Sensors & Transducers, Vol. 194, Issue 11, November 2015, pp. 42-53 42 Sensors & Transducers © 2015 by IFSA Publishing, S. L. http://www.sensorsportal.com Gas Identification Using Passive UHF RFID Sensor Platform 1, * Muhammad Ali AKBAR, 2 Mohamed ZGAREN, 1 Amine AIT SI ALI, 1 Abbes AMIRA, 1 Mohieddine BENAMMAR, 1 Faycal BENSAALI, 2 Mohamad SAWAN and 3 Amine BERMAK 1 College of Engineering, Qatar University, Doha, Qatar 2 Dept. of Electrical Engineering, Polytechnique Montreal, Montreal, Quebec, Canada 3 School of Engineering, Hong Kong Uni. of Sci. and Tech., Clear Water Bay, Hong Kong * E-mail: ali.akbar@qu.edu.qa Received: 31 August 2015 /Accepted: 15 October 2015 /Published: 30 November 2015 Abstract: The concept of passive Radio Frequency Identification (RFID) sensor tag is introduced to remove the dependency of current RFID platforms on battery life. In this paper, a gas identification system is presented using passive RFID sensor tag along with the processing unit. The RFID system is compliant to Electronics Product Code Generation 2 (EPC-Gen2) protocol in 902-928 MHz ISM band. Whereas the processing unit is implemented and analyzed in software and hardware platforms. The software platform uses MATLAB, whereas a High Level Synthesis (HLS) tool is used to implement the processing unit on a Zynq platform. Moreover, two sets of different gases are used along with Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) based feature reduction approaches to analyze in detail the best feature reduction approach for efficient classification of gas data. It is found that for the first set of gases, 90 % gases are identified using first three principal components, which is 7 % more efficient than LDA. However in terms of hardware overhead, LDA requires 50 % less hardware resources than PCA. The classification results for the second set of gases reveal that 91 % of gas classification is obtained using LDA and first four PCA, while LDA requires 52 % less hardware resources than PCA. The RFID tag used for transmission is implemented in 0.13 µm CMOS process, with simulated average power consumption of 2.6 µW from 1.2 V supply. ThingMagic M6e embedded reader is used for RFID platform implementation. It shows an output power of 31.5 dBm which allows a read range up to 9 meters. Copyright © 2015 IFSA Publishing, S. L. Keywords: Sensor tag, Pattern recognition, Gas identification, UHF RFID Reader, EPC Gen2, ISM Band. 1. Introduction Gas identification is one of the most critical challenges in the current gas industry because a single leakage of an explosive gas can cause a complete disaster for the whole company. The explosion of a gas container or the leakage of a hazardous gas will also be disastrous for the environment [1]. Therefore, human olfactory based Electronic Nose (EN) systems are introduced, with a wide range of applications like milk industry [2] and patient monitoring system [3]. In gas applications, the presence of complex compounds like water vapor with the gases of interest creates one of the challenging issues for the gas identification using EN [4]. The presence of battery further limits the life and durability of the sensor tag. www.sensorsportal.com/HTML/DIGEST/P_2756.htm