• Wind and Structures
• /
• 제18권6호
• /
• pp.619-631
• /
• 2014

This paper proposes new criteria to fix hidden neuron in Multilayer Perceptron Networks for wind speed prediction in renewable energy systems. To fix hidden neurons, 101 various criteria are examined based on the estimated mean squared error. The results show that proposed approach performs better in terms of testing mean squared errors. The convergence analysis is performed for the various proposed criteria. Mean squared error is used as an indicator for fixing neuron in hidden layer. The proposed criteria find solution to fix hidden neuron in neural networks. This approach is effective, accurate with minimal error than other approaches. The significance of increasing the number of hidden neurons in multilayer perceptron network is also analyzed using these criteria. To verify the effectiveness of the proposed method, simulations were conducted on real time wind data. Simulations infer that with minimum mean squared error the proposed approach can be used for wind speed prediction in renewable energy systems.

• Journal of information and communication convergence engineering
• /
• 제7권2호
• /
• pp.193-198
• /
• 2009

The H.264/ AVC video coding standard supports the intra prediction with various block sizes for luma component and a 8x8 block size for chroma components. This new feature of H.264/AVC offers a considerably higher improvement in coding efficiency compared to previous compression standards. In order to achieve this, H.264/AVC uses the Rate-distortion optimization (RDO) technique to select the best intra prediction mode for each block size, and it brings about the drastic increase of the computation complexity of H.264 encoder. In this paper, a fast block size decision algorithm is proposed to reduce the computation complexity of the intra prediction in H.264/AVC. The proposed algorithm computes the smoothness based on AC and DC coefficient energy for macroblocks and compares with the nonparametric criteria which is determined by considering information on neighbor blocks already reconstructed, so that deciding the best probable block size for the intra prediction. Also, the use of non-parametric criteria makes the performance of intra-coding not be dependent on types of video sequences. The experimental results show that the proposed algorithm is able to reduce up to 30% of the whole encoding time with a negligible loss in PSNR and bitrates and provides the stable performance regardless types of video sequences.

• 소성∙가공
• /
• 제14권7호
• /
• pp.601-606
• /
• 2005

A hole expansion process is an important process in producing a hub-hole in a wheel disc of a vehicle. In this process, the main parameter is the formability of a material that is expressed as the hole expansion ratio. In the process, a crack is occurred in the upper edge of a hole as the hole is expanded. Since prediction of the forming limit by hole expansion experiment needs tremendous time and effort, an appropriate fracture criterion has to be developed for finite element analysis to define forming limit of the material. In this paper, the hole expansion process of a hub-hole is studied by finite element analysis with ABAQUS/standard considering several ductile fracture criteria. The fracture mode and hole expansion ratio are compared with respect to the various fracture criteria. These criteria do not predict its fracture mode or hole expansion ratio adequately and show deviation from experimental results of hole expansion. A modified ductile fracture criterion is newly proposed to consider the deformation characteristics of a material accurately in a hole expansion process. A fracture propagation analysis at the hub-hole edge is also performed for high accuracy of prediction using the new fracture criterion proposed.

• 대한기계학회논문집A
• /
• 제33권2호
• /
• pp.114-126
• /
• 2009

In this paper, a versatile multi-criteria optimization concept for fatigue life prediction is introduced. Multi-criteria decision making in engineering design refers to obtaining a preferred optimal solution in the context of conflicting design objectives. Compromise decision support problems are used to model engineering decisions involving multiple trade-offs. These methods typically rely on a summation of weighted attributes to accomplish trade-offs among competing objectives. This paper gives an interpretation of the decision parameters as governing both the relative importance of the attributes and the degree of compensation between them. The approach utilizes a response surface model, the compromise decision support problem, which is a multi-objective formulation based on goal programming. Examples illustrate the concepts and demonstrate their applicability.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• 제18권4호
• /
• pp.973-983
• /
• 2007

Korea Military Academy has been using College Scholastic Ability Test(CSAT) and High School Grades(HSG) with other measures such as an Essay-type Test(ET), Physical Test(PT) and Personal Interview(PI) as criteria for entrance. The purpose of study is to investigate the properness of the criteria in admission decisions by examining the relationship between the college GPA and criteria, and the prediction of academic performance. The study showed that CSAT and HSG are significantly correlated with the college GPA, and these two criteria are better predictors for academic performance. Regression analysis also provided an important message that HSG is a better predictor than CSAT.

• 대한기계학회논문집A
• /
• 제20권3호
• /
• pp.832-842
• /
• 1996

Fatigue life prediction and fatigue behavior of circular notched carbon fiber reinforced plastic laminates are presented. Point and average stress criteria by Whitney and Nuismer are generalized to fatigue fracture criteria for notched laminates. Residual strength degradation model and the assumptions on the stress redistribution are introduced during the derivation of prediction equations. S-N curve, Basquin's relation, and H and H's FLPE1 are chosen for evaluation of residual strength of unnotched laminates and six prediction equations are derived. Experiments are performed using Graphite/Epoxy laminates whose fiber orientation is $[0$^\circ$/+45$^\circ$/-45$^\circ$/90$^\circ$]s. Presented prediction equations are reasonably close to experimental data and proposed appoach is found to be suitable to predict fatigue life of notched composite laminates.

• 한국화재소방학회논문지
• /
• 제14권4호
• /
• pp.7-16
• /
• 2000

본 연구에서는 대상물질을 선점한 후 그에 따른 세 가지 기준 즉 독성, 화재폭발, 환경기준과 각각의 피해예측기법을 설정하고 이 기준들을 알고리즘을 통한 통합한 종합위해등급으로서 선정된 대상물질에 적용하였다. 특히, 환경기준은 포괄적인 개념으로서 USCG 및 MSDS의 환경기준 분류와 NFPA의 건강위해성(Nh) 중 환경관련 부분을 조합하여 환경지수 모델화를 하였다. 또한 각 기준에 따른 피해예측 기법을 선택하여 지역별 인의에 위치한 화학물질 관련업체에 사용 또는 저장 중인 유해화학물질에 대해 적용하여 사용물질에 대한 종합위해등급 설정(단일물질에 대한 가연성, 독성, 반응성, 환경성에 대한 Hazard level 및 표시 모델화) 및 그에 따른 사고시 피해예측 강도산정 (CPQRA, IAEA, VZ eq), Risk contour를 구할 수 있었다. 이 결과 모든 화학공정 및 저장 등에서 발생할 수 있는 독성 누출, 화재폭발의 잠재적 위험성산정을 통한 안전성 평가의 Tool로 활용이 가능하다.

• 한국자동차공학회논문집
• /
• 제9권6호
• /
• pp.160-169
• /
• 2001

To predict busting failure in tubular hydroforming, the criteria for ductile fracture proposed by Oyane is combined with the finite element method. From the histories of stress and strain in each element obtained from finite element analysis, the fracture initiation site is predicted by mean of the criterion. The prediction by the ductile fracture criterion is applied to three hydroforming processes such as a tee extrusion, an automobile rear axle housing and lower am. For these products, the ductile fracture integral I is not only affected by the process parameters, but also by preforming processes. All the simulation results show the combination of the finite element analysis and the ductile fracture criteria is useful in the prediction of farming limit in hydroforming processes.

• 대한임베디드공학회논문지
• /
• 제18권2호
• /
• pp.59-65
• /
• 2023

Currently, polysomnography is essential to diagnose sleep-related breathing disorders. However, there are several disadvantages to polysomnography, such as the requirement for multiple sensors and a long reading time. In this paper, we propose a system for predicting the severity of sleep-related breathing disorders at home utilizing measurable elements in a wearable device. To predict severity, the variables were refined through a three-step variable selection process, and the refined variables were used as inputs into three machine-learning models. As a result of the study, random forest models showed excellent prediction performance throughout. The best performance of the model in terms of F1 scores for the three threshold criteria of 5, 15, and 30 classified as the AHI index was about 87.3%, 90.7%, and 90.8%, respectively, and the maximum performance of the model for the three threshold criteria classified as the RDI index was approx 79.8%, 90.2%, and 90.1%, respectively.