Integrating RFID Technology with Intelligent Classifiers for Meaningful Prediction Knowledge

Peter Darcy, Steven Tucker, Bela Stantic

School of Information and Communication Technology, Griffith University, Gold Coast, Australia.

DOI: 10.4236/ait.2013.32004                

Abstract

Radio Frequency Identification (RFID) is wireless technology that has been designed to automatically identify tagged objects using a reader. Several applications of this technology have been introduced in past literature such as pet identification and luggage tracking which have increased the efficiency and effectiveness of each environment into which it was integrated. However, due to the ambiguous nature of the captured information with the existence of missing, wrong and duplicate readings, the wide-scale adoption of the architecture is limited to commercial sectors where the integrity of the observations can tolerate ambiguity. In this work, we propose an application of RFID to take the reporting of class attendance and to integrate a predictive classifier to extract high level meaningful information that can be used in diverse areas such as scheduling and low student retention. We conclude by providing an analysis of the core strengths and opportunities that exist for this concept and how we might extend it in future research.

Keywords

Radio Frequency Identification; Classifier; Prediction; Neural Network; Bayesian Network

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	S. S. Chawathe, V. Krishnamurthy, S. Ramachandran and S. E. Sarma, “Managing RFID Data,” Proceedings of the Thirtieth International Conference on Very Large Data Bases, Vol. 30, 2004, pp. 1189-1195.
[2]	P. Darcy, B. Stantic and A. Sattar, “A Novel Integrated Classifier for Handling Data Warehouse Anomalies,” Advances in Databases and Information Systems (ADBIS 2011), Vienna, 20-23 September 2011, pp. 98-110.
[3]	R. Derakhshan, M. E. Orlowska and X. Li, “RFID Data Management: Challenges and Opportunities,” IEEE Conference on RFID, Brisbane, 26-28 March 2007, pp. 175- 182.
[4]	P. Pupunwiwat and B. Stantic, “Resolving RFID Data Stream Collisions Using Set-Based Approach,” The Sixth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP 2010), Gold Coast, 7-10 December 2010, pp. 61-66.
[5]	P. Darcy, P. Pupunwiwat and B. Stantic, “The Fusion of Pre/Post RFID Correction Techniques to Reduce Anomalies,” Intelligent Sensor Networks: Across Sensing, Signal Processing, and Machine Learning, CRC Press, New York, 2012. doi:10.1201/b14300-28
[6]	P. Darcy, B. Stantic and A. Sattar, “Applying a Neural Network to Recover Missed RFID Readings,” Australasian Computer Science Conference (ACSC 2010), Brisbane, 18-22 January 2010, pp. 133-142.
[7]	P. Darcy, B. Stantic and A. Sattar, “X-CleLo: Intelligent Deterministic RFID Data and Event Transformer,” Journal of Personal and Ubiquitous Computing, Vol. 16, No. 3, 2011, pp. 259-269.
[8]	M. Singh and M. Valtorta, “Construction of Bayesian Network Structures from Data: A Brief Survey and an Efficient Algorithm,” International Journal of Approximate Reasoning, 1995, pp. 259-265.
[9]	P. Darcy, B. Stantic and A. Sattar, “Augmenting a Deferred Bayesian Network with a Genetic Algorithm to Correct Missed RFID Readings,” Malaysian Joint Conference on Artificial Intelligence (MJCAI 2009), Kuala Lumpur, 14-16 July 2009, pp. 106-115.
[10]	W. S. Mcculloch and W. Pitts, “A Logical Calculus of the IdeasImmanent in Nervous Activity,” Bulletin of Mathematical Biophysics, Vol. 5, No. 4, 1943, pp. 115-133. doi:10.1007/BF02478259
[11]	D. Rumelhart, G. Hinton and R. Williams, “Learning Representations by Back-Propagating Errors,” Nature (London), Vol. 323, 1986, pp. 533-536.
[12]	M. Blumenstein, X. Y. Liu and B. Verma, “An Investigation of the Modified Direction Feature for Cursive Character Recognition,” Pattern Recognition, Vol. 40, No. 2, 2007, pp. 376-388. doi:10.1016/j.patcog.2006.05.017
[13]	J. Holland, “Adaptation in Natural and Artificial Systems,” University of Michigan Press, Massachusetts, 1975.
[14]	A. Rooij, R. Johnson and L. Jain, “Neural Network Training Using Genetic Algorithms,” World Scientific Publishing Co., Inc, River Edge, 1996.
[15]	AT&T, “RFID Tags Help Schools Keep Tabs,” 2008. http://www.corp.att.com/edu/docs/k12rfid2.pdf
[16]	C. Des Marais, “Texas School Uses RFID Badges to Track Student Locations,” 2012. http://www.pcworld.com/article/2011352/texas-school-uses-rfidbadges-to-track-student-locations.html
[17]	G. Bhanage, Y. Zhang, Y. Zhang, W. Trappe and R. Howard, “Roll Call: The Design for a Low-Cost and Power Efficient Active RFID Asset Tracking System,” The International Conference on Computer as a Tool, Piscataway, 9-12 September 2007, pp. 2521-2528.
[18]	W. Wang, C. Chang and C. Huang, “A Study on RFID Combined with Network Technology for Collective Management of Tour Bus Tourists,” Service Systems and Service Management (ICSSSM), Shanghai, 2-4 July 2012, pp. 547-550