Home health care routing and scheduling in densely populated communities considering complex human behaviours

This study focuses on the home health care routing problem (HHCRP) in scenario of high population density areas where many elders live closely together. considers two main objectives. The first is to reduce travel and wait times for nurses or elders. second concerns socially related objectives scheduling problems, such as ‘quality life’ empowerment, by considering assumptions acquaintanceship mutual preferences models effects service time HHCRP. We use Markov decision process chance-constrained programming (CCP) model system conserve sequential provision parameters better represent influence stochastic times. Because traditional deterministic algorithms cannot solve a model, we apply model-free reinforcement learning algorithm, Q-learning (QL), well ant colony optimisation (ACO) algorithm. Thus, tackle this developing algorithm complex, large-scale systems. study’s theoretical practical contributions are verified feedback from researchers practitioners.