A Raspberry Pi Based Event Driven Quasi Real Time Attendance Tracker

This project employs the IoT with an intelligent event-driven system in order to realize an efficient quasi real-time attendance tracker. The idea is to keep the whole system in the standby mode except for the low power motion sensor. On the detection of an event, when a person enters and originates a motion, the front-end embedded processor is alarmed. Afterwards, it activates the remaining system modules like webcam, communication block, etc. The event-driven feature improves the system performance in terms of resources utilization and power consumption compared to the counter classical ones. A first system implementation is realized and successfully tested. It is based on a raspberry pi 3 board, which is integrated with two Passive Infrared (PIR) sensors and two webcams. On the occurrence of an event the webcam is activated and it captures an image. The image is recorded via the Raspberry Pi webcam server and is shared with other system modules via the Porta Space application, which acts as a hub between the Raspberry Pi and the cloud. Simultaneously the attendance status is updated via the IFTTT on the cloud-based log. Moreover, the concerned authorities are notified via an email. The process is repeated every time when a person enters or leaves the concerned place. The attendance log remains globally available via the cloud and can be accessed anytime. The system design flow is described. The devised system functionality is tested with an experimental setup. Results have confirmed a proper system operation.

[1]  Saeed Mian Qaisar.  An event driven technique for filtering computational complexity reduction , 2015, 2015 International Conference on Event-based Control, Communication, and Signal Processing (EBCCSP).

[2]  S. M. Qaisar,et al.  A smart power management system monitoring and measurement approach based on a signal driven data acquisition , 2015, 2015 Saudi Arabia Smart Grid (SASG).

[3]  王海龙,et al.  Raspberry Pi Model B , 2012 .

[4]  Vlad Trifa,et al.  Building the Web of Things: With examples in Node.js and Raspberry Pi , 2016 .

[5]  Abdulhamit Subasi,et al.  An event driven surveillance system , 2016, 2016 5th International Conference on Electronic Devices, Systems and Applications (ICEDSA).

[7]  Visar Shehu,et al.  Using real time computer vision algorithms in automatic attendance management systems , 2010, Proceedings of the ITI 2010, 32nd International Conference on Information Technology Interfaces.

[8]  O. A. Idowu.  Development of Attendance Management System using Biometrics. , 2012 .

[9]  Kevin McFall,et al.  LOW-COST PLATFORM FOR AUTONOMOUS GROUND VEHICLE RESEARCH , 2014 .

[10]  Saeed Mian Qaisar.  Echantillonnage et traitement conditionnés par le signal : une approche prometteuse pour des traitements efficaces à pas adaptatifs , 2009 .

[11]  Saeed Mian Qaisar,et al.  Adaptive rate filtering a computationally efficient signal processing approach , 2014, Signal Process..

[12]  Simon Monk,et al.  Raspberry Pi Cookbook: Software and Hardware Problems and Solutions , 2016 .

[13]  Saeed Mian Qaisar,et al.  An efficient signal acquisition with an adaptive rate A/D conversion , 2013, 2013 IEEE International Conference on Circuits and Systems (ICCAS).

[14]  Fung Po Tso,et al.  The Glasgow Raspberry Pi Cloud: A Scale Model for Cloud Computing Infrastructures , 2013, 2013 IEEE 33rd International Conference on Distributed Computing Systems Workshops.

[15]  Rizqi Andry Ardiansyah,et al.  Design of An Electronic Narrator on Assistant Robot for Blind People , 2016 .

[16]  Mohammad Akbar,et al.  Design and implementation of a 5-bit flash ADC for education , 2016, 2016 5th International Conference on Electronic Devices, Systems and Applications (ICEDSA).

[17]  Min Chen,et al.  A Survey on Internet of Things From Industrial Market Perspective , 2015, IEEE Access.

[18]  Li Sun,et al.  Experimental Evaluation of WiFi Active Power/Energy Consumption Models for Smartphones , 2017, IEEE Transactions on Mobile Computing.