The Optimization of Bank Branches Efficiency by Means of Response Surface Method and Data Envelopment Analysis: A Case of Iran

Elham Shadkam,Mehdi Bijari 한국유통과학회 2015 The Journal of Asian Finance, Economics and Busine Vol.2 No.2

In this paper the DRC model is presented for solving multi objective problem. The proposed model is a combination of data envelopment analysis, Cuckoo algorithm and the response surface method. Due to reasons like costs, time and irreversible damages, it is not possible to analyze each and every one of the proposed models in practice, so the simulation is used. Since the number of experiments for simulation process is high then the optimization has gone to practice and directs the simulation process. The response surface method is used as one of the approaches of simulation optimization. Furthermore, data envelopment analysis is used to consider several response surfaces as efficiency response surface. Then this efficiency response surface is solved by Cuckoo algorithms. The main advantage of DRC model is to make one efficiency response surface function instate of multi surface function for every output and also using the advantages of Cuckoo algorithms. In order to demonstrate the effectiveness of the proposed approach, the branches of Refah bank in Mashhad is analyzed and the results are presented.

A STUDY ON THE RESPONSES OF OSTEOBLASTS TO VARIOUS SURFACE-TREATED TITANIUM

Lee Joung-Min,Kim Yung-Soo,Kim Chang-Whe,Jang Kyung-Soo,Lim Young-Jun The Korean Academy of Prosthodonitics 2004 대한치과보철학회지 Vol.42 No.3

Statement of problem. The long-term success of implants is the development of a stable direct connection between bone and implant surface, which must be structural and functional. To improve a direct implant fixation to the bone, various strategies have been developed focusing on the surface of materials. Among them, altering the surface properties can modify cellular responses such as cell adhesion, cell motility and bone deposition. Purpose. This study was to evaluate the cellular behaviors on the surface-modified titanium by morphological observation, cellular proliferation and differentiation. Material and methods. Specimens were divided into five groups, depending on their surface treatment: electropolishing(EP) anoclizing(AN), machining(MA), blasting with hydroxyapatite particle(RBM) and electrical discharge machining(EDM). Physicochemical properties and microstructures of the specimens were examined and the responses of osteoblast-like cells were investigated. The microtopography of specimens was observed by scanning electron microscopy(SEM). Surface roughness was measured by a three-dimensional roughness measuring system. The microstructure was analyzed by X-ray diffractometer(XRD) and scanning auger electron microscopy(AES). To evaluate cellular responses to modified titanium surfaces, osteoblasts isolated from neonatal rat were cultured. The cellular morphology and total protein amounts of osteoblast-like cell were taken as the marker for cellular proliferation, while the expression of alkaline phosphatase was used as the early differentiation marker for osteoblast. In addition, the type I collagen production was determined to be a reliable indicator of bone matrix synthesis. Results. 1. Each prepared specimen showed specific microtopography at SEM examination. The RBM group had a rough and irregular pattern with reticulated appearance. The EDM-treated surface had evident cracks and was heterogeneous consisting of broad sheet or plate with smooth edges and clusters of small grains, deep pores or craters. 2. Surface roughness values were, from the lowest to the highest, electropolished group, anodized group, machined group, RBM group and EDM group. 3. All groups showed amorphous structures. Especially anodized group was found to have increased surface oxide thickness and EDM group had titaniumcarbide(TiC) structure. 4. Cells on electropolished, anodized and machined surfaces developed flattened cell shape and cells on RBM appeared spherical and EDM showed both. After 14 days, the cells cultured from all groups were formed to be confluent and exhibited multilayer proliferation, often overlapped or stratified. 5. Total protein amounts were formed to be quite similar among all the group at 48 hours. At 14 days, the electropolished group and the anodized group induced more total protein amount than the RBM group(P<.05). 6. There was no significant difference among five groups for alkaline phosphatase(ALP) activity at 48 hours. The AN group showed significantly higher ALP activity than any other groups at 14 days(P<.05). 7. All the groups showed similar collagen synthesis except the EDM group. The amount of collagen on the electropolished and anodized surfaces were higher than that on the EDM surface(P<.05).

A STUDY ON OSTEOBLAST-LIKE CELL RESPONSES TO SURFACE-MODIFIED TITANIUM

Hong Min-Ah,Kim Yung-Soo,Kim Chang-Whe,Jang Kyung-Su,Lee Jae-Il The Korean Academy of Prosthodonitics 2003 대한치과보철학회지 Vol.41 No.3

Statement of problem: The success of implants depends on intimate and direct contact of implant material on bone tissue and on functional relationship with soft tissue contact. Creation and maintenance of osseointegration depend on the understanding of the tissue's healing, repairing, and remodeling capacity and these capacities rely on cellular behavior. Altering the surface properties can modify cellular responses such as cell adhesion, cell motility, bone deposition, Therefore, various implant surface treatment methods are being developed for the improved bone cell responses. Purpose: The purpose of this study was to evaluate the responses of osteoblast-like cells to surface-modified titanium. Materials and Methods: The experiment was composed of four groups. Group 1 represented the electropolished surface. Group 2 surfaces were machined surface. Group 3 and Group 4 were anodized surfaces. Group 3 had low roughness and Group 4 had high roughness. Physicochemical properties and microstructures of the discs were examined and the responses of osteoblast-like cells to the discs were investigated. The microtopography was observed by SEM. The roughness was measured by three-dimension roughness measuring system. The microstructure was analyzed by XRD, AES. To evaluate cell responses to modified titanium surfaces, osteoblasts isolated from calvaria of neonatal rat were cultured. Cell count, morphology, total protein measurement and alkaline phosphatase activities of the cultures were examined. Results and Conclusion: The results were as follows 1. The four groups showed specific microtopography respectively. Anodized group showed grain structure with micropores. 2. Surface roughness values were, from the lowest to the highest, electropolished group, machined group, low roughness anodized group, and high roughness anodized group. 3. Highly roughened anodized group was found to have increased surface oxide thickness and surface crystallinity. 4. The morphology of cells, flattened or spherical, were different from each other. In the electropolished group and machined group, the cells were almost flattened. In two anodized groups, some cells were spherical and other cells were flattened. And the 14 day culture cells of all of the groups were nearly flattened due to confluency. 5. The number of attached cells was highest in low roughness anodized group. And the machined group had significantly lower cell count than any other groups(P<.05). 6. Total protein contents showed no difference among groups. 7. The level of alkaline phosphatase activities was higher in the anodized groups than electropolished and machined groups(P<.05).

Capabilities of stochastic response surface method and response surface method in reliability analysis

Jiang, Shui-Hua,Li, Dian-Qing,Zhou, Chuang-Bing,Zhang, Li-Min Techno-Press 2014 Structural Engineering and Mechanics, An Int'l Jou Vol.49 No.1

The stochastic response surface method (SRSM) and the response surface method (RSM) are often used for structural reliability analysis, especially for reliability problems with implicit performance functions. This paper aims to compare these two methods in terms of fitting the performance function, accuracy and efficiency in estimating probability of failure as well as statistical moments of system output response. The computational procedures of two response surface methods are briefly introduced first. Then their capabilities are demonstrated and compared in detail through two examples. The results indicate that the probability of failure mainly reflects the accuracy of the response surface function (RSF) fitting the performance function in the vicinity of the design point, while the statistical moments of system output response reflect the accuracy of the RSF fitting the performance function in the entire space. In addition, the performance function can be well fitted by the SRSM with an optimal order polynomial chaos expansion both in the entire physical and in the independent standard normal spaces. However, it can be only well fitted by the RSM in the vicinity of the design point. For reliability problems involving random variables with approximate normal distributions, such as normal, lognormal, and Gumbel Max distributions, both the probability of failure and statistical moments of system output response can be accurately estimated by the SRSM, whereas the RSM can only produce the probability of failure with a reasonable accuracy.

Capabilities of stochastic response surface method and response surface method in reliability analysis

Shui-Hua Jiang,Dian-Qing Li,Chuang-Bing Zhou,Li-Min Zhang 국제구조공학회 2014 Structural Engineering and Mechanics, An Int'l Jou Vol.49 No.1

The stochastic response surface method (SRSM) and the response surface method (RSM) are often used for structural reliability analysis, especially for reliability problems with implicit performance functions. This paper aims to compare these two methods in terms of fitting the performance function, accuracy and efficiency in estimating probability of failure as well as statistical moments of system output response. The computational procedures of two response surface methods are briefly introduced first. Then their capabilities are demonstrated and compared in detail through two examples. The results indicate that the probability of failure mainly reflects the accuracy of the response surface function (RSF) fitting the performance function in the vicinity of the design point, while the statistical moments of system output response reflect the accuracy of the RSF fitting the performance function in the entire space. In addition, the performance function can be well fitted by the SRSM with an optimal order polynomial chaos expansion both in the entire physical and in the independent standard normal spaces. However, it can be only well fitted by the RSM in the vicinity of the design point. For reliability problems involving random variables with approximate normal distributions, such as normal, lognormal, and Gumbel Max distributions, both the probability of failure and statistical moments of system output response can be accurately estimated by the SRSM, whereas the RSM can only produce the probability of failure with a reasonable accuracy.

다구치 분석과 분산반응표면 분석을 활용한 최적점 탐사

정형철 한국자료분석학회 2010 Journal of the Korean Data Analysis Society Vol.12 No.2

Taguchi methods or response surface methods are frequently used by researchers to find the optimal design points in sensory evaluation or engineering processes. In this paper, we considered the process to find the optimal design points of the three factor which are considered of important ingredient factors to produce the rice-bread. The three factors are hydroxy propyl methyl cellulose, carboxy methyl cellulose, and a kind of lactose. The response variables are dense, hardness and volume of rice-bread are simultaneously measured by rheometer. In this case study, we considered the responses one by one not simultaneous, and used three methods to find the optimal design points, which are Taguchi method, ridge system and response surface method based on mean and variance response. The results of three methods are product the similar results, especially Taguich method and response surface method based on the minimizing the variance response make same results. With based on the fact, response surface method based on variance response have used a response surface alternative to the Taguchi robust parameter design approach. 식품의 관능검사나 최적화 조건을 탐사하는 방법으로 반응표면 분석이나 다구치 방법이 널리 활용된다. 본 연구에서는 쌀빵을 생산하는 데 있어 중요하게 판단되는 세 변인에 대한 다중 반응결과에 기초하여 각각의 최적점을 탐사하는 과정을 다루었다. 여기에서 다구치 방법과 능형분석 그리고 평균반응과 분산반응을 고려하는 반응표면분석을 사용하여 최적점을 비교하였다. 주된 실험이 2 수준 요인 실험이므로 반응표면분석으로는 최적점을 찾는 것이 다소 어렵다. 그러므로 다구치 실험결과를 기초로 반응표면의 분산을 최소로 하는 최적점을 찾는 방법을 사용하여 다구치 결과와 비교하였다. 비교결과 다구치 분석, 분산반응표면 결과가 매우 유사하였으며, 능형분석과는 약간의 차이가 있음을 볼 수 있었다.

Long-term real-world entecavir therapy in treatment-naive hepatitis B patients: base-line hepatitis B virus DNA and hepatitis B surface antigen levels predict virologic response

( Ju-yeon Cho ),( Won Sohn ),( Dong-hyun Sinn ),( Geum-youn Gwak ),( Yong-han Paik ),( Moon Seok Choi ),( Kwang Cheol Koh ),( Seung Woon Paik ),( Byung Chul Yoo ),( Joon Hyeok Lee ) 대한내과학회 2017 The Korean Journal of Internal Medicine Vol.32 No.4

Background/Aims: Entecavir is a potent nucleoside analogue with high efficacy and barrier for resistance. We aimed to investigate the long-term efficacy and viral resistance rate of entecavir and explore the factors associated with virologic response, including quantitative hepatitis B surface antigen (qHBsAg) levels. Methods: One thousand and nine treatment-naive chronic hepatitis B (CHB) patients were evaluated for cumulative rates of virologic response, biochemical response, and entecavir mutations. The role of baseline qHBsAg for virologic response was assessed in 271 patients with qHBsAg prior to entecavir treatment. Results: The median duration of entecavir treatment was 26.5 months. The cumulative rate of virologic response at years 1, 3, and 5 were 79.0%, 95.6%, and 99.4%, respectively. The cumulative rate of entecavir resistance was 1.0% and 2.1% in years 3 and 5. Multivariate analysis identified baseline hepatitis B e antigen (HBeAg) negative status (p < 0.001) and lower hepatitis B virus (HBV) DNA (p < 0.001) as predictors of virologic response. Lower qHBsAg was an independent predictor of virologic response in patients with baseline qHBsAg. There were no serious adverse events during treatment. Conclusions: Long-term entecavir treatment of nucleos(t)ide-naive CHB patients was associated with an excellent virologic response and a low rate of entecavir-resistant mutations at 5 years. Baseline HBV DNA load, qHBsAg levels, and HBeAg status were predictors of virologic response during entecavir treatment.

Reliability Analysis of Net Cross-section Resistance with Accidental Eccentricity of Holes

Franc Sinur,Darko Beg 한국강구조학회 2009 International Journal of Steel Structures Vol.9 No.2

The aim of the research was to determine reliability function of net cross-section resistance in relation to accidental eccentricity of nominally centric holes. The response surface method was used by taking into account the relevant Eurocode design provisions and reliability requirements. Within the response surface method, the central composite design method and the least square method were used with the employment of Monte Carlo simulations. The probable distributed variables such as strength fy, breadth b, thickness t, diameter d0 and eccentricity e were determined by the central composite design method. 280 different numerical simulations were set up with varying variables. A log-normal distribution for strength (fy) and a normal distribution for geometrical variables (b, t, d0, e) were employed by taking into account the coefficients of variations: Vfy=0.07, Vb=0.005, Vt=0.05 and Vd0=0.005. In order to determine the influence of eccentricity on partial safety factor, several normal distributions with different variation factors were applied in the analysis. The influence of the edge distance of the hole e2 over d0 ratio on the partial safety factor was determined by varying mean values of variable b. For comparison, two types of steel were used: structural steel S235 and high strength steel S690. Numerical simulations of the net cross-section resistance Fu were performed with ABAQUS 6.7. The response surface for the net cross-section resistance was determined by introducing a quadratic approximation function and by applying the least square method. The partial safety factor was then (statistically) obtained by means of robust Monte Carlo simulations on the calculated response surface. The aim of the research was to determine reliability function of net cross-section resistance in relation to accidental eccentricity of nominally centric holes. The response surface method was used by taking into account the relevant Eurocode design provisions and reliability requirements. Within the response surface method, the central composite design method and the least square method were used with the employment of Monte Carlo simulations. The probable distributed variables such as strength fy, breadth b, thickness t, diameter d0 and eccentricity e were determined by the central composite design method. 280 different numerical simulations were set up with varying variables. A log-normal distribution for strength (fy) and a normal distribution for geometrical variables (b, t, d0, e) were employed by taking into account the coefficients of variations: Vfy=0.07, Vb=0.005, Vt=0.05 and Vd0=0.005. In order to determine the influence of eccentricity on partial safety factor, several normal distributions with different variation factors were applied in the analysis. The influence of the edge distance of the hole e2 over d0 ratio on the partial safety factor was determined by varying mean values of variable b. For comparison, two types of steel were used: structural steel S235 and high strength steel S690. Numerical simulations of the net cross-section resistance Fu were performed with ABAQUS 6.7. The response surface for the net cross-section resistance was determined by introducing a quadratic approximation function and by applying the least square method. The partial safety factor was then (statistically) obtained by means of robust Monte Carlo simulations on the calculated response surface.

다중 반응표면식의 최적화

이우선 한국자료분석학회 2010 Journal of the Korean Data Analysis Society Vol.12 No.2

Response surface methodology is useful in the solution of many types of industrial problems. This paper has focused on the optimization of the multiple responses. Simultaneous consideration of multiple responses involves first building an appropriate response surface model for each response and then trying to find a set of conditions that optimize all responses or at least keeps them in desired ranges. Two major methods of approaches to multiple response optimization are the generalized distance approach(Khuri and Conlon, 1981) and the desirability function approach(Derringer and Suich, 1980). Desirability function approach is very useful in the case of multiple responses. This method makes use of a desirability function in which the researchers own priorities and desires on the response values are considered in the optimization procedure. This paper first reviewed the specific characteristics of the two approaches in detail. Also, actual data analysis was done using the generalized distance approach and the desirability function approaches of which results are shown in this paper. 본 연구는 둘 이상의 반응변수들을 동시에 만족시키는 다중 반응표면식의 최적화(optimization of multi-response surface) 문제를 다루고 있다. 이 방법들 중에서도 Khuri와 Cornell의 일반화 거리(generalized distance approach) 방법과 Derringer와 Suich의 바람직성 함수를 이용한 방법을 비교 분석하였다. 일반화 거리 방법은 실제로 다중 반응표면식의 최적점이 실험설계 공간의 중심에서 많이 떨어진 경계선에 근접한 점들이 선택될 위험이 상대적으로 높다는 사실을 알 수 있었다. 이 방법의 대안으로 바람직성 함수를 이용하여 전체적인 만족값을 최대로 하는 독립변수들의 수준을 찾는 바람직성함수 방법은 반응변수에 대한 중요가 다를 경우 아주 유용한 방법이며 일반화 거리 방법의 문제점을 다소나마 해결할 수 있는 방법으로 평가되고 있다. 이를 실증적으로 입증하기 위하여 Khuri와 Cornell(1996)의 실험분석사례의 자료를 근거로 일반화 거리 방법과 바람직성 함수를 이용한 방법의 결과를 구하고 이 두 방법의 차이를 비교분석하였다.

Statistical Modeling of Pretilt Angle Control on theHomogeneous Polyimide Surface as a Function ofRubbing Strength and Baking Temperature

Hee-Jin Kang,이정환,황정연,윤일구,Dae-Shik Seo 한국전기전자재료학회 2006 Transactions on Electrical and Electronic Material Vol.7 No.2

In this paper, the response surface modeling of the control of the pretilt angle in the nematic liquid crystal on the homogeneous polyimide surface with different surface treatment is investigated. The pretilt angle is one of the main factors to determine the alignment of the liquid crystal display. The pretilt angle is measured to analyze the variation of the characteristics on the various process conditions. The rubbing strength and the hard baking temperature are considered as input factors. After the design of experiments is performed, the process model is then explored using the response surface methodology. The analysis of variance is used to analyze the statistical significance and the effect plots are also investigated to examine the relationship between the process parameters and the response.