| dc.description.abstract | Traditional attendance tracking methods have been related to
inefficient use of time and resources. An automatic attendance tracking
system allows students to certify their attendance in conventional inperson classroom settings. This thesis proposes creating a new version
of the AttendanceKit [1] application suite that uses real-time NFC, or
Near-Field Communications [19] technology instead of UHF RFID (UltraHigh Frequency Radio-Frequency Identification) and recognition of
facial features to automate the process of recording attendance. The
suggested instrument will be created as a collection of mobile apps
specifically designed for use by institutions, lecturers, and students.
This method can substantially decrease the limitations related to
manual inspection while producing very exact results. The back-end
platform will make real-time modifications, sending automated push
notifications to students' mobile devices, encouraging them to launch
the app and verify their attendance.
In addition, these systems will have attendance tracking tools that
will enable teachers to assess and identify the absence status of
individual pupils. When a student submits a formal request, the
application allows professors to personally monitor attendance in
situations where unforeseen student problems occur. In addition, the
technique has the potential to automatically provide thorough reports
and analyses regarding the learning progress of individual students
within each specific class, as well as the overall performance of the
class as a whole. Educators and educational institutions can use this
vital information to determine the overall percentage of students who
demonstrate a strong commitment to attending classes. My
experimental findings demonstrate that doing preliminary simulations
of the system provides a more thorough comprehension of its
operations and interactions. The class's learning results are then assessed through an assessment. The approach accounts for both time
economy and accuracy.
Moreover, this study's findings offer a thorough assessment of the
system's efficacy when deployed using NFC tags and genuine mobile
devices. Furthermore, an innovative machine learning framework is
presented, which can be efficiently employed on tangible devices for
business applications. | en_US |
