IOT INTEGRATED CLASS MONITORING SYSTEM USING AI
Keywords:
Internet Of Things (IOT), Artificial Intelligence (AI), Face Recognition, Object Detection, Real-Time Monitoring, Attendance MarkingAbstract
This project presents an IoT-integrated class monitoring system using artificial intelligence (AI) for attendance marking and classroom automation. The system comprises two main components: attendance marking using cameras and a convolutional neural network (CNN) algorithm, and classroom automation based on human presence detection using IoT. The software stack includes Anaconda for Python environment management, Visual Studio C++ for Arduino Nano programming, and TensorFlow for implementing AI algorithms. Hardware components include cameras, an Arduino Nano microcontroller, and a dual- channel relay for controlling appliances. The attendance marking component utilizes face recognition with a pre- trained model to mark attendance in real-time. Detected faces are compared against a database, and attendance records are updated in a Google Sheets document. The IoT component detects human presence using object detection with a pre-trained TensorFlow model. Based on presence detection, appliances such as fans are controlled using the Arduino Nano and relay module. The system provides real- time monitoring and automation of classroom activities. Implementation involves integrating software and hard- ware components, loading pre-trained models, initializing system components, and continuously capturing frames from cameras. Challenges such as hardware compatibility and software configuration were addressed during implementation. Future enhancements include the integration of additional sensors for enhanced presence detection and the expansion of the system’s capabilities for automating other classroom functions. Overall, the IoT-integrated class monitoring system demonstrates the potential of AI and IoT technologies to streamline classroom management processes and enhance learning environments.
References
B. Bharmal, A. Shahapurkar, and A. Aswalkar, “Automatic home lighting solutions using human detection, sunlight intensity and room temperature,” International Research Journal of Engineering and Technology, vol. 4, 2017.
H. Ullah, A. Altamimi, M. Uzair, and M. Ullah, “Efficient anomaly detection in crowd videos using pre-trained 2d convolutional neural
networks,” Neurocomputing, vol. 290, pp. 74–86, May 2018.
A. Jadhav, T. Ladhe, and K. Yeolekar, “Ai-based attendance monitoring system,” IrjetVolume, vol. 04, no. 01, pp. 1–4, Jan 2017.
O. Shoewu and O. Idowu, “Face recognition based smart at- tendance system using iot,” The Pacific Journal of Science and Technology, vol. 13, no. 1, pp. 300–307, May 2012.
G. Hinton and R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, pp. 504–507, 2006.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 788–797.
V. Wiley and T. Lucas, “Research and development of the pupil identification and warning system using ai-iot,” International Jour- nal of Artificial Intelligence Research, vol. 2, no. 1, pp. 28–36, 2018.
X. S. Y. L. S. L. J. Kefan, “Crowd counting analysis using deep learning: a critical review,” Kybernet, year.
N. Bagali and P. G. Navalyal, “Sensor-based automatic fan con- trolling system and power consumption analysis,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 5, 2016.
