Showing 686 results for Type of Study: Research
Hossein Abbasimehr,
Volume 0, Issue 0 (10-2024)
Abstract
Businesses are aware of the importance of customer relationship management and strive to gain insights into customers and their needs. Clustering and prediction are widely used data mining methods for understanding customer behavior. In this paper, we introduce an intelligent approach that utilizes time series clustering to analyze customer behavior. To segment customers, we first construct time series of their behavior and then perform preprocessing on the data. Subsequently, a set of informative features reflecting the characteristics of each time series is extracted. These features are ranked using the Laplacian Score method and employed in clustering. The proposed method is applied to time-stamped transaction data of bank customers. After constructing a customer behavior series and extracting features, four informative features —variance of all points in the time series, entropy, spikiness, and lumpiness —are selected for clustering. Customer clustering is performed using four state-of-the-art clustering algorithms: k-medoids, k-means, Fuzzy C-Means clustering (FCM), and Self-Organizing Map (SOM) algorithms. The results demonstrate that, among various clustering methods, the k-medoids algorithm outperforms others. It divides customers into four clusters with a Silhouette metric of 0.6378.
Mojtaba Nowrouzifasih, Anwar Mahmoodi, Reza Maihami,
Volume 0, Issue 0 (10-2024)
Abstract
The demand for green products has increased in the past few years due to the heightened awareness of environmental issues and the increasing use of green products by consumers. Thus, choosing the best strategy for green product manufacturers is essential. At the same time, producers and retailers are likely to have their decisions influenced by government actions. In this study, we attempt to determine the product's price and greenness within two competitive supply chains. The study investigates the pricing of two substitutable and green products in which each supply chain produces a green product. Using Nash and Stackelberg Game models, we determine how supply chains and their members interact. A Nash model involves two competing supply chains with equal power, within each supply chain, however, there is a Stackelberg competition between the retailer and the manufacturer. The Stackelberg model assumes that one of the supply chains is the market leader. The results show that with increasing government intervention (government's adjustment factor and green level floor for subsidies), regardless of Nash or Stackelberg structures, the green level of the product will increase, and wholesale and retail prices will decrease. Additionally, the price changes in the retailer-Stackelberg structure are greater than those in the manufacturer-Stackelberg structure. Also, by bearing the greenness cost by the manufacturer or retailer, companies can positively impact their profits as well as the level of greenness in their products. When the manufacturer makes an investment in greenness, the retailer and consumer benefit from it, and ultimately become the main force behind the development of green products.
Raden Pujiyono, Marimin Marimin, Arif Imam Suroso, Setiadi Djohar,
Volume 0, Issue 0 (10-2024)
Abstract
| The Indonesian paint industry contributes significantly to the national economy but remains highly dependent on imported raw materials, constituting approximately 77% of the total supply. This study aims to develop strategic solutions to increase local content and reduce import dependency by applying the Analytic Hierarchy Process (AHP) and Interpretive Structural Modeling (ISM). Based on AHP results, Capacity Building and Workforce Development emerged as the top-ranked strategy, with a final priority value of 0.330, followed by Strengthening Local Supply Chain (0.262). ISM analysis identified the Centre for Increasing Local Content as a key institutional driver influencing other actors in the supply chain. The sensitivity analysis confirmed the robustness of the AHP prioritization, showing less than 5% variation in rankings across multiple expert input scenarios. This indicates that the proposed strategies are stable and reliable under varying assumptions. The research provides a structured, multi-criteria framework aligning local strategies with national policy and international trade obligations. The study offers policymakers and industry leaders practical insights by integrating technology, human capital, and supply chain optimization to support a resilient and sustainable local content policy. Integrating AHP and ISM methods presents a novel approach, contributing original insights to the industrial strategy literature. |
Ida Lumintu, Achmad Maududie,
Volume 0, Issue 0 (10-2024)
Abstract
Effective inventory management is critical for mitigating inefficiencies such as overproduction, excessive holding costs, and stockouts. This study leverages DBSCAN and GMM clustering methods, combined with Principal Component Analysis (PCA) for dimensionality reduction, to categorize inventory data into distinct risk-based clusters. The analysis highlights that DBSCAN outperformed GMM, achieving a silhouette score of 0.62 compared to 0.49, while identifying three meaningful inventory clusters. Each cluster reflects unique combinations of risk factors, providing actionable insights for optimizing inventory levels. The study demonstrates how these clusters enable targeted strategies to address inefficiencies and improve overall inventory management. Limitations include the reliance on historical data, which may not fully capture dynamic market conditions, and the assumption of fixed clustering parameters. The findings underscore the importance of choosing clustering algorithms suited to the data's characteristics and highlight the potential of PCA in enhancing computational efficiency. Future research should explore dynamic clustering techniques and integrate real-time data streams to refine inventory management strategies further.
F.d. Javanroodi , K. M. Nikbin ,
Volume 17, Issue 3 (9-2006)
Abstract
There is an increasing need to assess the service life of components containing defect which operate at high temperature. This paper describes the current fracture mechanics concepts that are employed to predict cracking of engineering materials at high temperatures under static and cyclic loading. The relationship between these concepts and those of high temperature life assessment methods is also discussed. A model for predicting creep crack growth initiation and growth in terms of C* and the creep uniaxial ductility is presented and it is shown that this model gives good agreement with the experimental results. The effects of cyclic loading on crack growth behaviour are considered and fractography evidence is shown to back a simple cumulative damage concept when dealing with creep/fatigue interaction. Finally a discussion is presented which highlights the important aspect of life assessment methodology for high temperature plant.
H. Yarjiabadi, M. H. Shojaeefard, A.r. Noorpoor, H.yarjiabadi, , M. Habibian , A.r. Noorpoor ,
Volume 17, Issue 3 (9-2006)
Abstract
The hydrocyclone has a very important roll in industrial separation. The consideration of its behavior is very important for design. In this investigation, behavior of water flow and particles trajectory inside a hydrocyclone has been considered by means of numerical and experimental methods, and results have been compared together. To have a numerical simulation, a CFD software was used, and for modeling flow the RNG k – model applied. Finally, the effect of particle size on hydrocyclone performance has been studied. It was found that the grade efficiency and number of particle that exit from underflow of the hydrocyclone is increased when bigger particles is used.
A series of experiments has been carried out in a laboratory with a hydrocyclone. Comparison shows that, there is a good agreement between the CFD models and experimental result.
M. Haghpanahi, H. Pirali ,
Volume 17, Issue 3 (9-2006)
Abstract
Finite element analysis of a tubular T-joint subjected to various loading conditions including pure axial loading, pure in-plane bending (IPB) and different ratios of axial loading to in-plane bending loading has been carried out. This effort has been established to estimate magnitudes of the peak hot spot stresses (HSS) at the brace/chord intersection and to find the corresponding locations as well, since, in reality, offshore tubular structures are subjected to combined loading, and hence fatigue life of these structures is affected by combined loading. Therefore in this paper, at the first step, stress concentration factors (SCFs) for pure axial loading and in-plane bending loading are calculated using different parametric equations and finite element method (FEM). At the next step, the peak HSS distributions around the brace/chord intersection are presented and verified by the results obtained from the API RP2A Code procedure. Also the locations of the peak hot spot stresses which are the critical points in fatigue life assessment have been predicted.
M. M. Shokrieh, R. Rafiee ,
Volume 17, Issue 3 (9-2006)
Abstract
The main goal of this research is to extract the full mechanical properties of stitch biax and triax composite materials which are necessary for finite element analysis, based on limited available experimental data and without performing full static characterization tests. Utilized experimental data are limited to elastic modulus of two 0o and 45o directions. Using presented technique and aforementioned data, mechanical properties of unidirectional fabrics of biax and triax are obtained and consequently mechanical properties of biax and triax composites are calculated. Evaluation of the results proved proper performance of the technique in this research.
M.r. Modarres Razavi, S.h. Seyedein, P.b. Shahabi , S.h Seyedein,
Volume 17, Issue 3 (9-2006)
Abstract
In this paper hemodynamic wall parameters which play an important role to diagnose arterial disease were studied and compared for three different rheology models (Newtonian, Power law and Quemada). Also because of the pulsatile behavior of blood flow the results were obtained for three Womersley numbers which represent the frequencies of the applied pulses. Results show that Quemada model always located between Newtonian and Power law models however its behavior is closer to Power law model. Concerning this behavior and better agreement between Quemada and experimental blood viscosity, it can be expected that Quemada results are more realistic and accurate.
M. Nikian, , M. Naghashzadegan, S. K. Arya ,
Volume 17, Issue 3 (9-2006)
Abstract
The cylinder working fluid mean temperature, rate of heat fluxes to combustion chamber and temperature distribution on combustion chamber surface will be calculated in this research. By simulating thermodynamic cycle of engine, temperature distribution of combustion chamber will be calculated by the Crank-Nicolson method. An implicit finite difference method was used in this code. Special treatments for piston movement and a grid transformation for describing the realistic piston bowl shape were designed and utilized. The results were compared with a finite element method and were verified to be accurate for simplified test problems. In addition, the method was applied to realistic problems of heat transfer in an Isuzu Diesel engine, and gave good agreement with available experimental.
M. H. Shojaeefard, F. A. Boyaghchi , M. B. Ehghaghi ,
Volume 17, Issue 4 (11-2006)
Abstract
In this paper the centrifugal pump performances are tested when handling water and viscous oils as Newtonian fluids. Also, this paper shows a numerical simulation of the three-dimensional fluid flow inside a centrifugal pump. For these numerical simulations the SIMPLEC algorithm is used for solving governing equations of incompressible viscous/turbulent flows through the pump. The k-ε turbulence model is adopted to describe the turbulent flow process. These simulations have been made with a steady calculation using the multiple reference frames (MRF) technique to take into account the impeller- volute interaction. Numerical results are compared with the experimental characteristic curve for each viscous fluid. The data obtained allow the analysis of the main phenomena existent in this pump, such as: head, efficiency and power changes for different operating conditions. Also, the correction factors for oils are obtained from the experiment for part loading (PL), best efficiency point (BEP) and over loading (OL). These results are compared with proposed factors by American Hydraulic Institute (HIS) and Soviet :::union::: (USSR). The comparisons between the numerical and experimental results show good agreement.
Gh. Yari , M. D Jafari ,
Volume 17, Issue 4 (11-2006)
Abstract
Main result of this paper is to derive the exact analytical expressions of information and covariance matrix for multivariate Pareto, Burr and related distributions. These distributions arise as tractable parametric models in reliability, actuarial science, economics, finance and telecommunications. We showed that all the calculations can be obtained from one main moment multidimensional integral whose expression is obtained through some particular change of variables. Indeed, we consider that this calculus technique for that improper integral has its own importance.
A. Shidfar, Ali Zakeri,
Volume 17, Issue 4 (11-2006)
Abstract
This paper considers a linear one dimensional inverse heat conduction problem with non constant thermal diffusivity and two unknown terms in a heated bar with unit length. By using the WKB method, the heat flux at the end of boundary and initial temperature will be approximated, numerically. By choosing a suitable parameter in WKB method the ill-posedness of solution will be improved. Finally, a numerical example will be presented.
M.r. Alirezaee, S.a Mir-Hassani,
Volume 17, Issue 4 (11-2006)
Abstract
In the evaluation of non-efficient units by Data Envelopment Analysis (DEA) referenced Decision Making Units (DMU’s) have an important role. Unfortunately DMU’s with extra ordinary output can lead to a monopoly in a reference set, the fact called abnormality due to the outliers' data. In this paper, we introduce a DEA model for evaluating DMU’s under this circumstance. The layer model can result in a ranking for DMU’s and obtain an improving strategy leading to a better layer.
M. Nadjafikhah, H. R. Salimi Moghaddam ,
Volume 17, Issue 4 (11-2006)
Abstract
In this article, we generalize the concept of the Lie algebra of vector fields to the set of smooth sections of a T-bundle which is by definition a canonical generalization of the concept of a tangent bundle. We define a Lie bracket multiplication on this set so that it becomes a Lie algebra. In the particular case of tangent bundles this Lie algebra coincides with the Lie algebra of vector fields.
A. Aghajani , V. Roomi ,
Volume 18, Issue 1 (1-2007)
Abstract
Abstract: This paper investigates the problem of whether all trajectories of the system and cross the vertical isocline, which is very important for the existence of periodic solutions and oscillation theory. Sufficient conditions are given for all trajectories to cross the vertical isocline.
M.b Ghaemi , P. Spain ,
Volume 18, Issue 1 (1-2007)
Abstract
Abstract: In this paper, we exhibit new conditions for the sum of two commuting AC-operators to be again an AC-operator. In particular, this is satisfied on Hilbert space when one of them is a scalar-type spectral operator.
M. Nadjafikhah , A.r. Forough ,
Volume 18, Issue 1 (1-2007)
Abstract
Abstract : Let be a 2nd order ODE. By Cartan equivalence method, we will study the local equivalence problem under the transformations group of time-fixed coordinates. We are going to solve this problem by an applicable method which has been recognized by R. Gardner, and classify them.
K. Maleknejad , M. Rabbani ,
Volume 18, Issue 1 (1-2007)
Abstract
Abstract: There are some methods for solving integro-differential equations. In this work, we solve the general-order Feredholm integro-differential equations. The Petrov-Galerkin method by considering Chebyshev multiwavelet basis is used. By using the orthonormality property of basis elements in discretizing the equation, we can reduce an equation to a linear system with small dimension. For numerical examples, the solutions may be produced with good accuracy, by choosing suitable trial and test spaces in Petrov-Galerkin method.
A. Golbabai, B. Keramati , M. Arabshahi ,
Volume 18, Issue 1 (1-2007)
Abstract
Abstract: In this paper homotopy perturbation is applied to system of linear Fredholm integral equations of the first kind .For these systems, degenerate kernels are considered and in order to avoid successive integrations ,an easy matrix computation is derived for approximating the solution of the problem.
