Electric Street Cart with Protocols for Airborne Diseases

This paper presented the experimental implementation of an electric street cart integrated with protocols for airborne diseases. The proposed system combines Raspberry Pi-based embedded processing, webcam-based face-mask detection, deep-learning image classification, infrared-based proximity monitoring, and audio alerts. The implemented prototype successfully detects face masks in static images and real-time video streams and provides warnings when mask or social-distance protocols are violated. The use of MobileNetV2, OpenCV, TensorFlow, Keras, and Python provides a practical software platform for implementing the system on Raspberry Pi. The project demonstrates that AI-based monitoring and sensor-based proximity detection can be integrated into a compact street-cart platform. With further improvements in accuracy, sensing, computing capability, and system integration, the concept can be extended to a wider range of public environments.

[1] J. Ma, M. Du, and C. Wang, “Advances in Airborne Microorganism Detection Using Biosensors,” as cited in the project report. [2] D. C. Nguyen, M. Ding, P. N. Pathirana, et al., “Blockchain and AI Based Solutions to Combat Coronavirus,” as cited in the project report. [3] M. Lingana Gouda, Ranjitha, and Sangeeta, work on face-mask detection and airborne-disease protocols, International Journal of Advanced Research in Science, Communication and Technology, as cited in the project report. [4] B. Shiva and Jyothi, “Face Mask Detection System Using Deep Learning,” as cited in the project report. [5] P. N. Belhumeur, J. P. Hespanha, and D. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, as cited in the project report.