Automated Classroom Attendance in Educational Environments Using a BLE-Based Context-Aware Middleware

• Emanuel de Franceschi Vieira UFSM https://orcid.org/0009-0007-8381-3662
• Tiago Antônio Rizzetti UFSM https://orcid.org/0000-0002-2717-8699
• Renato Preigschadt De Azevedo UFSM https://orcid.org/0000-0002-5045-9595

DOI: https://doi.org/10.5753/sbcup.2026.23393

Resumo

This paper presents a context-aware middleware for educational environments that uses Bluetooth Low Energy (BLE) signals to infer room-level presence and support pervasive applications. The architecture integrates ESP32 devices with ESPresense firmware, MQTT communication, Home Assistant for contextual interpretation, and a Python-based middleware responsible for filtering, persisting, and exposing contextual events through a REST API. To validate the proposal, an automated classroom attendance application was implemented on top of this infrastructure. The evaluation was conducted through three controlled simulation runs of 60 minutes each, involving 30 synthetic students and pseudo-random mobility patterns. Results showed stable operation, no WebSocket failures, and coherent attendance behavior across arrival, stay, and departure phases. Although 21,600 MQTT messages were published per run, only 14.38% generated persisted events, indicating effective noise reduction by the middleware compared to a raw-event persistence baseline. During the stay phase, the average attendance reached 27.43 out of 30 students (91.43%). The paper also discusses privacy, deployment cost, hardware portability, and limitations of BLE-only presence sensing in real classrooms.

Referências

Abu-Rasheed, H., Weber, C., and Fathi, M. (2023). Context based learning: a survey of contextual indicators for personalized and adaptive learning recommendations – a pedagogical and technical perspective. Frontiers in Education, Volume 8 - 2023.

Huang, L.-S., Su, J.-Y., and Pao, T.-L. (2019). A context aware smart classroom architecture for smart campuses. Applied Sciences, 9(9).

Kaur, A., Bhatia, M., and Stea, G. (2022). A survey of smart classroom literature. Education Sciences, 12(2).

Morgan, A. A. (2024). On the accuracy of ble indoor localization systems: An assessment survey. Computers and Electrical Engineering, 118:109455.

Puckdeevongs, A., Tripathi, N. K., Witayangkurn, A., and Saengudomlert, P. (2020). Classroom attendance systems based on bluetooth low energy indoor positioning technology for smart campus. Information, 11(6).

Schilit, B., Adams, N., and Want, R. (1994). Context-aware computing applications.

Teran, M., Aranda, J., Carrillo, H., Mendez, D., and Parra, C. (2017). Iot-based system for indoor location using bluetooth low energy.

Vieira, E. and Rizzetti, T. (2025). Performance evaluation of an espresense/mqtt architecture for real-time locating system. In Anais da XXII Escola Regional de Redes de Computadores, pages 68–73, Porto Alegre, RS, Brasil. SBC.

Weiser, M. (1991). The computer for the 21 st century. Scientific american, 265(3):94–105.