http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Recognition of Basic Motions for Snowboarding using AHRS
Ki-Hyeon Kwon(권기현),Hyung-Bong Lee(이형봉) 韓國컴퓨터情報學會 2016 韓國컴퓨터情報學會論文誌 Vol.21 No.3
Internet of Things (IoT) is widely used for biomechanics in sports activities and AHRS(Attitude and Heading Reference System) is a more cost effective solution than conventional high-grade IMUs (Inertial Measurement Units) that only integrate gyroscopes. In this paper, we attach the AHRS to the snowboard to measure the motion data like Air To Fakie, Caballerial and Free Style. In order to reduce the measurement error, we have adopted the sensors equipped with Kalman filtering and also used Euler angle to quaternion conversion to reduce the Gimbal-lock effect. We have tested and evaluated the accuracy and execution time of the pattern recognition algorithms like PCA, ICA, LDA, SVM to show the recognition possibility of it on the basic motions of Snowboarding from the 9-axis trajectory information which is gathered from AHRS sensor. With the result, PCA, ICA have low accuracy, but SVM have good accuracy to use for recognition of basic motions of Snowboarding.
Multi Behavior Learning of Lamp Robot based on Q-learning
Ki-Hyeon Kwon(권기현),Hyung-Bong Lee(이형봉) 한국디지털콘텐츠학회 2018 한국디지털콘텐츠학회논문지 Vol.19 No.1
The Q-learning algorithm based on reinforcement learning is useful for learning the goal for one behavior at a time, using a combination of discrete states and actions. In order to learn multiple actions, applying a behavior-based architecture and using an appropriate behavior adjustment method can make a robot perform fast and reliable actions. Q-learning is a popular reinforcement learning method, and is used much for robot learning for its characteristics which are simple, convergent and little affected by the training environment (off-policy). In this paper, Q-learning algorithm is applied to a lamp robot to learn multiple behaviors (human recognition, desk object recognition). As the learning rate of Q-learning may affect the performance of the robot at the learning stage of multiple behaviors, we present the optimal multiple behaviors learning model by changing learning rate.
Quality Inspection of Dented Capsule using Curve Fitting-based Image Segmentation
Ki-Hyeon Kwon(권기현),Hyung-Bong Lee(이형봉) 한국컴퓨터정보학회 2016 韓國컴퓨터情報學會論文誌 Vol.21 No.12
Automatic quality inspection by computer vision can be applied and give a solution to the pharmaceutical industry field. Pharmaceutical capsule can be easily affected by flaws like dents, cracks, holes, etc. In order to solve the quality inspection problem, it is required computationally efficient image processing technique like thresholding, boundary edge detection and segmentation and some automated systems are available but they are very expensive to use. In this paper, we have developed a dented capsule image processing technique using edge-based image segmentation, TLS(Total Least Squares) curve fitting technique and adopted low cost camera module for capsule image capturing. We have tested and evaluated the accuracy, training and testing time of the classification recognition algorithms like PCA(Principal Component Analysis), ICA(Independent Component Analysis) and SVM(Support Vector Machine) to show the performance. With the result, PCA, ICA has low accuracy, but SVM has good accuracy to use for classifying the dented capsule.
Kwon, Ki Young,Kim, Jae Hyun,Youn, Jongkyu,Jeon, Chulmin,Lee, Jinwoo,Hyeon, Taeghwan,Park, Hyun Gyu,Chang, Ho Nam,Kwon, Yongchai,Ha, Su,Jung, Hee‐,Tae,Kim, Jungbae WILEY‐VCH Verlag 2014 Electroanalysis Vol.26 No.10
<P><B>Abstract</B></P><P>A simple study using a fixed amount of mesoporous carbon (MSU‐F‐C) was performed for the comparison of pyranose oxidase (POx) and glucose oxidase (GOx) in their electrochemical performance under biosensor and biofuel cell operating modes. Even though the ratio of POx to GOx in the glucose oxidation activity per unit weight of MSU‐F‐C was 0.35, the ratios of POx to GOx in sensitivity and power density were reversed to be 6.2 and 1.4, respectively. POx with broad substrate specificity and an option of large scale production using recombinant <I>E. coli</I> has a great potential for various electrochemical applications, including biofuel cells.</P>
A New Waxy Rice Cultivar with Multiple Disease Resistance and High Yield, "Boseogchal"
Ki Yong Ha,Ki Young Kim,Jong Cheol Ko,Man Gee Baek,Jae Kil Lee,Jae Kwon Ko,Bo Kyeong Kim,Jeong Kwon Nam,Jin Il Choung,So Hyeon Baek,Yeong Doo Kim,Chung Kon Kim,Kwang Yong Jung 한국육종학회 2006 한국육종학회지 Vol.38 No.4
Boseogchal is a newjaponica rice cultivar developed from the three-way cross ofHwayoung, Tamjin and Sinseonchalat Honam Agricultural Research Institute (HARI), RDA, in 2004. It is a waxy rice with about 117 days of growth duration fromtransplanting to har
Performance evaluation of Edge-based Method for classification of Gelatin Capsules
Ki-Hyeon Kwon(권기현),In-Soo Choi(최인수) 한국디지털콘텐츠학회 2017 한국디지털콘텐츠학회논문지 Vol.18 No.1
In order to solve problems in automatic quality inspection of tablet capsules, computation-efficient image processing technique, appropriate threshold setting, edge detection and segmentation methods are required. And since existing automatic system for quality inspection of tablet capsules is of very high cost, it needs to be reduced through the realization of low-price hardware system. This study suggests a technique that uses low-cost camera module to obtain image and inspects dents on tablet capsules and sorting them by applying TLS curve fitting technique and edge-based image segmentation. In order to assess the performance, the major classifications algorithm of PCA, ICA and SVM are used to evaluate training time, test time and accuracy for capsule image area and curve fitting edge data sets.
권기현(Ki-Hyeon Kwon),임정대(Jung-Dae Lim) 한국컴퓨터정보학회 2012 韓國컴퓨터情報學會論文誌 Vol.17 No.4
고추는 건조과정에서 부패되거나 색이변하는 경우가 발생하므로 건고추 품질을 높이기위해서는 건고추를 선별 할 수 있는 기법이 필요하다. 독립성분분석은 블라인드소스분리에서 가장 널리 사용되는 방법으로 이 기법을 사용하여 건조시킨 고추 영상에서 가장 중요한 성분에 대한 농축영상을 얻는다. 취득한 농축영상은 일반 이진(BW) 영상과 달리 주요 성분만 반영한 것으로 영상의 주요 성분 분포 상태를 알 수 있으며 품질을 판단하여 선별하는 것이 가능하다. 또한, 추출된 농축영상의 크기는 고추의 매운 맛을 내는 주요 성분인 캡사이신류의 양과 관련성이 있음을 알 수 있다. ICA 독립성분을 기반으로 한 농축영상 추출을 통해 고추 건조과정에서 부패되어 색상이 좋지 않거나 캡사이신류과 같은 주요 성분이 없게 된 고추를 선별해하는 방법을 제안한다. Hot pepper can be easily faded or discolored in drying process, so we need to use the sorting technique to improve the quality for dried hot pepper. Independent Component Analysis (ICA) is one of the most widely used methods for blind source separation. In this paper we use this technique to get a concentration image of the most important component which plays a role in the dried pepper. This concentration image is different from the binary image and it reflects the characteristics of major components, so that we know the distribution and quality of the component and how to sort the dried pepper. Also, the size of the concentration image can tell the relation with capsaicinoids which make hot taste. We propose a sorting method of the dried hot pepper that is faded or discolored and lacked a major component likes capsaicin in drying process using ICA concentration image.