• Management Science and Financial Engineering
• /
• 제16권2호
• /
• pp.53-65
• /
• 2010

Despite the overall success of neighbor-based CF methods, there are some fundamental questions about neighbor selection and prediction mechanism including arbitrary similarity, over-fitting interpolation weights, no trust consideration between neighbours, etc. This paper proposes a simple method to compute absolute interpolation weights based on similarity values. In order to supplement the method, two schemes are additionally devised for high-quality neighbour selection and trust metrics based on co-ratings. The former requires that one or more neighbour's similarity should be better than a pre-specified level which is higher than the minimum level. The latter gives higher trust to neighbours that have more co-ratings. Experimental results show that the proposed method outperforms the pure IBCF by about 8% improvement. Furthermore, it can be easily combined with other predictors for achieving better prediction quality.

• Korea-Australia Rheology Journal
• /
• 제16권3호
• /
• pp.129-134
• /
• 2004

The aggregation characteristics of red blood cells (RBCs) were measured using a newly developed light-transmission slit rheometer. Conventional methods of RBC disaggregation such as the rotational Couette system were replaced with a pressure-driven slit flow system with a vibrational mechanism. Using a vibration generator, one can disaggregate the RBC aggregates stored in the slit. While shear stress decreases exponentially, instantaneous pressure and the transmitted light intensity were measured over time. Applying an abrupt shearing flow after disaggregation caused a rapid elongation of the RBCs followed by loss of elongation with the decreasing shear stress. While the shear stress is further decreasing, the RBCs start to re-aggregate and the corresponding transmitted intensity increases with time, from which the aggregation indices can be obtained using a curve-fitting program.

• Journal of the Korean Statistical Society
• /
• 제34권3호
• /
• pp.209-218
• /
• 2005

In response surfaces analysis, we often proceed by supposing that, over a limited region of factor space, a polynomial of only first or second degree might adequately approximate the true function. To find the best subset model, all possible quadratic regressions for response surfaces can be very valuable to get optimum solutions under some reasonable experimentations. However, there is a very hard computational burden to get all possible quadratic regressions. In practice, it is sufficient to consider only hierarchical models. In this paper, we propose an algorithm to get all possible hierarchical quadratic regressions for fitting response surfaces.

• 대한기계학회논문집
• /
• 제18권5호
• /
• pp.1182-1191
• /
• 1994

This paper presents an enhanced method of slit beam projection intended for the rapid measurement of 3-dimensional surface profiles of dies and molds. Special emphasis is given to optimizing the design of optical system so that the measuring accuracy can be maximized by adopting two-plane camera calibration together with sub-pixel image processing techniques. Finally, several measurement examples are discussed to demonstrate that an actual measuring accuracy of $\pm$ 0.2 mm can be achieved over the measuring range of 500 mm{\times}300mm{\times}200mm$.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 추계학술대회논문집
• /
• pp.244-249
• /
• 2002

Rubber seat is extensively used to reduce the vibration of machine or structure. Over the years an enormous effort has been put into developing procedures to provide properties of rubber material for design function. However, there are still a lot of difficulties to analyze static characteristics of rubber components with hyper elasticity and nonlinear large deformation. In this paper material property is obtained by strain-stress curve using a tension test. Mooney-Rivlin Coefficients are gotten by fitting strain-stress curve. The visco-elastic characteristics of refrigerator rubber mount is determined by using ANSYS. And to minimize the rubber stiffness, the rubber seat shape optimization is performed.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2001년도 춘계학술대회 논문집
• /
• pp.106-109
• /
• 2001

The use of ceramic inserts in hot extrusion dies offers significant technical and economic advantages over other forms of manufacture. These potential benefits can however only be realized by optimal design of the tools so that the ceramic inserts are not subjected to stresses that lead to their premature failure. In this paper, process simulation and stress analysis are thus combined during the design, and a data exchange program has been developed that enables optimal design of the dies taking into account the elastic deflections generated in shrink fitting the die inserts and that caused by the stresses generated in the process. The stress analysis of the dies is used to determine the stress conditions on the ceramic insert by considering contact and interference effects under both mechanical and thermal loads. The results are compared with the experimental ones for verification.

• 환경생물
• /
• 제21권4호
• /
• pp.384-391
• /
• 2003

The induction of chromosome aberrations in Hordeum vulgare germs after irradiation is studied for the dose range of 10 to 1,000 mGy. The relationship between the frequency of aberrant cells and the absorbed dose is shown to be non -linear and has a dose-independent plateau within the range of 56-467 mGy where the level of cytogenetic damage is statistically significantly distinguished from the spontaneous level. The comparison of the goodness of the experimental data fitting with mathematical models of different complexities, using the most common quantitative criteria, demonstrates the benefit of the piecewise linear model over the linear and polynomial ones in approximating the cytogenetical disturbance frequency. The results of our study support the conclusion about indirect mechanism of chromosome aberrations induced by low doses or dose rates mutagenesis.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제12권2호
• /
• pp.81-95
• /
• 2008

In this paper, the negative Polya-Eggenberger distribution has been introduced by compounding negative binomial distribution with beta distribution of I-kind which generates a number of univariate contagious or compound (or mixture of) distributions as its particular cases. The distribution is unimode, over dispersed and all of its positive and negative integer moments exist. The difference equation of the proposed model shows that it is a member of the Ord's family of distribution. Some of its interesting properties have been explored besides different methods of estimation been discussed. Finally, the parameters of the proposed model have been estimated by using a computer programme in R-software. Application of the proposed model to some data, available in the literature, has been given and its goodness of fit demonstrated.

• Smart Structures and Systems
• /
• 제10권4_5호
• /
• pp.459-470
• /
• 2012

This paper summarizes a study for the modal analysis and model updating conducted using the monitoring data obtained from the Canton Tower of 610 m tall, which was established as an international benchmark problem by the Hong Kong Polytechnic University. Modal properties of the tower were successfully identified using frequency domain decomposition and stochastic subspace identification methods. Finite element model updating using the measurement data was further performed to reduce the modal property differences between the measurements and those of the finite element model. Over-fitting during the model updating was avoided by using an optimization scheme with a regularization term.

• The Journal of the Acoustical Society of Korea
• /
• 제22권3E호
• /
• pp.124-132
• /
• 2003

We propose a new method for speech/non-speech classifiers based on concepts of the adaptive boosting (AdaBoost) algorithm in order to detect speech for robust speech recognition. The method uses a combination of simple base classifiers through the AdaBoost algorithm and a set of optimized speech features combined with spectral subtraction. The key benefits of this method are the simple implementation, low computational complexity and the avoidance of the over-fitting problem. We checked the validity of the method by comparing its performance with the speech/non-speech classifier used in a standard voice activity detector. For speech recognition purpose, additional performance improvements were achieved by the adoption of new features including speech band energies and MFCC-based spectral distortion. For the same false alarm rate, the method reduced 20-50% of miss errors.