• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.3
• /
• pp.315-325
• /
• 2015

Smart Car market has been experiencing continuous growth to drive leading companies in automotive and IT industries to focus on advancing related technologies. As the IT technologies fuse into automotive technologies, the patent litigation has been showing changes. One of the prominent changes in patent litigation pattern of Smart Car field is the increased activities of the Non-Practicing Entities (NPEs), whose main field has been the IT area. However, the automotive companies have been mainly focusing on preventing patent disputes against competitors through trend analysis, which caused them to become relatively vulnerable to the attacks from NPEs. In this study, we developed a methodology for monitoring and analyzing the activities of NPEs using network analysis tools to suggest effective strategies for manufacturing companies to fortify their ability to respond against unanticipated attacks. Our methodology, which is developed for the Smart Car field, can also be useful for other fields such as IT and electronics.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.37 no.4
• /
• pp.281-286
• /
• 2004

Spermatogenesis and sperm ultrastructure of the marsh clam (Corbicula japonica) were investigated by electron microscopic observations. Testis of the marsh clam consists of numerous spermatogenic follicle containing germ cells in the different developmental stages. Spermatogonia are located nearest the outer wall of the follicle, while spermtocytes and spermatids are positioned nearer to the lumen. Spematogonia are oval-shaped and about $5{\mu}m$ In diameter. Spermatogonia develop into spermatocyte, spermatid and spermatozoon. In the spermatid to about $2{\mu}m$ in diameter, cytoplasm decreases and mitochondria move to the base of the nucleus and fuse into several spheres, the centrioles become orthogonally oriented, a flagellum appears, and an acrosomal vesicle forms. The mature sperm has primitive type, consisting of a head, a midpiece and a tail. The sperm was arrow-shaped, and its head is about $8{\mu}m$ long and comprised of a long nucleus and an acrosome. The four mitochondria encircled the centrosome in midpiece. The flagellum had the classical 9+2 axoneme structure, and axonemal lateral fins in the tail were observed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1239-1248
• /
• 2018

This paper proposes a fault tolerant and high efficiency operation algorithm for a 4 LEG DC/DC converter for a battery energy storage system(BESS) forming a main power source in a standalone DC micro grid. The BESS for the main power supply in the stand-alone DC micro-grid is required to operate at high speed according to fault tolerant control and load by operating at all times. Fault-tolerance control changes the short-circuit fault to an open-circuit fault by using a fuse in case of leg fault in 4 legs, and operates stably through phase shift control. In addition, considering the loss of the power semiconductor, the number of LEG operation is adjusted to operate at high efficiency in the full load region. In this paper, fault tolerant control and high efficiency operation algorithm of DC/DC converter for BESS in standalone DC micro grid is presented and it is proved through simulation and experiment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.3
• /
• pp.65-78
• /
• 2013

To analyze influences under open fault conditions in switching devices, an integrated simulation and condition monitoring scheme for a permanent magnet synchronous generator (PMSG) based variable speed grid-connected wind turbine system are presented. Among various faults in power electronics components, the open fault in switching devices may arise when the switches are destructed by an accidental over current, or a fuse for short protection is blown out. Under such a faulty condition, the grid-side inverter as well as the generator-side converter does not operate normally, producing an increase of current harmonics, and a reduction in output and efficiency. As an effective way for a condition monitoring of generation system by online basis without requiring any diagnostic apparatus, the estimation schemes for generated voltage, flux linkage, and stator resistance are proposed and the validity of the proposed scheme is proved through comparative simulations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.267-272
• /
• 2007

네트워크 파일시스템은 원격의 서비스와 자원에 대해 로컬의 그것과 같은 투명성을 제공하기 때문에 널리 사용된다. 네트워크 파일시스템을 제작하거나 수정하는 일에는 운영체제의 커널과 통신 프로토콜에 대한 고려가 필요하므로 복잡하고 많은 시간이 걸린다. 기존의 파일시스템 프레임워크를 사용할 경우 운영체제의 커널 모듈에 대한 고려는 줄일 수 있지만 여전히 통신 프로토콜에 대한 고려는 필요하다. 따라서 네트워크 파일시스템의 빠른 제작을 도와주는 네트워크 파일시스템 프레임워크가 필요하다. 본 논문은 웹서비스 프로토콜인 SOAP과, 사용자 수준 파일시스템 프레임워크인 FUSE를 이용해 사용자 수준 네트워크 파일시스템 프레임워크인 NFSF를 설계하고 구현한다. NFSF는 단일 클라이언트 모듈과 서버 상위모듈, 서버 하위모듈의 3단계 계층을 두고, 중요 파일시스템 API를 서버 하위 모듈로 바인딩한다. 통신 프로토콜을 포함한 단일 클라이언트 모듈과 서버 상위 모듈을 프레임워크에서 제공하여 네트워크 파일시스템 제작 시 서버 하위 모듈만을 제작하게 함으로써 네트워크 파일시스템 제작과정을 '로컬 저장 장치 자체에 대한 고려'로 축소시킨다.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.102-103
• /
• 2007

In order to apply resistive superconducting fault current limiters into electric power systems, the urgent issues to be settled are as follows, such as initial installation price of SFCL, operation and maintenance cost due to ac loss of superconductor and the life of cryostat, and high voltage and high current problems. The ac loss and high cost of superconductor and cryostat system are main bottlenecks for real application. Furthermore in order to increase voltage and current ratings of SFCL, a lot of superconductor components should be connected in series and parallel which resulted in extreme high cost. Thus, in order to make practical SFCL, we designed novel hybrid SFCL which combines superconductor and conventional electric equipment including vacuum interrupter, power fuse and current limiting reactor. The main purpose of hybrid SFCL is to drastically reduce total usage of superconductor by adopting current commutation method by use of superconductor and high fast switch. Consequently, it was possible to get the satisfactory test results using this method, and further works for practical applications are in the process.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.390-392
• /
• 2003

Video mosaicing techniques have been widely used in virtual reality environments. Especially in GIS field, video mosaics are becoming more and more common in representing urban environments. Such applications mainly use spherical or panoramic mosaics that are based on images taken from a rotating camera around its nodal point. The viewpoint, however, is limited to location within a small area. On the other hand, 2D-mosaics, which are based on images taken from a translating camera, can acquire data in wide area. The 2D-mosaics still have some problems : it can‘t be applied to images taken from a rotational camera in large angle. To compensate those problems , we proposed a novel method for creating video mosaics in 3D space. The proposed algorithm consists of 4 steps: feature -based optical flow detection, camera orientation, 2D-image projection, and image registration in 3D space. All of the processes are fully automatic and successfully implemented and tested with real images.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.241-243
• /
• 2003

This paper presents an algorithm that automatically extracts buildings among many different features on the earth surface by fusing LIDAR data with panchromatic aerial images. The proposed algorithm consists of three stages such as point level process, polygon level process, parameter space level process. At the first stage, we eliminate gross errors and apply a local maxima filter to detect building candidate points from the raw laser scanning data. After then, a grouping procedure is performed for segmenting raw LIDAR data and the segmented LIDAR data is polygonized by the encasing polygon algorithm developed in the research. At the second stage, we eliminate non-building polygons using several constraints such as area and circularity. At the last stage, all the polygons generated at the second stage are projected onto the aerial stereo images through collinearity condition equations. Finally, we fuse the projected encasing polygons with edges detected by image processing for refining the building segments. The experimental results showed that the RMSEs of building corners in X, Y and Z were ${\pm}$8.1㎝, ${\pm}$24.7㎝, ${\pm}$35.9㎝, respectively.

• MALSORI
• /
• no.60
• /
• pp.165-180
• /
• 2006

In this paper, we present several confidence measures (CM) for speech recognition systems to evaluate the reliability of recognition results. We propose heuristic CMs such as mean log-likelihood score, N-best word log-likelihood ratio, likelihood sequence fluctuation and likelihood ratio testing(LRT)-based CMs using several types of anti-models. Furthermore, we propose new algorithms to add weighting terms on phone-level log-likelihood ratio to merge word-level log-likelihood ratios. These weighting terms are computed from the distance between acoustic models and knowledge-based phoneme classifications. LRT-based CMs show better performance than heuristic CMs excessively, and LRT-based CMs using phonetic information show that the relative reduction in equal error rate ranges between $8{\sim}13%$ compared to the baseline LRT-based CMs. We use the support vector machine to fuse several CMs and improve the performance of utterance verification. From our experiments, we know that selection of CMs with low correlation is more effective than CMs with high correlation.