Machine Learning Techniques in RFID Datasets
Meghna Sharma1, Manjeet Singh Tomer2, Priyanka Vashisht3

1Meghna Sharma, Dept. of Computer Science and Engineering The NorthCap University, Gurugram.
2Manjeet Singh Tomer , Dept. of Computer Applications J C Bose University of Science and Technology, YMCA, Faridabad
3Priyanka Vashisht, Dept. of Computer Science and Engineering The NorthCap University, Gurugram.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 24, 2020. | Manuscript published on March 30, 2020. | PP: 4345-4353 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9052038620/2020©BEIESP | DOI: 10.35940/ijrte.F9052.038620

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: In today’s world of wireless communication, technologies like Wi-Fi, Global Positioning Systems (GPS), Radio Frequency Identification (RFID) and Wireless Sensor Networks (WSN) play a vital role in various applications for the benefit and convenience of the society. A widespread application of RFID networks based on automatic data capture technology is supply chain management. In RFID enabled supply chain process lot of possibilities of outliers or anomaly generation due to technical or environmental factors exist. This work mainly focuses on identifying various techniques used for outlier detection in RFID datasets in supply chain process. Most of literature studies are related to objects tracking and product management in the domain of supply chain but very few researchers have worked on the abnormal condition or outlier detection while monitoring of RFID tagged objects. Outliers are any kind of deviation in supply chain processes from its normal processing or behavior. Our research is specific to the supply-chain process using RFID system specifically for the abnormality detection in the localization process in supply-chain process. Inaccurate localization of objects can be due to several reasons like theft, counterfeiting, traffic problem, environmental factors or malfunctioning of the vehicle carrying RFID tagged objects.
Keywords: RFID, Machine Learning, Wireless Communication, Outlier Detection.
Scope of the Article: Machine Learning.