Search results

Shannon’s entropy is usually defined separately for discrete, and for (absolutely) continuous random variables. However, many random variables encountered in practice have mixed (discrete‐continuous) distributions. A simple expression for the entropy of random variables with mixed (discrete‐continuous) distributions is derived in terms of the usual entropy definitions. In addition, the maximum entropy problem in the general setting of mixture distributions is discussed.

In real-world cases, it is common to encounter mixed discrete-continuous problems where some or all of the variables may take only discrete values. To solve these non-linear optimization problems, the use of finite element methods is very time-consuming. The purpose of this study is to investigate the efficiency of the proposed hybrid algorithms for the mixed discrete-continuous optimization and compare it with the performance of genetic algorithms (GAs).

In this paper, the enhanced multipoint approximation method (MAM) is used to reduce the original nonlinear optimization problem to a sequence of approximations. Then, the sequential quadratic programing technique is applied to find the continuous solution. Following that, the implementation of discrete capability into the MAM is developed to solve the mixed discrete-continuous optimization problems.

The efficiency and rate of convergence of the developed hybrid algorithms outperforming GA are examined by six detailed case studies in the ten-bar planar truss problem, and the superiority of the Hooke–Jeeves assisted MAM algorithm over the other two hybrid algorithms and GAs is concluded.

The authors propose three efficient hybrid algorithms, the rounding-off, the coordinate search and the Hooke–Jeeves search-assisted MAMs, to solve nonlinear mixed discrete-continuous optimization problems. Implementations include the development of new procedures for sampling discrete points, the modification of the trust region adaptation strategy and strategies for solving mix optimization problems. To improve the efficiency and effectiveness of metamodel construction, regressors f defined in this paper can have the form in common with the empirical formulation of the problems in many engineering subjects.

Reliability-based design optimizations (RBDOs) of engineering structures involve complex non-linear/non-differentiable performance functions, including both continuous and discrete variables. The gradient-based RBDO algorithms are less than satisfactory for these cases. The simulation-based approaches could also be computationally inefficient, especially when the double-loop strategy is used. This paper aims to present a pseudo-double loop flexible RBDO, which is efficient for solving problems, including both discrete/continuous variables.

The method is based on the hybrid improved binary bat algorithm (BBA) and weighed simulation method (WSM). According to this method, each BBA’s movement generates proper candidate solutions, and subsequently, WSM evaluates the reliability levels for design candidates to conduct swarm in a low-cost safe-region.

The accuracy of the proposed enhanced BBA and also the hybrid WSM-BBA are examined for ten benchmark deterministic optimizations and also four RBDO problems of truss structures, respectively. The solved examples reveal computational efficiency and superiority of the method to conventional RBDO approaches for solving complex problems including discrete variables.

Unlike other RBDO approaches, the proposed method is such organized that only one simulation run suffices during the optimization process. The flexibility future of the proposed RBDO framework enables a designer to present multi-level design solutions for different arrangements of the problem by using the results of the only one simulation for WSM, which is very helpful to decrease computational burden of the RBDO. In addition, a new suitable transfer function that enhanced convergence rate and search ability of the original BBA is introduced.

This paper first reviews factor reconstructability analysis (RA) modelling completely by data. Gives a description of levelled variable factor reconstruction analysis model generation process and its further extension to forecasting, evaluation and optimisation. It introduces RA modelling with multi‐variety information and knowledge. From generation of mixed variable RA models to generation of models with both data and knowledge, the paper gives a related table and a figure on “Information flow of reconstructability analysis with multi‐variety information and knowledge” which included database, RA relational knowledge base, and interfaces for input of experts' knowledge. Finally, it gives some examples and prospects.

The purpose of this paper is to attempt to outline the standard profile of the typical wine consumer, by identifying some relevant features that can influence his/her purchasing choices. Therefore, the purpose of the research is to identify the pre-eminent attributes for wine consumers and the different levels of importance that consumers ascribe to the attributes identified at the time of purchase.

In order to collect the necessary data, an ad hoc questionnaire was utilized. The questionnaire, which was anonymous, was directly distributed with the face-to-face method. In total, 1,500 copies of the questionnaire had been prepared. The data collected were processed through the use of the binary logistic regression model and the ordinal logistic regression model. The first binary logistic regression model allows to evaluate the dependence of the dichotomous variable on some potential predictors. The ordinal logistic regression model, known in literature as a cumulative model of proportional quotas, is generally appropriate for situations in which the ordinal response variable has discrete categories.

The results returned by the elaboration of the binary logistic regression model refer to the influence of the variables sex, age, educational status and income on the “wine consumption” result, which is a dichotomous variable. The only variables found to be statistically significant are gender and educational status. The most significant variables that emerged from the implementation of the ordinary logistic regression model are gender, brand, choice based on price, place of production, harvest and certification. The analysis carried out has shown that with reference to wine as a product, it is essential to focus on several attributes, among which there are of course quality and brand.

Although field experiments are extremely useful for testing behavioral hypotheses, they are often limited by a small sample. Future research in this area might focus on the knowledge level of sustainable wine of the consumer. In relation to the knowledge of the characteristics of the wine, it is possible to estimate the willingness to pay a surplus for a wine produced with sustainable methods by the consumer and the possible level of price premium.

The originality of the research lies mainly in a deeper knowledge of wine consumption trends. This information is useful to better define the wine market and to allow, especially to small businesses, to establish effective marketing strategies in relation to the real preferences of consumers and the decision-making process of choice put in place by them. In order to achieve this, the influence of all the variables on the “satisfaction of wine consumption” result was evaluated. The strength of this paper is the use of an adequate statistical approach based on the use of models, typical of inferential statistics, to reach conclusions that can be extended to the entire population of wine growers.

The purpose of this study is to develop and test a new customer satisfaction index model for Turkish mobile phone sector (TMPS).

Based on relevant literature and theoretical considerations on customer satisfaction, a new measurement model was developed. A survey based on the proposed model was conducted to 700 mobile phone users in Istanbul. Partial least squares method was employed to estimate the proposed structural equation model (SEM).

The general applicability of a SEM depends on the reliability and validity of the modeling results. The proposed satisfaction model exhibits strong explanatory power with its satisfactory reliability and validity results.

The proposed model was tested for the TMPS. It should ideally be tested periodically for different sectors with more data, and the index results should be compared.

The results of this study provide very important information for the managers in formulating competitive marketing strategies. The results show the critical points where the limited resources of the firms should be allocated to improve satisfaction and loyalty. Independent and uniform measurement characteristics of the studied model provide a useful tool for tracking performance and systematic benchmarking over time. It also provides information about the weaknesses and strengths of the company from the eyes of its customers.

This study is an attempt to develop and implement a satisfaction model for the TMPS. The proposed model consists of well‐established theories and approaches in customer behavior.

The paper describes the use of hedonic analysis to examine the impact of the South Yorkshire Supertram on house prices in Sheffield. The approach was distinguished by the use of asking prices rather than transaction prices, the use of dummy variables to capture neighbourhood quality effects and the use of a GIS to calculate continuous distance variables. Compared with similar previous studies the equations performed well and identified, for the first time in a British context, a small, discrete transport induced price effect. Supertram initially depressed the prices of nearby houses but prices show signs of recovery. Further research is needed to examine the longer term impact of Supertram on the housing market.

This paper aims to focus on the trade-off between losses and converter cost.

The continual development of power electronic converters, for a wide range of applications such as renewable energy systems (interfacing photovoltaic panels via power converters), is characterized by the requirements for higher efficiency and lower production costs. To achieve such challenging objectives, a computer-aided design optimization based on genetic algorithms is developed in Matlab environment. The elitist non-dominated sorting genetic algorithm is used to perform search and optimization, whereas averaged models are used to estimate power losses in different semiconductors devices. The design problem requires minimizing the losses and cost of the boost converter under electrical constraints. The optimization variables are, as for them, the switching frequency, the boost inductor, the DC capacitor and the types of semiconductor devices (IGBT and MOSFET). It should be pointed out that boost topology is considered in this paper but the proposed methodology is easily applicable to other topologies.

The results show that such design methodology for DC-DC converters presents several advantages. In particular, it proposes to the designer a set of solutions – as an alternative of a single one – so that the authors can choose a posteriori the adequate solution for the application under consideration. This then allows the possibility of finding the best design among all the available choices. Furthermore, the design values for the selected solution were obtainable components.

The authors focus on the general aspect of the discrete optimization approach proposed here. It can also be used by power electronics designers with the help of additional constraints in accordance with their specific applications. Furthermore, the use of such non-ideal average models with the multi-objective optimization is the original contribution of the paper and it has not been suggested so far.

This study aims to enhance the simultaneous utilization of measure in product design by mapping out the possible and potential uses of a measure for both academicians and practitioners.

To map out a way for the simultaneous utilization of measure, the authors assessed and portrayed the diverse facets of a four-factor measure for the development of mobile devices by adopting pluralistic techniques through a series of studies and three different study samples.

This study provided a solution for enhancing the usability of measure in product management, showing that a measure can be developed using a pluralistic methodology so that the results can be incorporated into the practitioners’ design activities that occur and when the gap between theory and practice is a knowledge production problem.

The main positioning of this study involves the science-design interface (Simon, 1992) to bridge the important gap between theory and practice by showcasing a measure development for product design as a strategy of intellectual arbitrage (Van De Ven and Johnson, 2006). Relying on the design scientific approach, the authors focused this study on a prescriptive procedure rather than a more rigorous methodological procedure.

The authors provided product managers with a systematic and synergistic approach to developing a measure and recommended several usages of the developed measure to enhance its simultaneous utilization between academics and practitioners.

Emphasizing pluralistic methodology in the measure development, the authors recommended the concept of intra-examination. The first-order intra-examination, utilizing Bayesian Networks, makes available the thick descriptions of the measure and supports reasoning under uncertainty. The second-order intra-examination examined nomological networks regarding the pragmatic relationships between the four factors that comprise the measure and other important constructs.

In self‐directed retirement plans, farmers are responsible for selecting the types of risky investments toward which the funds in their retirement plan are allocated. Furthermore, farmers do not necessarily purchase sufficient annuities with their savings upon retirement. There is little empirical evidence on the level of income sought or obtained. The purpose of this study is to analyze the long‐term investment behavior with respect to retirement planning.

Two types of data were merged for the analysis: data from the Farm Accountancy Data Network (FADN) cross‐sectional dataset, and subjective data collected by a questionnaire survey. A response rate of 39 percent was achieved enabling analysis of 440 farm records. By means of regression analysis, the impact of subjective elements, for example level of income sought, as well as farm structure and financial farm characteristics on income obtained at the time of retirement were revealed.

By decomposing the underlying decision alternatives, it was shown that the long‐term investment behavior differed substantially among farmers, but the alternative decisions made were hardly affected by structural and objective parameters. The current study reveals the dilemma faced by any farmer who has the option to invest in his own business. Off‐farm retirement investments simply provide an alternative destination for investible funds and it is a rational decision to invest these funds in their own business, thus making the farm itself their retirement “nest‐egg”. However, a discrepancy between the level of income sought and obtained was found.

There is a need to study how farmers can be encouraged to use existing options for obtaining a more comprehensive retirement plan.

In the investigated case, farmers are entitled like all residents to receive retirement benefits provided by the state, referred to as state pension. The use of three alternative retirement plans complementing the state‐sponsored retirement benefits is investigated. Perceptions about whether or not the state pension was sufficient to rely on as the sole source of income did not affect participation in a retirement plan. This stresses the importance that the contributions made and assets reserved should be regularly evaluated and reviewed (via, for example, extension or internet tools) to ensure that the available capital will meet the future income sought.

It is a challenge to identify the adequacy to attain retirement readiness by self‐directed investment plans. The strategic choices to be made are complex, while the outcome is risky. In the current study, the long‐term investment behavior with respect to retirement planning is analyzed by decomposing the underlying decision alternatives.