An adaptive neuro‐fuzzy system for stock portfolio analysis

We propose an adaptive neuro‐fuzzy inference system (ANFIS) for stock portfolio return prediction. Previous work has shown that portfolio optimization can be improved by using predicted stock earnings rather than historical earnings. We show that predicted portfolio returns can be improved by using ANFIS and taking as input a variety of technical and fundamental attributes about various indices of the stock market. To generate membership functions, we use a robust noise rejection‐clustering algorithm. The neuro‐fuzzy model is tested on portfolios constituted from the Tehran Stock Exchange. In our experiments, the proposed method performs better in predicting the portfolio return than the classical Markowitz portfolio optimization method, a multiple regression, a neural network, and the Sugeno–Yasukawa method. © 2010 Wiley Periodicals, Inc.     

Multi-criteria decision making for assembly line balancing

Assembly line balancing often has significant impact on performance of manufacturing systems, and is usually a multiple-objective problem. Neither an algorithmic nor a procedural assembly line balancing methodology is usually effective in solving these problems. This article proposes a data envelopment analysis (DEA) approach to solve an assembly line balancing problem. A computer-aided assembly line balancing tool as Flexible Line Balancing software is used to generate a considerable number of solutions alternatives as well as to generate quantitative decision-making unit outputs. The quantitative performance measures were considered in this article. Then DEA was used to solve the multiple-objective assembly line balancing problem. An illustrative example shows the effectiveness of the proposed methodology.     

A memetic algorithm for minimizing the total weighted completion time on a single machine under step-deterioration

In this paper, we consider minimizing total weighted completion time criteria on a single machine. Jobs processing times are step function of its starting time and all jobs have a common due date. First, we present some new lemmas and dominance properties for this NP-hard problem, and then a memetic algorithm using these properties is developed. We compare the solutions of the memetic algorithm with optimal solutions obtained from complete enumeration. The results show that the average percentage error of the proposed algorithm from optimal solutions is about 2% and as the variance of processing time increase, the percentage errors decrease.     

Cyclic scheduling of a robotic flexible cell with load lock and swap

In this paper, we study the problem of robotic cell scheduling with m machines with flexibility, load lock and swap assumptions. The robotic cell repetitively produces parts of identical types. We determine the cycle time of all 1-unit cycles in this type of robotic cell and present two new lower bounds for robot move cycles with load lock and swap, either there is flexibility or inflexibility. We also provide a new robot move cycle and prove that it dominates all classical robot move cycles considered in the existing literature of m-machine robotic cells.     

A latency-aware task scheduling algorithm for allocating virtual machines in a cost-effective and time-sensitive fog-cloud architecture

The Journal of Supercomputing - Recently, with the expansion of communications and generated data, the need for processing this high volume of data in minimum time and maximum speed has increased....     

Solving a bi-objective cell formation problem with stochastic production quantities by a two-phase fuzzy linear programming approach

We propose a bi-objective cell formation problem with demand of products expressed in a number of probabilistic scenarios. To deal with the uncertain demand of products, a framework of two-stage stochastic programming model is presented. The proposed model considers minimizing the sum of the miscellaneous costs (machine constant cost, expected machine variable cost, cell fixed-charge cost, and expected intercell movement cost) and expected total cell loading variation. Because of conflicting objectives, we develop a two-phase fuzzy linear programming approach for solving bi-objective cell formation problem. To show the effectiveness of the proposed approach, numerical examples are solved and the results are compared with the two existing approaches in the literature. The computational results show that the proposed fuzzy method achieves lower objective functions as well as higher satisfaction degrees.     

Flow shop scheduling with two batch processing machines and nonidentical job sizes

A batch processing machine can process several jobs simultaneously. In this research, we consider the problem of a two-stage flow shop with two batch processing machines to minimize the makespan. We assume that the processing time of a batch is the longest processing time among all the jobs in that batch and the sizes of the jobs are nonidentical. There is a limitation on batch sizes and the sum of job sizes in a batch must be less than or equal to the machine capacity. Since this problem is strongly nondeterministic polynomial time hard, we propose two heuristic algorithms. The first one is knowledge-based and the other is based on the batch first fit heuristic proposed previously. To further enhance the solution quality, two different simulated annealing (SA) algorithms based on the two constructive heuristics is also developed. Since heuristic methods for this problem has not been proposed previously, a lower bound is developed for evaluating the performance of the proposed methods. Several test problems have been solved by SAs and lower bound method and the results are compared. Computational studies show that both algorithms provide good results but the first SA (ARSA) algorithm considerably outperforms the second one (FLSA). In addition, the results of ARSA algorithm, optimal solutions, and lower bounds are compared for several small problems. The comparisons show that except for one instance, the ARSA could find the optimal solutions and the proposed lower bound provides small gaps comparing with the optimal solutions.     

A variable neighborhood binary particle swarm algorithm for cell layout problem

In this paper, a new mathematical model is proposed for inter- and intra-cell layout problem in cellular manufacturing system. A binary particle swarm optimization algorithm with a new heuristic approach for satisfying the constraints of model is implemented to solve the proposed model. Also, a variable neighborhood search is applied for finding better local optimal solutions. Some sensitivity analyses are carried out to find the best values of PSO parameters. To prove the efficiency of the proposed algorithm, various numerical examples in small, medium, and large sizes in both perfect geometric shapes and random placements are generated and solved.     

An integrated weighted fuzzy multi-objective model for supplier selection and order scheduling in a supply chain

This paper presents a new weighted fuzzy multi-objective model to integrated supplier selection, order quantity allocation and customer order scheduling problem to prepare a responsive and order-oriented supply chain in a make-to-order manufacturing system. Total cost and quality of purchased parts as well as the reliability of on-time delivery of customer orders are regarded as the objectives of the model. On the other hand, flexible suppliers can contribute to the responsiveness and flexibility of entire supply chain in the face of uncertain customer orders. Therefore, a mathematical measure is developed for evaluating the volume flexibility of suppliers and is considered as the other objective of the model. Furthermore, by considering the effect of interdependencies between the selection criteria and to handle inconsistent and uncertain judgments, a fuzzy analytic network process method is used to identify top suppliers and consider as the last objective. In order to optimise these objectives, the decision-maker needs to decide from which supplier to purchase parts needed to assemble the customer orders, how to allocate the demand for parts between the selected suppliers, and how to schedule the customer orders for assembled products over the planning time horizon. Numerical examples are presented and computational analysis is reported.     

A multi-objective particle swarm optimisation algorithm for unequal sized dynamic facility layout problem with pickup/drop-off locations

This paper deals with a multi-objective unequal sized dynamic facility layout problem (DFLP) with pickup/drop-off locations. First, a mathematical model to obtain optimal solutions for small size instances of the problem is developed. Then, a multi-objective particle swarm optimisation (MOPSO) algorithm is implemented to find near optimal solutions. Two new heuristics to prevent overlapping of the departments and to reduce ‘unused gaps’ between the departments are introduced. The performance of the MOPSO is examined using some sets of available test problems in the literature and various random test problems in small, medium, and large sizes. The percentage of improvements on the initial solutions is calculated for small, medium and large size instances. Also, the generation metric and the space metric for non-dominated solutions are examined. These experiments show the good performance of the developed MOPSO and sensitivity analysis show the robustness of the obtained solutions.