Michael Mutingi

A fuzzy-based particle swarm optimisation approach for task assignment in home healthcare

Home healthcare (HHC) organisations provide coordinated healthcare services to patients at their homes. Motivated by the ever-increasing need for home-based care, the assignment of tasks to available healthcare staff is a common and complex problem in homecare organisations. Designing high quality task schedules is critical for improving worker morale, job satisfaction, service efficiency, service quality, and competitiveness over the long term. The desire is to provide high quality task assignment schedules that satisfy the patient, the care worker, and the management. This translates to maximising schedule fairness in terms of workload assignments, avoiding task time window violation, and meeting management goals as much as possible. However, in practice, these desires are often subjective as they involve imprecise human perceptions. This paper develops a fuzzy multi-criteria particle swarm optimisation (FPSO) approach for task assignment in a home healthcare setting in a fuzzy environment. The proposed approach uses a fuzzy evaluation method from a multi-criteria point of view. Results from illustrative computational experiments show that the approach is promising.

Dynamic Simulation of Healthcare Manpower Systems: A Market-based Perspective

Health manpower supply decisions are highly critical in every growing society. In times of growing healthcare needs, the dynamics of the healthcare job market creates challenges for many training institutions when formulating policy structures for training and supply of healthcare professionals. Dynamic interactions between variables, time lags, and feedback effects need a cautious consideration in healthcare manpower planning. Poor policy structures have negative impacts, such as overor under-investment in training capacity build-up which ultimately leads to unwanted imbalances in the labour market. A cautious approach is required when selecting the right information feedbacks that can assist in designing manpower policy structures. In this paper, we develop a system dynamics approach that utilizes a select set of indices which reflect trends in the labour market. The model demonstrates the dynamic influence between college recruitment, training, supply and demand in a causal loop form. Dynamic what-if analyses further expose the effects of modifying key policy parameters in a typical healthcare manpower system. Thus, strategic policies for manpower supply decisions can be developed and evaluated. The system dynamics model is a potential decision support tool to assist policy makers in formulating healthcare manpower decisions.

System dynamics of renewable energy technology adoption

The adoption of renewable energy technologies (RET) has been facing a number of barriers and constraints due to dynamic interaction of adoption related factors. This paper simulates from a systems dynamics point of view the dynamic behavior of the RET adoption process. Complex dynamic interactions between technology adopters, policy makers and policies are captured based on systems thinking. Based on a set of input policy parameters and variables, the behavior of RET adoption is investigated. Sensitivity experiments and further “what-if” experiments are conducted in this study. Useful managerial insights are drawn from the simulation results, relevant for policy makers concerned with renewable energy technologies.

Home Healthcare Staff Scheduling: A Taxonomic State-of-the-Art Review

Home healthcare staff scheduling has become increasingly important as healthcare business becomes more service oriented and cost conscious. With the ever increasing home care needs, healthcare staff shortages, increasing world-wide pressure for improved health care, and the rising healthcare costs, developing appropriate models for optimizing home healthcare operations is imperative. Healthcare service providers require effective decision support tools to meet customer expectations in a cost effective manner, satisfy staff requirements such as flexible work shifts, shift equity, individual preferences, part-time work, and meet management goals. Various methods have been developed to solve homecare staff scheduling problems. In this paper, we make a state-of-the-art review of the models and algorithms that have been reported in the literature. In addition, we analyze the existing empirical studies, identifying the research trends and voids in home healthcare staff scheduling. Finally, we identify essential prospective research avenues.

Healthcare Staff Scheduling : Emerging Fuzzy Optimization Approaches

By reading, you can know the knowledge and things more, not only about what you get from people to people. Book will be more trusted. As this healthcare staff scheduling emerging fuzzy optimization approaches, it will really give you the good idea to be successful. It is not only for you to be success in certain life you can be successful in everything. The success can be started by knowing the basic knowledge and do actions.

Reliability Optimization for the Complex Bridge System: Fuzzy Multi-criteria Genetic Algorithm

System reliability optimization often involves multiple fuzzy conflicting objectives, for instance, reducing system cost and reliability improvement. This paper presents a system reliability optimization problem for the complex bridge system. First, the problem is formulated as a fuzzy multi-criteria nonlinear program. Second, we propose a fuzzy multi-criteria genetic algorithm approach (FMGA) to solve the problem. Fuzzy evaluation techniques are used to handle fuzzy goals and constraints, resulting in a flexible and adaptable approach that provides high-quality solutions within reasonable computation times. Using fuzzy theory concepts, the preferences of the decision maker on the cost and reliability objectives are judiciously incorporated. Third, computational experiments results are presented based on benchmark problems in the literature. The computational results obtained show that the proposed method is encouraging.

A fuzzy simulated evolution algorithm for multi-objective homecare worker scheduling

Due to ever-growing need for satisfactory homecare services in every society, development of efficient staff scheduling methods is crucial. Homecare services are aimed at providing medical, paramedical and social aid to patients at their own homes, leading to reduced hospitalization and healthcare operations costs in the medium to long term. However, the homecare staff scheduling problem is a complex one as it combines the hard vehicle routing and the staff assignment problems. This research presents a fuzzy simulated evolution algorithm, based on fuzzy evaluation, to address staff planning and scheduling in a home care environment. The objective is to decide (i) which patients to assign to each staff, and (ii) the best route or trip for each worker to execute the healthcare tasks, to satisfy the time window preferences of the patients. Results on illustrative experiments presented show that the approach is promising.

Adoption of Renewable Energy Technologies: A Fuzzy System Dynamics Perspective

Renewable energy technologies (RETs) are essential for low-carbon energy, environment, and economic systems. The adoption of RETs has been facing a number of barriers and constraints due to the dynamic interaction between potential technology adopters, adopters, imitators, inhibitors, and the technology policies in place. However, the major challenge in modeling RET adoption is the existence of linguistic or fuzzy variables which often confront the decision maker. Linguistic and time-dependent variables lead to uncertainties in the impact of decisions taken. In this connection, the aim of this chapter is to develop a fuzzy system dynamics approach to improve the usefulness of energy policy system models characterized with linguistic variables. Complex dynamic interactions between technology adopters, imitators, inhibitors, policy makers, and energy policies are captured based on systems thinking. Based on a set of input policy parameters and variables, the behavior of RET adoption is investigated. Sensitivity experiments and further “what-if” experiments are conducted in this study. Useful managerial insights are drawn from the simulation results, relevant for policy makers concerned with RETs. Fuzzy logic and system dynamics methodologies are integrated from a systems perspective to model typical RET scenarios. It is anticipated that the methodology will be vital for real-world energy policy design and assessment in the twenty-first century.

Optimizing Order Batching in Order Picking Systems: Hybrid Grouping Genetic Algorithm

Optimizing order batching is an essential decision problem for efficient manual order picking systems in distribution warehouses. It involves traversing through a distribution warehouse to collect items so as to satisfy customer orders. For efficient operation of manual order picking systems, order batching should be optimized. Customer orders should be grouped into picking orders of limited sizes, while ensuring that the total distance traversed by order pickers is minimized. To solve the problem, a hybrid grouping genetic algorithm (HGGA), incorporating unique grouping operators, constructive heuristics, and other heuristic algorithms, is proposed. Based on benchmark heuristics, extensive numerical experiments are conducted to test the utility of the algorithm. Comparative computational results demonstrate that the HGGA can provide high-quality solutions. Additionally, the computation times of the HGGA are generally shorter when compared to other algorithms. Thus, reduced length of picker tours leads to the overall reduction of the order picking time, which cuts down on overtime, workforce size, and the overall operational costs, while improving the quality of service.

Developing Multi-agent Systems for mHealth Drug Delivery

Recent research has explored how mobile networks are revolutionizing multiple aspects of healthcare in both developing and developed countries. As an area of innovation with the potential to make a huge difference, mHealth involves the utilization of mobile communication technologies to deliver healthcare services, such as SMS alerts that remind patients to take their prescription drugs at the appropriate time, remote diagnosis and even treatment for patients who do not have easy access to physicians, remote health monitoring devices that track and report patients’ conditions, and scheduling drug delivery. Such services could have a major impact on healthcare outcomes and costs. Decision making in mHealth drug delivery systems is complex. Decisions involve satisficing multiple goals regarding customer service quality, service cost, and healthcare worker satisfaction. With the increasing world-wide need for effective home healthcare, the increasing elderly population, and the increasing pressure from governments and other stakeholders, developing effective approaches for mHealth drug delivery decisions is imperative. In this paper, we present a multi-agent architecture that facilitates decision making in mHealth drug delivery system. 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, where decisions are based on intelligent agents that provide quick and intelligent alternative decisions in a dynamic environment.