Smart Timetable Scheduler and Management System for Campus

Abstract

Department timetable scheduling is a challenging and complex problem and has been confirmed to be an NP-complete problem. In this paper, Hybrid GA-PSO algorithm is used to overcome the timetable scheduling problem and to meet all constraints of the department for automated time table generation. Algorithm is designed by performance analysis of two Artificial Intelligence Algorithms which are Particle Swarm Optimization Algorithm (PSO) and Genetic Algorithm (GA). Machine learning Algorithm is used to develop hardware model for the automatic time table scheduler to send notifications to intimate faculties about the class, based on face recognition. The Haar-cascade Algorithm is used for face detection and Local Binary Pattern Histogram Algorithm (LBPH) for face recognition to train the data. Python programming languages and the OpenCV library are used because they enable a higher level of precision and adequacy to be achieved. Training and identification are done in embedded device known as Raspberry Pi and GSM module is used to send notifications to faculties to achieve an effective time table management system for smart campus.