• Title/Summary/Keyword: 모델 압축

Search Result 1,647, Processing Time 0.029 seconds

Predictive System for Unconfined Compressive Strength of Lightweight Treated Soil(LTS) using Deep Learning (딥러닝을 이용한 경량혼합토의 일축압축강도 예측 시스템)

  • Park, Bohyun;Kim, Dookie;Park, Dae-Wook
    • Journal of the Korea institute for structural maintenance and inspection
    • /
    • v.24 no.3
    • /
    • pp.18-25
    • /
    • 2020
  • The unconfined compressive strength of lightweight treated soils strongly depends on mixing ratio. To characterize the relation between various LTS components and the unconfined compressive strength of LTS, extensive studies have been conducted, proposing normalized factor using regression models based on their experimental results. However, these results obtained from laboratory experiments do not expect consistent prediction accuracy due to complicated relation between materials and mix proportions. In this study, deep neural network model(Deep-LTS), which was based on experimental test results performed on various mixing conditions, was applied to predict the unconfined compressive strength. It was found that the unconfined compressive strength LTS at a given mixing ratio could be resonable estimated using proposed Deep-LTS.

Parametric Video Compression Based on Panoramic Image Modeling (파노라믹 영상 모델에 근거한 파라메트릭 비디오 압축)

  • Sim Dong-Gyu
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.43 no.4 s.310
    • /
    • pp.96-107
    • /
    • 2006
  • In this paper, a low bitrate video coding method based on new panoramic modeling is proposed for panning cameras. An input video frame from a panning camera is decomposed into a background image, rectangular moving object regions, and a residual image. In coding the background, we employ a panoramic model that can account for several image formation processes, such as perspective projection, lens distortion, vignetting and illumination effects. Moving objects aredetected, and their minimum bounding rectangular regions are coded with a JPEG-2000 coder. We have evaluated the effectiveness of the proposed algorithm with several indoor and outdoor sequences and found that the PSNR is improved by $1.3{\sim}4.4dB$ compared to that of JPEG-2000.

Effect of an Opening on Buckling Strength of Polygonal Section Wind Turbine Tower (다각형 단면 풍력타워 좌굴강도에 대한 개구부의 영향)

  • Choi, Byung Ho;Park, Seong Mi;Hwang, Min Oh
    • 한국방재학회:학술대회논문집
    • /
    • 2011.02a
    • /
    • pp.163-163
    • /
    • 2011
  • 풍력타워 기둥구조물에는 유지관리 등의 이유로 출입구 역할을 하는 개구부가 존재하게 된다. 다각형 타워구조물에 개구부형상이 존재하게 되면 압축좌굴 강도에 영향이 있을 것으로 예상되지만, 이를 정량적으로 평가하거나 예측하기는 용이하지 않고 간접적으로 판단할 만한 관련 기준이나 지침도 부족한 상태이다. 이에 최병호 등(2011)에서 다룬 다각형 단면 기둥구조물의 하단에 개구부를 형상화한 수치해석 모델을 수립하고 축방향 압축하중을 재하하는 탄성좌굴 해석 및 비선형비탄성해석을 수행하였다. 본 논문에서는 기존 다각형 단면 기둥모델 중에서 6각형 단면모델에 관해 중점적으로 다루고 있다. 다각형 단면 기둥 해석모델은 단순한 다각형 단면 타워구조에 대해서 뿐 만 아니라, 각 subpanel에 종방향 보강재를 둔 모델에 대해서도 추가적으로 검토하였다. 개구부의 형상은 높이 2000mm, 폭 800mm이며 상하부에 만곡부를 둔 형태이다. 수치해석은 3차원 유한요소해석프로그램인 ABAQUS를 이용하여 수행하였으며, 보강방안으로는 일정범위까지의 모듈 subpanel의 판두께를 보강하는 방안과 edge stiffener를 적용하는 방안에 대해서 검토하였다. 각각의 보강방식에 따른 효과를 비교해 보기 위해 개구부가 없는 모델, 단순히 개구부만 설정한 모델, 판두께를 보강한 모델, edge stiffener로 보강한 모델에 대해 비교해석을 수행하였다. 보강재 없는 단순 다각형 타워구조 모델에 대한 해석결과로부터 개구부로 인한 강도저하는 미미한 수준인 것으로 나타났다. 반면, 종방향 보강재가 적용된 6각형 단면 타워구조 모델에서는 개구부로 인한 강도저감이 22.9%로 높게 나타났으며 상당한 영향이 있는 것으로 분석되었다. 또한 개구부 주변의 판두께 보강이나 edge stiffener보강 등으로 상당한 강도향상 효과가 확인되었으나, 개구부로 인해 손실된 강도 수준을 완전히 회복하는 수준에 미치지 못하는 것으로 나타났다. 따라서, 향후 다양한 보강방식에 대한 보다 포괄적인 변수연구를 통해 개구부의 영향 없이 온전한 다각형 단면 타워 구조의 극한강도에 도달되기 위한 보강 조건에 대해 검토될 필요가 있을 것으로 사료된다.

  • PDF

A Nonlinear Material Model for Concrete Compression Strength considering confining effect (콘크리트 압축강도에 따른 횡철근 구속효과를 고려한 비선형 재료모델)

  • Park, Jae-Guen;Lee, Heon-Min;Sung, Dae-Jung;Choi, Jung-Ho;Shin, Hyun-Mock
    • Proceedings of the Korea Concrete Institute Conference
    • /
    • 2008.04a
    • /
    • pp.261-264
    • /
    • 2008
  • When the concrete is confined to width direction, stress-strain curve of concrete are different from the uniaxial behavior. In case of normal strength concrete, Mander model are used with concrete material model which considers confining effect. Sakino-Sun model showed experimental result of specimen-level and the highest accuracy. Therefore, Normal strength concrete used Mander model. and High strength concrete used Sakino-Sun model. But there are significant differences from actual data when medium strength concrete used Mander or Sakino-Sun model. and Limit scope of maximum or minimum compressive strength of concrete is not clear when applied to two models. Therefore, In this research, material nonlinear model of confined concrete is suggested when concrete which has 30-40MPa's strength is confined to width direction.

  • PDF

Comparison of Error Rate and Prediction of Compression Index of Clay to Machine Learning Models using Orange Mining (오렌지마이닝을 활용한 기계학습 모델별 점토 압축지수의 오차율 및 예측 비교)

  • Yoo-Jae Woong;Woo-Young Kim;Tae-Hyung Kim
    • Journal of the Korean Geosynthetics Society
    • /
    • v.23 no.3
    • /
    • pp.15-22
    • /
    • 2024
  • Predicting ground settlement during the improvement of soft ground and the construction of a structure is an crucial factor. Numerous studies have been conducted, and many prediction equations have been proposed to estimate settlement. Settlement can be calculated using the compression index of clay. In this study, data on water content, void ratio, liquid limit, plastic limit, and compression index from the Busan New Port area were collected to construct a dataset. Correlation analysis was conducted among the collected data. Machine learning algorithms, including Random Forest, Neural Network, Linear Regression, Ada Boost, and Gradient Boosting, were applied using the Orange mining program to propose compression index prediction models. The models' results were evaluated by comparing RMSE and MAPE values, which indicate error rates, and R2 values, which signify the models' significance. As a result, water content showed the highest correlation, while the plastic limit showed a somewhat lower correlation than other characteristics. Among the compared models, the AdaBoost model demonstrated the best performance. As a result of comparing each model, the AdaBoost model had the lowest error rate and a large coefficient of determination.

Maximizing WSQ Compression Rate by Considering Fingerprint Image Quality (지문 영상 품질을 고려한 WSQ 최대 압축)

  • Hong, Seung-Woo;Lee, Sung-Ju;Chung, Yong-Wha;Choi, Woo-Yong;Moon, Dae-Sung;Moon, Ki-Young;Jin, Chang-Long;Kim, Hak-Il
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.20 no.3
    • /
    • pp.23-30
    • /
    • 2010
  • Compression techniques can be applied to large-scale fingerprint systems to store or transmit fingerprint data efficiently. In this paper, we investigate the effects of FBI WSQ fingerprint image compression on the performance of a fingerprint verification system using multiple linear regressions. We propose a maximum compression using fingerprint image quality score. Based on the experiments, we can confirm that the proposed approach can compress the fingerprint images up to 3 times more than the fixed compression ratio without significant degradation of the verification accuracy.

Shear Strength Model for Slab-Column Connections (슬래브-기둥 접합부에 대한 전단강도모델)

  • Choi, Kyoung-Kyu;Park, Hong-Gun;Kim, Hye-Min
    • Journal of the Korea Concrete Institute
    • /
    • v.22 no.4
    • /
    • pp.585-593
    • /
    • 2010
  • On the basis of the strain-based shear strength model developed in the previous study, a strength model was developed to predict the direct punching shear capacity and unbalanced moment-carrying capacity of interior and exterior slab-column connections. Since the connections are severely damaged by flexural cracking, punching shear was assumed to be resisted mainly by the compression zone of the slab critical section. Considering the interaction with the compressive normal stress developed by the flexural moment, the shear strength of the compression zone was derived on the basis of the material failure criteria of concrete subjected to multiple stresses. As a result, shear capacity of the critical section was defined according to the degree of flexural damage. Since the exterior slab-column connections have unsymmertical critical sections, the unbalanced moment-carrying capacity was defined according to the direction of unbalanced moment. The proposed strength model was applied to existing test specimens. The results showed that the proposed method predicted the strengths of the test specimens better than current design methods.

An Experimental Study on the Modelling for the Prediction of the Behaviour of EPS (EPS의 거동 예측 모델에 관한 실험적 연구)

  • 천병식;임해식
    • Geotechnical Engineering
    • /
    • v.12 no.5
    • /
    • pp.127-136
    • /
    • 1996
  • Recently, EPS which has unit weight of only 20~30kg/m3, is used for acquiring the safety of settlement and bearing capacity, In Korea, EPS was first used in 1993 as backfill material for abutment that was constructed on soft ground in Inchon. Since then EPS has been used increasingly as backfill material. However, adequate modelling has not yet been proposed for the prediction of the behavior of EPS. Only it's design strength was proposed as the results of unconfined strength and creep test. Accordingly this paper executed triaxial compression test on EPS with various density and confining pressure. Through the analysis of test data the behavior of EPS for strainstress, tangential modulus and poisson's ratio can be expressed in functions with parameters of density and confining pressure of EPS. From these results, this paper proposed a nonliner model describing the behavior of EPS.

  • PDF