• 제목/요약/키워드: Development and use of models

검색결과 1,085건 처리시간 0.028초

기동 표적 추적을 위한 퍼지 IMM 알고리즘에 관한 연구 (A Study on Fuzzy Interacting Multiple Model Algorithm for Maneuvering Target Tracking)

  • 김현식;김진석;황수복
    • 한국군사과학기술학회지
    • /
    • 제7권4호
    • /
    • pp.5-12
    • /
    • 2004
  • The tracking algorithm based on the interacting multiple model(IMM) requires a considerable number of sub-models for the various maneuvering targets in order to have a good performance. But it is not feasible to use the nm algorithm in the real system because of the computational burden. Therefore, we need an algorithm which requires less computing resources while maintaining a good performance. In this paper, we propose a fuzzy interacting multiple model algorithm(FIMMA) for the tracking of maneuvering targets, which uses a minimal number of sub-models by considering the maneuvering properties and adjusts the mode transition probabilities by using the mode probability as a fuzzy input. In order to verify the performance of FIMMA, the developed algorithm is applied to the tracking of i borne targets. Simulation results show that the FIMMA is very effective in the tracking of maneuvering targets.

사전 학습된 한국어 BERT의 전이학습을 통한 한국어 기계독해 성능개선에 관한 연구 (A Study of Fine Tuning Pre-Trained Korean BERT for Question Answering Performance Development)

  • 이치훈;이연지;이동희
    • 한국IT서비스학회지
    • /
    • 제19권5호
    • /
    • pp.83-91
    • /
    • 2020
  • Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

통합 토지이용 교통모형을 이용한 교통정책평가에 관한 연구 I: 기존사례연구를 중심으로 (Study on Transport Policy Assessment Using the Integrated Land Use Transport Model)

  • 이승재;손지언
    • 한국ITS학회 논문지
    • /
    • 제9권1호
    • /
    • pp.111-120
    • /
    • 2010
  • 도로교통 장려정책은 1970년대부터 산업성장에 기반이 되어 국가전반에 순기능을 발휘하였으나, 점차 수도권에 집중 된 토지개발정책과 맞물려 역기능이 나타나기 시작했다. 승용차보유대수가 폭발적으로 증가하였던 시기는 정부의 적극적인 도시개발이 진행되어온 시기와 맞물린다고 볼 수 있다. 교통은 통행목적 및 활동에 기반하는 파생적 수요이기 때문에 교통수요를 정확히 추정하고, 이를 통해 정책평가를 도출하기 위해서는 토지이용에 대한 특성파악이 선행되어야 한다. 본 연구에서는 기존에 연구된 교통과 토지이용에 관한 통합모델을 고찰하여, 교통수요추정의 정확성 확보를 위한 정책평가 기반을 마련하는데 연구의 목적이 있다. 따라서 교통-토지이용모델의 이론적 배경이 되고 있는 Predictive model과 Optimizing model에 대해서 고찰하고, 해외사례를 통하여 사용된 모델에 대한 평가 및 장단점에 대해 살펴보았다. 본 연구는 이미 시행되고 있거나, 계획되고 있는 다양한 도시정책을 평가하기 위한 준거를 제시하기 위한 사전단계임으로 이를 기반으로 향후에 서울 및 수도권을 대상으로 하는 통합토지이용모델을 개발할 수 있을 것이다. 또한 기술의 발달로 인한 U-Society환경이 교통패턴에 미치는 영향, 즉 이동 중에 다양한 활동을 할 수 있는 U-Transportation 현상이 통행패턴에 미치는 영향을 파악함으로 ITS 사업 추진에 중요한 기반으로 활용될 수 있을 것이다.

이메뉴팩처링을 위한 협업 프로세스 모델링 (Collaborative Process Modeling for Embodying e-Manufacturing)

  • 류광열;조용주;최헌종;이석우
    • 산업공학
    • /
    • 제18권3호
    • /
    • pp.221-233
    • /
    • 2005
  • e-Manufacturing can be referred to as a system methodology enabling the integration of manufacturing operations and IT technologies to achieve objectives of an enterprise. It is recently regarded as a powerful solution to survive in a chaotic marketplace. While conducting an e-Manufacturing project, we first needed to capture collaborative processes conducted by multiple participants in order to define functions of a system supporting them. However, pervasive process modeling techniques including IDEF3, Petri nets, and UML are not sufficient for modeling collaborative processes. Therefore, we first briefly investigate several process modeling methods including aforementioned modeling methods and ARIS focusing on the collaboration point of view. Then, we propose a new modeling method referred to as Collaborative Process Modeling (CPM) to clearly describe collaborative processes. Also, we develop and illustrate a rule for transforming collaborative process models into Marked Graph models to use the analysis power of the Petri nets. Using CPM empowers us to develop collaborative process models with simple notations, understand and facilitate the realization of the collaboration, and verify models before rushing into the development.

A new approach for 3-D pushover based analysis of asymmetric buildings: development and initial evaluation

  • Baros, Dimitrios K.;Anagnostopoulos, Stavros A.
    • Earthquakes and Structures
    • /
    • 제12권5호
    • /
    • pp.543-557
    • /
    • 2017
  • Results of an extensive study aiming to properly extend the well known pushover analysis into 3-D problems of asymmetric buildings are presented in this paper. The proposed procedure uses simple, 3 DOF, one-story models with shear-beam type elements in order to quantify the effects of inelastic torsional response of such buildings. Correction coefficients for the response quantities at the "stiff" and "flexible" sides are calculated using results from non-linear time history analyses of the simple models. Their values are then applied to the results of a simple, plane pushover analysis of the detailed building models. Results from the application of the new method for a set of three, conventionally designed, five-story buildings with high values of uniaxial eccentricities are compared with those obtained from multiple non-linear dynamic time history analyses, as well as from similar pushover methods addressing the same problem. This initial evaluation indicates that the proposed procedure is a clear improvement over the simple (conventional) pushover method and, in most cases, more accurate and reliable than the other methods considered. The accuracy, however, of all these methods is reduced substantially when they are applied to torsionally flexible buildings. Thus, for such challenging problems, use of inelastic dynamic analyses for a set of two component earthquake motions appears to be the preferable solution.

농약의 초기위해성평가체계에 관한 연구 - Captan, Paraquat dichloride, Glyphosate에 대한 Case study - (Initial Risk Assessment System of Pesticides - A case study of captan, paraquat dichloride, and glyphosate -)

  • 이용주;김균;김용화
    • 농약과학회지
    • /
    • 제9권3호
    • /
    • pp.214-220
    • /
    • 2005
  • 초기위해성평가는 신물질 개발시 급성자료와 물리화학적 특성자료를 이용하여 위해성평가를 수행하고 정책결정자들에게 위해성에 관한 정보를 제공하여 의사결정 수단으로 활용되고 있다. 본 연구에서는 초기위해성평가 체계의 틀을 구축하고 구축된 위해성평가 체계를 검증하기 위하여 captan, glyphosate, paraquat dichloride의 세 가지 농약을 대상물질로 하여 인체 및 생태의 초기위해성을 평가하였다. 이때 두 종류의 수계 예측 모형인 GENEEC (GENeric Estimated Environmental Concentration)과 FOCUS (FOrum for the Co-ordination of pesticide models and their USe)가 농약의 노출평가를 위하여 사용되었으며 glyphosate와 paraquat dichloride는 인체 및 생태에 위해성이 낮은 것으로 나타났으나 captan의 어류 위해성은 급성독성이 높은 것으로 나타났다. 이 결과는 U.S. EPA RED (Reregistration Eligibility Decision) 결과와 유사한 경향성을 보여 본 연구체계의 신뢰성을 검증할 수 있었다.

Improving the Genetic Algorithm for Maximizing Groundwater Development During Seasonal Drought

  • Chang, Sun Woo;Kim, Jitae;Chung, Il-Moon;Lee, Jeong Eun
    • 지질공학
    • /
    • 제30권4호
    • /
    • pp.435-446
    • /
    • 2020
  • The use of groundwater in Korea has increased in recent years to the point where its extraction is restricted in times of drought. This work models the groundwater pumping field as a confined aquifer in a simplified simulation of groundwater flow. It proposes a genetic algorithm to maximize groundwater development using a conceptual model of a steady-state confined aquifer. Solving the groundwater flow equation numerically calculates the hydraulic head along the domain of the problem; the algorithm subsequently offers optimized pumping strategies. The algorithm proposed here is designed to improve a prior initial groundwater management model. The best solution is obtained after 200 iterations. The results compare the computing time for five simulation cases. This study shows that the proposed algorithm can facilitate better groundwater development compared with a basic genetic algorithm.

Current strategies using 3D organoids to establish in vitro maternal-embryonic interaction

  • Islam Mohamed Saadeldin;Seif Ehab;Ahmed Elsayed Noreldin;Ayman Abdel-Aziz Swelum;Seonggyu Bang;Hyejin Kim;Ki Young Yoon;Sanghoon Lee;Jongki Cho
    • Journal of Veterinary Science
    • /
    • 제25권3호
    • /
    • pp.40.1-40.19
    • /
    • 2024
  • Importance: The creation of robust maternal-embryonic interactions and implantation models is important for comprehending the early stages of embryonic development and reproductive disorders. Traditional two-dimensional (2D) cell culture systems often fail to accurately mimic the highly complex in vivo conditions. The employment of three-dimensional (3D) organoids has emerged as a promising strategy to overcome these limitations in recent years. The advancements in the field of organoid technology have opened new avenues for studying the physiology and diseases affecting female reproductive tract. Observations: This review summarizes the current strategies and advancements in the field of 3D organoids to establish maternal-embryonic interaction and implantation models for use in research and personalized medicine in assisted reproductive technology. The concepts of endometrial organoids, menstrual blood flow organoids, placental trophoblast organoids, stem cell-derived blastoids, and in vitro-generated embryo models are discussed in detail. We show the incorportaion of organoid systems and microfluidic technology to enhance tissue performance and precise management of the cellular surroundings. Conclusions and Relevance: This review provides insights into the future direction of modeling maternal-embryonic interaction research and its combination with other powerful technologies to interfere with this dialogue either by promoting or hindering it for improving fertility or methods for contraception, respectively. The merging of organoid systems with microfluidics facilitates the creation of sophisticated and functional organoid models, enhancing insights into organ development, disease mechanisms, and personalized medical investigations.

GIS를 활용한 카르스트 지역의 싱크홀 민감성 분석: 삼척시를 중심으로 (GIS Based Sinkhole Susceptibility Analysisin Karst Terrain: A Case Study of Samcheok-si)

  • 안세진;성효현
    • 한국지형학회지
    • /
    • 제24권4호
    • /
    • pp.75-89
    • /
    • 2017
  • Sinkholes are key karst landforms that primarily evolve through the dissolution of limestone, and it posing a significant threat to roads, buildings, and other man-made structures. This study aims to analyze the area susceptible to sinkhole development using GIS and to identify potential danger area from sinkholes. Eight sinkhole related factors (slope angle, distance to caves, distance to faults, bedrock lithology, soil depth, drainage class, distance to mines, and distance to traffic routes) were constructed as spatial databases with sinkhole inventory. Based on the spatial database, sinkhole susceptibility maps were produced using nearest neighbor distance and frequency ratio models. The maps were verified with prediction rate curve and area under curve. The result indicates that the nearest neighbor distance and frequency ratio models predicted 95.3% and 94.4% of possible sinkhole locations respectively. Furthermore, to identify potential sinkhole danger area, the susceptibility map was compared with population distribution and land use map. It has been found that very highly susceptible areas are along Osipcheon and southeast southwest part of Hajang-myeon and south part of Gagok-myeon of Samcheok-si. Among those areas, it has been identified that potential sinkhole danger areas are Gyo-dong, Seongnae-dong, Jeongna-dong, Namyang-dong and Dogye-eup. These results can be useful in the aspects of land use planning and hazard prevention and management.

THE USE OF NUMERICAL MODELS IN SUPPORT OF SITE CHARACTERIZATION AND PERFORMANCE ASSESSMENT STUDIES FOR GEOLOGICAL REPOSITORIES

  • Neerdael, Bernard;Finsterle, Stefan
    • Nuclear Engineering and Technology
    • /
    • 제42권2호
    • /
    • pp.145-150
    • /
    • 2010
  • The paper is describing work being developed in the frame of a 5-year IAEA Coordinated Research Programme (CRP) started in late 2005. Participants gained knowledge of modelling methodologies and experience in the development and use of rather sophisticated simulation tools in support of site characterization and performance assessment calculations. These goals were achieved by a coordinated effort, in which the advantages and limitations of numerical models are examined and demonstrated through a comparative analysis of simplified, illustrative test cases. This knowledge and experience should help them address these issues in their own country's nuclear waste program. Coordination efforts during the first three years of the project aimed at enabling this transfer of expertise and maximizing the learning experience of the participants as a group. This was accomplished by identifying common interests of the participants (i.e., Process Modelling and Total System Performance Assessment methodology), and by defining complementary tasks that are solved by the members. Synthesis of all available results by comparative assessments is planned in the coming months. The project will be completed end of 2010. This paper is summarizing activities up to November 2009.