• Title/Summary/Keyword: 배치모델

Search Result 839, Processing Time 0.026 seconds

Semantic Segmentation of Drone Imagery Using Deep Learning for Seagrass Habitat Monitoring (잘피 서식지 모니터링을 위한 딥러닝 기반의 드론 영상 의미론적 분할)

  • Jeon, Eui-Ik;Kim, Seong-Hak;Kim, Byoung-Sub;Park, Kyung-Hyun;Choi, Ock-In
    • Korean Journal of Remote Sensing
    • /
    • v.36 no.2_1
    • /
    • pp.199-215
    • /
    • 2020
  • A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

Evaluation of Korea Coast Guard Districts Using F-AHP & ARAS Method for Deployment Marine Air Drones (F-AHP법 및 ARAS법을 이용한 해양항공드론 배치를 위한 해양경찰서 관할구역 평가)

  • Jang, Woon-Jae
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.26 no.5
    • /
    • pp.466-473
    • /
    • 2020
  • A marine air drone is a new device that can be used to respond to and prevent marine casualties. Determining the districts where marine air drones can be deployed helps the government decision makers identify efficient policy. The aim of this study is to develop a model using the fuzzy-analytic hierarchy process (F-AHP) and additive ratio assessment (ARAS) method to evaluate appropriate districts for deploying marine air drones. To verify the applicability of the proposed model, a case study was performed with respect to the Korea coast guard (KCG) districts. Since the deployed marine air drones are characterized by a high degree of overlap between the evaluation attributes. the F-AHP is used to determine the weights of identified criteria. The results of this study, show that missing people from the shore was the most important criterion for deployment of the drone. For ranking the local districts of the KCG, the ARAS is applied in the case study with the single goal of 50% reduction in marine casualties. Consequently, the highest priority district was identified as Mokpo, followed by Incheon, Seogwipo, Taean, Wando, Yeosu, Pohang, Tongyeong, Gunsan, Bolyeong, Jeju, Buan, Donghae, Sokcho, Ulsan, Uljin, Busan, Changwon, and Pyeongtaeg.

Fabric Mapping and Placement of Field Programmable Stateful Logic Array (Field Programmable Stateful Logic Array 패브릭 매핑 및 배치)

  • Kim, Kyosun
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.49 no.12
    • /
    • pp.209-218
    • /
    • 2012
  • Recently, the Field Programmable Stateful Logic Array (FPSLA) was proposed as one of the most promising system integration technologies which will extend the life of the Moore's law. This work is the first proposal of the FPSLA design automation flow, and the approaches to logic synthesis, synchronization, physical mapping, and automatic placement of the FPSLA designs. The synchronization at each gate for pipelining determines the x-coordinates of cells, and reduces the placement to 1-dimensional problems. The objective function and its gradients for the non-linear optimization of the net length and placement density have been remodeled for the reduced global placement problem. Also, a recursive algorithm has been proposed to legalize the placement by relaxing the density overflow of bipartite bin groups in a top-down hierarchical fashion. The proposed model and algorithm are implemented, and validated by applying them to the ACM/SIGDA benchmark designs. The output state of a gate in an FPSLA needs to be duplicated so that each fanout gate can be connected to a dedicated copy. This property has been taken into account by merging the duplicated nets into a hyperedge, and then, splitting the hyperedge into edges as the optimization progresses. This yields additional 18.4% of the cell count reduction in the most dense logic stage. The practicality of the FPSLA can be further enhanced primarily by incorporating into the logic synthesis the constraint to avoid the concentrated fains of gates on some logic stages. In addition, an efficient algorithm needs to be devised for the routing problem which is based on a complicated graph. The graph models the nanowire crossbar which is trimmed to be embedded into the FPSLA fabric, and therefore, asymmetric. These CAD tools can be used to evaluate the fabric efficiency during the architecture enhancement as well as automate the design.

Pushover Analysis of an Unbraced 5-Story Steel Framed Structure for Arrangement of Semi-Rigid Connection (반강접 접합부 배치에 따른 비가새 5층 철골골조구조물의 비탄성 정적해석)

  • Kang, Suk-Bong;Kim, Sin-Ae
    • Journal of Korean Society of Steel Construction
    • /
    • v.22 no.4
    • /
    • pp.325-334
    • /
    • 2010
  • In this study, an unbraced five-story steel-framed structure was designed in accordance with KBC2005 to understand the features of structural behavior for the arrangement of semi-rigid connections. A pushover analysis of the structural models was performed, wherein all the connections were idealized as fully rigid and semi-rigid. Additionally, horizontal and vertical arrangements of the semi-rigid connection were adopted for the models. A fiber model was utilized for the moment-curvature relationship of the steel beam and the column, and a three-parameter power model was adopted for the moment-rotation angle of the semi-rigid connection. The top displacement, base-shear force, required ductility for the connection, sequence of the plastic hinge, and design factors such as the overstrength factor, ductility factor, and response modification coefficient were investigated using the pushover analysis of a 2D structure subjected to the equivalent static lateral force of KBC2005. The partial arrangement of the semi-rigid connection was found to have secured higher strength and lateral stiffness than that of the A-Semi frame, and greater ductility than the A-Rigid frame. The TSD connection was found suitable for use for economy and safety in the sample structure.

Effect of Path Loss Models for CDMA Base Station Deployment in LOS Environments (LOS 환경에서 CDMA 기지국 배치를 위한 Path Loss Model의 영향)

  • Min, Seung-Wook
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.36 no.1A
    • /
    • pp.1-7
    • /
    • 2011
  • Cell Capacity and cell layout are strongly dependent on the up-link interference caused by out-of-cell mobiles. Accurate prediction of the propagation path loss from out-of-cell mobiles is essential to achieve system designs that minimize the infrastructure required for a given quality of service (QOS). Less accurate predictions can be expected to yield designs requiring the use of a greater number of base stations. In order to quantify the dependence of infrastructure on prediction accuracy, this paper considers the cellular systems, LOS (line of sight) cells along a road or highway.

Multi-floor Layout Model for Topsides of Floating Offshore Plant using the Optimization Technique (최적화 기법을 이용한 부유식 해양 플랜트 상부 구조의 다층 배치 모델)

  • Jeong, Se-Yong;Roh, Myung-Il;Shin, Hyunkyoung
    • Journal of the Society of Naval Architects of Korea
    • /
    • v.52 no.1
    • /
    • pp.77-87
    • /
    • 2015
  • For a floating offshore plant such as FPSO(Floating, Production, Storage, and Off-loading unit), various equipment should be installed in the restricted space, as compared with an onshore plant. The requirement for an optimal layout method of the plant has been increased in these days. Thus, a layout method of the floating offshore plant was proposed in this study. For this, an optimization problem for layout design was mathematically formulated, and then an optimization algorithm based on the genetic algorithm was implemented with C++ language in order to solve it. Finally, the proposed method was applied to an example of FPSO topsides. As a result, it was shown that the proposed method can be applied to layout design of the floating offshore plant such as FPSO.

A Study on the Relational Data Model for the Representation of Ship Structure (관계형 데이타모델을 이용한 선체구조의 표현에 관한 연구)

  • Y.D. Kim;K.Y. Lee;S.W. Seo;H.Y. Ryu;C.H. Hong
    • Journal of the Society of Naval Architects of Korea
    • /
    • v.28 no.2
    • /
    • pp.12-20
    • /
    • 1991
  • The informations of ship structural design have been represented as the form various drawing plants, but to enhance the design productivity, it is necessary to utilize the advanced technologies such as CAD system and database management system. In this study, efforts are focused on the data modelling of those informations of midship configuration and attribute for the integration of ship structural design programs through database system. As actual example, midship configuration of bulk carrier was visualized by computer graphics. Relational data model is employed and topological informations is used for the best treatment of geometries representing structural arrangement. RDBMS 'ORACLE' was used for the implementation of the results.

  • PDF

Model Scramjet Engine Design for Ground Test (지상시험용 모델 스크램제트 엔진의 설계)

  • Kang, Sang-Hun;Lee, Yang-Ji;Yang, Soo-Seok
    • Journal of the Korean Society of Propulsion Engineers
    • /
    • v.11 no.5
    • /
    • pp.1-13
    • /
    • 2007
  • Scramjet engine is one of the most promising propulsion systems for future transport. For the ground test with T4 shock tunnel, model scramjet engine is designed. Design flight Mach number is 7.6 and flight altitude is 30km. Engine intake is designed by Levenberg-Marquardt optimization method and Korkegi relation. Furthermore, cowl cut out region is installed by the rule of Kantrowitz limit. Inside the combustor, cavity type flame holder is installed. Cavity is designed by Rayleigh line relation and PSR model. Numerical analysis is performed for the design confirm.

Simulation Modeling Method Using ARENATM Considering Alternative Machines in the Manufacturing System for Aircraft Parts (대체장비를 고려한 항공기 부품 생산라인의 ARENATM 시뮬레이션 모델링 방법론)

  • Na, Sang Hyun;Moon, Dug Hee
    • Journal of the Korea Society for Simulation
    • /
    • v.25 no.4
    • /
    • pp.1-12
    • /
    • 2016
  • The industry producing the parts of aircraft engines is a traditional order-made system with highly variety and small quantity, and the manufacturing system is the typical job shop with identical or non-identical multiple machines in a workstation. Furthermore, there are many alternative operations and alternative machines allowed in machining processes, and tremendous routings and assembly operations should be considered. Usually simulation is the most efficient technology to analyze such a complex system, and high modeling skills are required for developing the simulation models. In this paper, a case study on a company which produces the parts of aircraft engines is introduced, specially focused on simulation modeling methodologies for the complex system.

A Simulation Study of Stochastic Combat Networks (확률과정을 따르는 전투 네트워크 시뮬레이션 연구)

  • Min, Hyun-Joon;Hong, Yoon-Gee
    • Journal of the Korea Society for Simulation
    • /
    • v.19 no.1
    • /
    • pp.113-123
    • /
    • 2010
  • The interest in combat network systems rises among specialists as the military technology advances. This study considers some new elements such as characteristics of weapon systems, force moving rules at the end of each small battle, etc. to improve the accuracy of the analysis of series of mini battle problems. There is a significant difference in MOEs among the scenarios and the models. This study suggests some further works in weapon allocation, moving speed, tactics, weather, and topography which need to be investigated.