ABSTRACT
This research explores the application of machine learning techniques to address queuing challenges in both the transportation and health sectors. Queuing problems in these critical domains often lead to inefficiencies, increase in waiting times, and resource misallocation. Leveraging machine learning algorithms offers a promising avenue to enhance system performance, streamline operations and ultimately improve user satisfaction. In the transportation sector, this study investigates the development of predictive models for traffic flow and congestion management. By analyzing historical data and real-time inputs, machine learning algorithms can anticipate traffic patterns, enable proactive decision making for optimization, traffic signal control and resource allocation. The aim is to reduce congestion, enhance travel time predictability, and improve overall transportation efficiency. In the health sector, the research focuses on optimizing patient flow within healthcare facilities. Machine learning algorithms has been employed to analyze patient arrival patterns, predict service demands, and optimize appointment scheduling. This approach aims to minimize patient waiting times, allocate resources efficiently, and enhance the overall patient experience. The study also looks at how machine learning might be used to prescribe drugs for minor ailments, which would allow healthcare facilities to allocate resources efficiently and on time. The result shows that if the intelligence of AI chatbots is incorporated into the health sector, over 80 % of time spent by patients in hospital will be saved. Also, it is noticeable that there was a reduction in the volume of traffic in fifteen minutes’ prediction. In urban areas like Lagos, Benin and Abuja where traffic influences even people’s schedule, this model can be programmed into sensors insertable into smart cars and traffic lights for fifteen minutes traffic prediction, suggestions of less congested routes and optimal traffic flow.
