Students Trajectory Pattern Finding Scheme Based on RSSI Geolocation as a Part of Smart Campus

Smart campus refers to supporting facilities for activities that are integrated using information technology. Various events or problems in the campus environment can be identified and well-tracked. In this paper, student trajectory patterns will be determined as a passive step in verifying the legality of smartphone users on campus. The Receive Signal Strength Indicator (RSSI) data obtained from the Wireless Access Point will be processed to determine the location of students using the Fingerprinting Indoor Localization method. The K-Nearest Neighbor algorithm is used as the basis for determining the user’s position with the Manhattan metric and k=1, the model accuracy is 81%. The simulation result shows that in the testing phase of the test set, the average position error obtained was 12.39 meters, with a building prediction accuracy of 98% and a floor prediction accuracy of 88%.