Papers by Michael Mutingi
In a fuzzy environment where the decision making involves multiple criteria, fuzzy multi-criteria... more In a fuzzy environment where the decision making involves multiple criteria, fuzzy multi-criteria decision making approaches are a viable option. The nurse re-rostering problem is a typical complex problem situation, where scheduling decisions should consider fuzzy human preferences, such as nurse preferences, decision maker’s choices, and patient expectations. For effective nurse schedules, fuzzy theoretic evaluation approaches have to be used to incorporate the fuzzy human preferences and choices. The present study seeks to develop a fuzzy multi-criteria simulated evolution approach for the nurse re-rostering problem. Experimental results show that the fuzzy multi-criteria approach has a potential to solve large scale problems within reasonable computation times. Keywords—fuzzy simulated evolution; fuzzy theory; multiple criteria; nurse re-rostering
international journal of industrial engineering computations, 2013
Integrated cell formation and layout (CFLP) is an extended application of the group technology ph... more Integrated cell formation and layout (CFLP) is an extended application of the group technology philosophy in which machine cells and cell layout are addressed simultaneously. The aim of this technological innovation is to improve both productivity and flexibility in modern manufacturing industry. However, due to its combinatorial complexity, the cell formation and layout problem is best solved by heuristic and metaheuristic approaches. As CFLP is prevalent in manufacturing industry, developing robust and efficient solution methods for the problem is imperative. This study seeks to develop a fuzzy simulated evolution algorithm (FSEA) that integrates fuzzy-set theoretic concepts and the philosophy of constructive perturbation and evolution. Deriving from the classical simulated evolution algorithm, the search efficiency of the major phases of the algorithm is enhanced, including initialization, evaluation, selection and reconstruction. Illustrative computational experiments based on existing problem instances from the literature demonstrate the utility and the strength of the FSEA algorithm developed in this study. It is anticipated in this study that the application of the algorithm can be extended to other complex combinatorial problems in industry.
Manufacturing System, 2012
Cellular Manufacturing System (CMS), an application of group technology philosophy, is a recent t... more Cellular Manufacturing System (CMS), an application of group technology philosophy, is a recent technological innovation that can be used to improve both productivity and flexibility in modern manufacturing environments (Signh, 93;. In practice, the essence of CMS is to decompose a manufacturing system into manageable autonomous subsystems (called manufacturing cells) so as to enhance shop-floor control, material handling, tooling, and scheduling. The decomposition process involves identification of part families with similar processes or design features and machine cells so that each family can possibly be processed in a single cell. In addition to this, machine layout within each cell is considered essential in order to improve efficiency and effectiveness of the overall production system. Consequently, setup times, work-in-process inventories, and throughput times are reduced significantly. The overall process of designing CMS involves the following four generic phases: 1. Cell formation: involves grouping of machines which can operate on a product family with little or no inter-cell movement of the products. 2. Group layout: includes layout of machines within each cell (intra-cell layout), and layout of cells with respect to one another (inter-cell layout). 3. Group scheduling: involves scheduling of parts for production 4. Resource allocation: assignment of tools, manpower, materials, and other resources In general, the design of CMS includes three critical decisions, namely, cell formation, group layout, and scheduling. In the most ideal case, these criteria should be addressed simultaneously so as to obtain the best possible results . However, due to the complex nature of the decision problem coupled with the limitations of conventional approaches, most of the cell formation studies have focused on these decisions independently or sequentially . Most cell formation approaches proposed in literature use flow patterns of parts (sequence data) for cell design issues only. On the other hand, the layout designers did not consider the cell formation problem. Due to the fact that the sequential approach addresses the cell formation and the cell layout problem in a disjointed fashion, the quality of the final www.intechopen.com Manufacturing System 206 solution is often compromised. In this chapter, an integrated approach to cell formation and layout design is presented, based on available sequence data. The GGA-based approach utilizes sequence data to identify machine cells as well as machine layout within each cell. In this view, the major objectives for this chapter are as follows:
Decision making in home care service is complex due to the need to satisfice multi-objective goal... more Decision making in home care service is complex due to the need to satisfice multi-objective goals such as maximizing customer service quality, minimizing service cost, and maximizing employee satisfaction. With the increasing world-wide need for efficient and effective home healthcare, the increasing elderly population, and the increasing pressure from governments and other stakeholders in various societies, the development of effective novel approaches for home care decisions is imperative. In this paper, we present a multi-agent architecture that facilitates decision making characterised with multiple objectives. The approach integrates the capabilities of a multi-agent system and Web services so as to facilitate effective decisions for home healthcare services. The aim is to provide a multi-agent system based on genetic algorithm, where decisions are based on intelligent agents that provide intelligent alternative decisions in a multiple-objective environment.
As environmental issues are continually and rapidly emerging as one of the most crucial topics in... more As environmental issues are continually and rapidly emerging as one of the most crucial topics in strategic manufacturing decision making, the formulation of "green" performance management systems is very important. This research seeks to introduce and explore green performance measurement frameworks that exist in various real-world case studies that are found in literature. The study yielded a set of four taxonomic performance measurement systems that are applicable in specific contexts of manufacturing supply chain strategies. Moreover, specific green performance metrics are provided in respect of the identified green manufacturing strategies. Implications of the application of each performance management system on existing manufacturing policies are evaluated, giving practical managerial insights. The study forms an essential framework for the decision maker to rapidly develop a suitable performance system in a green manufacturing environment, within a reasonable time frame.
Grouping problems are hard combinatorial problems concerned with partitioning or grouping items i... more Grouping problems are hard combinatorial problems concerned with partitioning or grouping items into categories, based on a given set of decision criteria. Complex industrial problems such as home healthcare scheduling, vehicle routing problem, task assignment, and team formation fall into this class of problems. These grouping problems are characterized with complex features, posing several computational challenges to decision makers in various disciplines. This study is concerned with investigation of common challenges inherent in grouping problems across industry disciplines. Based on recent case studies in the literature, the paper investigates common challenges and complicating features in real-world grouping problems. These features are classified into model abstraction, presence of multiple constraints, fuzzy management goals, and computational complexity. Further analysis of the case examples revealed four types of the complicating features. Insights into the general grouping problem and the inadequacies of solution methods are presented. Suitable approaches are then suggested. Thus, the study recommends solution approaches that make use of multi-criteria, flexible, interactive approaches that incorporate fuzzy set theory, fuzzy logic, multi-criteria decision, and expert systems.
In the presence of imprecise management targets, staff preferences, and patients’ expectations, t... more In the presence of imprecise management targets, staff preferences, and patients’ expectations, the healthcare staff scheduling problem becomes complicated. The goals, preferences, and client expectations, being humanistic, are often imprecise and always evolving over time. We present a fuzzy genetic algorithm (FGA) approach for addressing healthcare staff scheduling problems in fuzzy environments. The proposed FGA-based approach can handle multiple conflicting objectives and constraints. To improve the algorithm, fuzzy set theory is used for fitness evaluations of alternative candidate schedules by modeling the fitness of each alternative solution using fuzzy membership functions. Furthermore, the algorithm is designed to incorporate the decision maker’s choices and preferences, in addition to staff preferences. Rather than prescribing a sing solution to the decision maker, the approach provides a population of alternative solutions from which the decision maker can choose the most...
Decision makers are often faced with the problem of grouping inventory into categories for cost-e... more Decision makers are often faced with the problem of grouping inventory into categories for cost-effective and efficient management and control of inventory. The classical ABC inventory analysis has been applied widely in industry. However, the approach is associated with practical limitations: the desired service level and budget allocation constraints are not considered simultaneously, there is no guarantee for optimal solutions, and qualitative decision criteria are not modelled explicitly. It is desirable to develop models that can capture quantitative and qualitative criteria, from a multi-criteria optimization view point. In light of these limitations, the purpose of this research is to model the inventory grouping problem using grouping genetic algorithms approach. We first assess the grouping structure of the inventory classification problem, and then model the grouping problem from the grouping genetic algorithm perspective. Further research prospects and applications are ev...
The homecare worker scheduling problem is inundated with fuzzy and often conflicting goals, const... more The homecare worker scheduling problem is inundated with fuzzy and often conflicting goals, constraints and preferences. In such an uncertain environment, the decision maker needs to find a satisficing solution approach that takes into account the humanistic judgments and the conflicting nature of the goals. This paper proposes a fuzzy satisficing approach, based on fuzzy set theory, for addressing the homecare worker scheduling problem. The aim is to provide a satisficing approach that considers the management goals, the worker preferences, as well as the service quality as specified by the healthcare clients. By addressing the desired goals or preferences of the three players, (i) the management, (ii) the worker, and (iii) the client, the approach provides a more realistic, flexible and adaptable method for real-world healthcare staff scheduling in an uncertain environment.
ď€ Abstract—The nurse scheduling problem (NSP) has a great impact on the quality and efficiency of... more ď€ Abstract—The nurse scheduling problem (NSP) has a great impact on the quality and efficiency of health care operations. Healthcare Operations Analysts have to assign daily shifts to nurses over the planning horizon, so that operations costs are minimized, health care quality is improved, and the nursing staff is satisfied. Due to conflicting objectives and a myriad of restrictions imposed by labor laws, company requirements, and other legislative laws, the NSP is a hard problem. In this paper we present a particle swarm optimization-based algorithm that relies on a heuristic mechanism that incorporates hard constraints to improve the computational efficiency of the algorithm. Further, we incorporate soft constraints into objective function evaluation to guide the algorithm. Results from illustrative examples show that the algorithm is effective and efficient, even over large scale problems.
A genetic algorithm approach for multiple criteria November 14th, 2010 This paper presents a gene... more A genetic algorithm approach for multiple criteria November 14th, 2010 This paper presents a genetic algorithm based model for facility layout Layout of departments consisting of finite elements is modelled in gene structures Better and better solutions that satisfy multiple objectives are produced by employing genetic operations to these genes Better quality layouts are obtained by this method on the test problems available in the literature
2015 International Conference on Industrial Engineering and Operations Management (IEOM), 2015
Effective engineering change management (ECM) procedures are very important over the whole life c... more Effective engineering change management (ECM) procedures are very important over the whole life cycle of every engineering change (EC), from EC proposal to implementation and documentation. However, the success of an EC procedure depends on the amount of focus on the critical areas of the EC project. The purpose of this research to develop an alternative ECM framework based on critical success factors of ECM. The study follows through three steps: (i) identify the common focus areas of ECM, (ii) identify, from past empirical studies, the critical success factors for ECM, and (iii) develop a proposed framework that incorporates the identified critical success factors for ECM. The proposed ECM framework provides practitioners with a change management process that incorporate ECM critical success factors, to guide in implementation of ECM projects.. This is anticipated to increase the chance of success for the ECM projects.
2015 International Conference on Industrial Engineering and Operations Management (IEOM), 2015
Motivated by the biological metamorphosis process and the need to solve multi-objective optimizat... more Motivated by the biological metamorphosis process and the need to solve multi-objective optimization problems with conflicting and fuzzy goals and constraints, this paper proposes a simulated metamorphosis algorithm, based on the concepts of biological evolution in insects, such as moths, butterflies, and beetles. By mimicking the hormone controlled evolution process the algorithm works on a single candidate solution, going through initialization, iterative growth loop, and finally maturation loop. The method is a practical way to optimizing multi-objective problems with fuzzy conflicting goals and constraints. The approach is applied to the nurse scheduling problem. Equipped with the facility to incorporate the user's choices and wishes, the algorithm offers an interactive approach that can accommodate the decision maker's expert intuition and experience, which is otherwise impossible with other optimization algorithms. By using hormonal guidance and unique operators, the algorithm works on a single candidate solution, and efficiently evolves it to a near-optimal solution. Computational experiments show that the algorithm is competitive.
The design of appropriate green supply chains in the manufacturing sector is a crucial task. The ... more The design of appropriate green supply chains in the manufacturing sector is a crucial task. The present paper seeks to (i) identify suitable performance measures for green supply chains and to (ii) develop a dynamic simulation model to assist supply chain decision-makers in developing appropriate policies and strategies in green supply chain management. Based on the principles of the system dynamics methodology, causal linkages between internal and external factors affecting the development of green strategies are investigated. Green concepts are used to develop crucial environmental and eco-efficiency performance measures in regards to strategic green supply management. Results from what-if analysis indicate that proper implementation of green strategies produces significant improvements for environmental, economic/financial and operational performance. Further numerical experiments demonstrate that the model can provide sound managerial insights.
Benchmarking: An International Journal
Purpose Small- and medium-sized enterprises (SMEs) have now become an important part of economy f... more Purpose Small- and medium-sized enterprises (SMEs) have now become an important part of economy for not only developed nations but also for emerging economies. Irrespective of the benefits that can be derived, SMEs in emerging economies still lack the will to implement quality management (QM) practices. Using a comparative study, the purpose of this paper is to understand the status of QM practices in SMEs of emerging economies. Design/methodology/approach A survey-based approach was adopted to understand the established QM practices in the SMEs. A survey instrument was designed by reviewing the literature on QM initiatives in SMEs. A sample of 270 SMEs across Southern India and 189 SMEs in Namibia was selected through stratified random sampling technique. Findings The overall response rate was 19.52 percent for India and 26.46 percent for Namibia, respectively. There were similarities and differences in responses from SMEs in both countries. Similarities are in terms of limited imp...
An integrated computer decision making system is developed to help in product scheduling for a mu... more An integrated computer decision making system is developed to help in product scheduling for a multi-product colour system. It is an attractive option that will enhance flexibility of supply in fast-changing areas, fashion design, and consumer tastes. Problems in the production system will be solved by designed models. The transformation of the local manufacturing industry towards CIM systems has already begun to take root. This paper examines the potential benefits to TN Textiles and how it can exploit CIM technology. CIM simultaneously facilitates production of high product variety at optimum costs as TN must work with increasingly scarce resources.
operation, yet plant design optimisation decisions are based on past experience and intuition rat... more operation, yet plant design optimisation decisions are based on past experience and intuition rather than on scientific analysis. Genetic algorithms as a tool for circuit analysis in plant design and optimisation was considered. The multi-objective evolutionary algorithm initialises the plant design and optimisation based on experimental results, which are used to formulate and determine the objective function values. A simulation was conducted to assess the performance of candidate solutions. The two optima are then traded-off using cost objective, which is sought to be minimized. Once an optimum was selected, the circuit mass balance and equipment design was performed, bringing the theory of network design and genetic algorithms into unison. Results of the study provide financial benefits, optimal parameter settings for the comminution equipment and ultimately better plant performance.
Uploads
Papers by Michael Mutingi