학회 논문지 Vol.23 No.3
Tracking multiple moving targets involves many issues such as the sensors’ limited field of view, and the unknown number of targets with unknown dynamics. This paper performs multi-target tracking and target number estimation using a Gaussian mixture probability hypothesis density (GM-PHD) filter. Mutual information is calculated by approximate computation in nonparametric methods and the network of sensing robots is controlled to detect the maximum number of targets by maximizing the mutual information. In addition, we propose the motion pattern learning method using multiple Gaussian Process (GP) models to enhance the multi-target tracking performance for various types of movement by accurately predicting future target states. Among the multiple motion patterns learned in advance, the most proper pattern is assigned by the maximum likelihood principle. The performance of the proposed algorithm is validated via simulation in terms of the accuracy of target number estimation, and the reliability of multi-target tracking.
Jinhong Kim,Siwon Song,Jae Hyung Park,Seunghyeon Kim,Taeseob Lim,Hyungi Byun,Sang-Hun Shin,Bongsoo Lee 한국방사성폐기물학회 2022 한국방사성폐기물학회 학술논문요약집 Vol.20 No.1
In this study, the positions of Cs-137 gamma ray source are estimated from the plastic scintillating fiber bundle sensor with length of 5 m, using machine learning data analysis. Seven strands of plastic scintillating fibers are bundled by black shrink tube and two photomultiplier tubes are used as a gamma ray sensing and light measuring devices, respectively. The dose rate of Cs-137 used in this study is 6 μSv·h?1. For the machine learning modeling, Keras framework in a Python environment is used. The algorithm chosen to construct machine learning model is regression with 15,000 number of nodes in each hidden layer. The pulse-shaped signals measured by photomultiplier tubes are saved as discrete digits and each pulse data consists of 1,024 number of them. Measurements are conducted separately to create machine learning data used in training and test processes. Measurement times were different for obtaining training and test data which were 1 minute and 5 seconds, respectively. It is because sufficient number of data are needed in case of training data, while the measurement time of test data implies the actual measuring time. The machine learning model is designated to estimate the source positions using the information about time difference of the pulses which are created simultaneously by the interaction of gamma ray and plastic scintillating fiber sensor. To evaluate whether the double-trained machine learning model shows enhancement in accuracy of source position estimation, the reference model is constructed using training data with one-time learning process. The double-trained machine learning model is designed to construct first model and create a second training data using the training error and predetermined coefficient. The second training data are used to construct a final model. Both reference model and double-trained models constructed with different coefficients are evaluated with test data. The evaluation result shows that the average values calculated for all measured position in each model are different from 7.21 to 1.44 cm. As a result, by constructing the double-trained machine learning model, the final accuracy shows 80% of improvement ratio. Further study will be conducted to evaluate whether the double-trained machine learning model is applicable to other data obtained from measurement of gamma ray sources with different energy and set a methodology to find optimal coefficient.
Analysis of Sensing Mechanisms in a Gold-Decorated SWNT Network DNA Biosensor
Jinhong Ahn,Seok Hyang Kim,Jaeheung Lim,Jung Woo Ko,Chan Hyeong Park,Young June Park 대한전자공학회 2014 Journal of semiconductor technology and science Vol.14 No.2
We show that carbon nanotube sensors with gold particles on the single-walled carbon nanotube (SWNT) network operate as Schottky barrier transistors, in which transistor action occurs primarily by varying the resistance of Au-SWNT junction rather than the channel conductance modulation. Transistor characteristics are calculated for the statistically simplified geometries, and the sensing mechanisms are analyzed by comparing the simulation results of the MOSFET model and Schottky junction model with the experimental data. We demonstrated that the semiconductor MOSFET effect cannot explain the experimental phenomena such as the very low limit of detection (LOD) and the logarithmic dependence of sensitivity to the DNA concentration. By building an asymmetric oncentricelectrode model which consists of serially-connected segments of CNTFETs and Schottky diodes, we found that for a proper explanation of the experimental data, the work function shifts should be ~ 0.1 eV for 100 pM DNA concentration and ~ 0.4 eV for 100 μM.