Comparative Studies of Supporting Vector Machines and Artificial Neural Networks for Scheduling Optimization

This project is to construct an improved clinic scheduling and flow system for optimization. Providing a solution to this issue will require determining the main clinic scheduling problem and figuring out what hardware and software issues are needed to be solved. We took an approach to optimize the appointment schedule by training and comparing various Machine Learning models such as Supporting Vector Machines and Artificial Neural Networks, and pick the model with the best performance for the scheduling optimization. The software framework was developed based on the Django web server with the Scikit-Learn Machine Learning library from Python.

Keywords:

Machine Learning , Supporting Vector Machines , Artificial Neural Networks