• 제목/요약/키워드: Predication

검색결과 81건 처리시간 0.021초

NUMERICAL SIMULATION OF SCOUR BY A WALL JET

  • A.A.Salehi Neyshabouri;R.Barron;A.M.Ferreira da Silva
    • Water Engineering Research
    • /
    • 제2권3호
    • /
    • pp.179-185
    • /
    • 2001
  • The time consuming and expensive nature of experimental research on scouring processes caused by flowing water makes it attractive to develop numerical tools for the predication of the interaction of the fluid flow and the movable bed. In this paper the numerical simulation of scour by a wall jet is presented. The flow is assumed to be two-dimensional, and the alluvium is cohesionless. The solution process, repeated at each time step, involves simulation of a turbulent wall jet flow, solution of the convection-diffusion of sand concentration, and prediction of the bed deformation. For simulation of the jet flow, the governing equations for momentum, mass balance and turbulent parameters are solved by the finite volume method. The SIMPLE scheme with momentum interpolation is used for pressure correction. The convection-diffusion equation is solved for sediment concentration. A boundary condition for concentration at the bed, which takes into account the effect of bed-load, is implemented. The time rate of deposition and scour at the bed is obtained by solving the continuity equation for sediment. The shape and position of the scour hole and deposition of the bed material downstream of the hole appear realistic.

  • PDF

공동주택 건축내장재의 TVOC 방출량에 관한 예측모델 연구 (A Study on Predication model for TVOC Emissions of Finishing material in Apartment House)

  • 김형수;이경회
    • KIEAE Journal
    • /
    • 제2권3호
    • /
    • pp.55-62
    • /
    • 2002
  • While cognition about an environment pollution becomes important recently, the intense pollution measures about an indoor air environment is required. In the case of building indoor environment, over 80% of modem people is living in building and these days an interest of building interior materials which becomes a reason for indoor environmental pollution in public house, office, is increasing. An experimental measurement method of this study is as follows. (1) American EPA TO-17, ASTMD5116-97, measurement method in VOCs experiment of Japanese closet industrial association (2) 2.4-DNPH cartridge method in HCHO experiment, based on American EPA TO-11 and measurement method of Japanese closet industrial association (3) standard compound is analyzed by using HPLC after solvent extraction process (4) paint and furniture are selected as measurement objects (5) we also made small chamber to grasp an emission characteristic of HCHO and VOCs and to get an environment-amicable forecast model through it, then we developed the model which can forecast emission rate by chamber experiment.

재질열화가 표면 균열 진전에 미치는 영향과 수명 예측에 관한 연구 (Effect of Temper-Embrittlement on Surface Crack Growth and Fatigue Life Prediction)

  • 권재도
    • 대한기계학회논문집
    • /
    • 제13권5호
    • /
    • pp.921-927
    • /
    • 1989
  • 본 연구에서는 피로 균열의 진전 특성 및 표면 균열과 같은 3차원 균열의 진전 특성에 나타나는 재질 열화의 영향, 열화와 피로 파괴 형태의 관계, 균열진전 속도의 분산(scattering)과 열화의 관계등에 주목해서 열화재와 회복재의 2종류의 재료를 사용해, 피로 시험에 의한 균열진전의 실험적 특성을 고찰하였다. 또한, 저자들의 종래 관통 균열 진전 특성에 대한 연구 결과를 응용해서 열화와 균열진전의 확률특성을 고려한 표면균열 진전에 대한 시뮬레이션(simulation)을 행해서 피로 수명 예측에 미치는 열화의 영향에 대해 검토해 보았다.

A Reversible Data Hiding Method for AMBTC Compressed Image without Expansion inside Stego Format

  • Hui, Zheng;Zhou, Quan
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권11호
    • /
    • pp.4443-4462
    • /
    • 2020
  • This paper proposes a new framework of reversible data hiding scheme for absolute moment truncation coding (AMBTC) compressed images. AMBTC-based RDH can be applied to optical remote sensing (ORS) image transmission, which achieves target region preservation and image compression simultaneously. Existing methods can be concluded as two types. In type I schemes, stego codes mimic the original AMBTC format where no file bloat occurs, yet the carried secret data is limited. Type II schemes utilize predication errors to recode quantity levels of AMBTC codes which achieves significant increase in embedding capacity. However, such recoding causes bloat inside stego format, which is not appropriate in mentioned ORS transmission. The proposed method is a novel type I RDH method which prevents bloat inside AMBTC stego codes with significant improvement in embedding capacity. The AMBTC compressed trios are grouped into two categories according to a given threshold. In smooth trio, the modified low quantity level is constructed by concatenating Huffman codes and secret bits. The reversible contrast mapping (RCM) is performed to complex trios for data embedment. Experiments show that the proposed scheme provides highest payload compared with existing type I methods. Meanwhile, no expansion inside stego codes is caused.

A Robust Energy Consumption Forecasting Model using ResNet-LSTM with Huber Loss

  • Albelwi, Saleh
    • International Journal of Computer Science & Network Security
    • /
    • 제22권7호
    • /
    • pp.301-307
    • /
    • 2022
  • Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

A Prediction Model for studying the Impact of Separated Families on Students using Decision Tree

  • Ourida Ben boubaker;Ines Hosni;Hala Elhadidy
    • International Journal of Computer Science & Network Security
    • /
    • 제23권4호
    • /
    • pp.79-84
    • /
    • 2023
  • Social studies show that the number of separated families have lately increased due to different reasons. Despite the causes for family rift, many problems are resulted which affected the children physically and psychologically. This effect may cause them fail in their life especially at school. This paper focuses on the negative reaction of the parents' separation with other factors from the computer science prospective. Since the artificial intelligent field is the most common widespread in computer science, a predictive model is built to predict if a specific child whose parents separated, may complete the school successfully or fail to continue his education. This will be done using Decision Tree that have proved their effectiveness on the predication applications. As an experiment, a sample of individuals is randomly chosen and applied on our prediction model. As a result, this model shows that the separation may cause the child success at school if other factors are satisfied; the intelligent of the guardian, the relation between the parents after the separation, his age at the separation time, etc.

시간 정보를 이용한 확장성 있는 하이브리드 Recommender 시스템 (Scalable Hybrid Recommender System with Temporal Information)

  • ;;김재우;문경덕;김진태;이성창
    • 한국인터넷방송통신학회논문지
    • /
    • 제12권2호
    • /
    • pp.61-68
    • /
    • 2012
  • 최근 디지털 컨텐츠와 컨텐츠 사용자의 기하 급수적인 증가와 함께 recommender 시스템이 주목을 받으며 많은 응용 프로그램에 적용되고 있는 가운데, recommender 시스템의 확장성과 대체적으로 이와 반비례하는 정확성이 이슈가 되고 있다. 본 논문에서는 recommender 시스템 모델 중 하이브리드 모델의 매트릭스를 제거하고 아이템의 특성을 정하기 위해 클러스터링 기술을 사용한 Scalable Hybrid Recommender System을 제안한다. 제안된 모델은 recommender 시스템의 확장성과 정확성을 향상시키기 위해서 아이템에 대한 사용자의 평가 정보, demographic 정보와 구체적인 시간 정보를 사용한다. Reduction 기술 사용을 통해 Item-feature 매트릭스의 사이즈를 축소하고, 사용자 demographic 정보를 사용하여 temporal aware hybrid user model을 만든 후, 비슷한 정보를 가진 사용자간 클러스터링을 통해, 가장 유사한 정보를 가진 사용자들을 추출하여, 사용자간 정보를 비교함으로써 사용자가 원하는 아이템의 특성을 예상하고 사용자에게 N개의 아이템을 추천함으로써, 기존의 recommender 시스템보다 더욱 향상된 결과를 도출해 낼 수 있는 알고리즘을 제시하였다.

수위-유량곡선을 위한 비매개 변수적 Kernel 회귀모형 (Nonparametic Kernel Regression model for Rating curve)

  • 문영일;조성진;전시영
    • 한국수자원학회논문집
    • /
    • 제36권6호
    • /
    • pp.1025-1033
    • /
    • 2003
  • 수공구조물의 설계를 비롯하여, 수자원 분야의 기술적 설계의 기초는 수문자료의 처리와 분석에 중심을 두고 있다고 할 수 있다. 수문 자료의 분석방법 중 가장 보편적이면서도 중요한 방법은 자료들의 관계를 도식적으로 규명하는 회귀분석이다. 수위-유량 관계곡선과 같은 수문 자료에 대한 기존의 매개변수적 회귀모형이 갖는 단점은 자료의 특성에 따라, 복수의 회귀식이 산정되거나 동일자료에 대해서도 서로 다른 회귀식이 산정됨으로써 신뢰할 수 있는 회귀곡선을 만들기가 어렵다는 것이다. 이에 비해 주어진 자료에 의해 도출되는 kernel 회귀모형은 자료의 특성과 경향성을 적절히 표현해 줄 수 있는 방법이다. 본 논문에서는 비매개변수적 방법인 kernel 회귀모형을 분석하고, kernel 회귀모형의 중요 인자인 bandwidth의 선택 방법에 따른 kernel 회귀모형의 특성에 대해 비교 분석하였다.

대기질 예측을 위한 기후·대기환경 통합모델링시스템 (ICAMS)의 기온 및 강수량 예측 능력 평가 (Evaluation of Temperature and Precipitation on Integrated Climate and Air Quality Modeling System (ICAMS) for Air Quality Prediction)

  • 최진영;김승연;홍성철;이재범;송창근;이현주;이석조
    • 한국대기환경학회지
    • /
    • 제28권6호
    • /
    • pp.615-631
    • /
    • 2012
  • This study provides an evaluation for capability of Integrated Climate and Air quality Modeling System (ICAMS) on future regional scale climate projection. Temperature and precipitation are compared between ground-level observation data and results of regional models (MM5) for the past 30 years over the Korean peninsula. The ICAMS successfully simulates the local-scale spatial/seasonal variation of the temperature and precipitation. The probability distribution of simulated daily mean and minimum temperature agree well with the observed patterns and trends, although mean temperature shows a little cold bias about $1^{\circ}C$ compared to observations. It seems that a systematic cold bias is mostly due to an underestimation of maximum temperature. In the case of precipitation, the rainfall in winter and light rainfall are remarkably simulated well, but summer precipitation is underestimated in the heavy rainfall phenomena of exceeding 20 mm/day. The ICAMS shows a tendency to overestimate the number of washout days about 7%. Those results of this study indicate that the performance of ICAMS is reasonable regarding to air quality predication over the Korean peninsula.

다중 참조 영상의 적응적 선택 및 선택적 인트라 모드를 이용한 H.264/AVC의 고속 모드 결정 방법 (Fast Mode Decision in H.264/AVC Using Adaptive Selection of Reference Frame and Selective Intra Mode)

  • 이웅호;이정호;조익환;정동석
    • 한국통신학회논문지
    • /
    • 제31권3C
    • /
    • pp.271-278
    • /
    • 2006
  • 비트율-왜곡 최적화 기법은 H.264/AVC(Advance Video Coding)의 부호화 효율을 높이기 위한 방법이긴 하나 모드 결정 과정 중 부호화기의 복잡도를 높아지는 단점이 있다. 많은 고속화 모드결정 연구들이 모드결정의 복잡도를 줄이기 위하여 제안되어져 왔었다. 본 논문에서는 H.264/AVC의 모드결정의 전체적인 복잡도를 줄이기 위하여 다중 참조 영상 선택 고속화 알고리즘과 선택적인 인트라 모드 선택 알고리즘의 두 가지 고속화 알고리즘을 제안한다. 참조영상 선택 고속화 알고리즘은 인터 모드 결정에 효과적이며, 선택적인 인트라 모드 선해 알고리즘은 과도한 인트라 모드 결정의 계산량을 효율적으로 감소시켰다. 제안된 알고리즘을 실험한 결과로 평균 44.63%의 부호화 시간 감소비를 보이면서 영상의 열화와 같은 부호화 효율 감소는 거의 눈에 띄지 않았다.