Guilherme Figueiredo;Brandon Hubbs;Adarsh D. Radadia
{"title":"使用无源RFID标签监测头部方向","authors":"Guilherme Figueiredo;Brandon Hubbs;Adarsh D. Radadia","doi":"10.1109/JRFID.2023.3323948","DOIUrl":null,"url":null,"abstract":"This paper describes an RFID system for head orientation tracking (R-SHOT), a novel wireless and battery-free approach for monitoring head kinematics. R-SHOT uses two linear polarized antennas mounted on a metal frame backpack, three commercial RFID tags placed orthogonally on the subject’s head, an RFID reader, software for data collection and processing, and an IMU for calibration. Training datasets were collected using stationary head positions with varying yaw, pitch, and roll, which were then used to develop a second-order multi-variate model to predict the Euler angles (R2 = 0.997 and standard error = 1–3°). Attempts to use a first-order model, reduce variables, and increase the number of static head positions for model training did not yield favorable results. Challenges in model development due to noise and asynchronous sampling were overcome using a Kalman filter and linear interpolation. The R-SHOT model developed using static head positions was found to predict Euler angles - when applied to full head motion - with low error, especially when the head position was closer to an extreme. The development of this model holds the keys to future real-time application of R-SHOT for patient care and mobility aid solutions.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"7 ","pages":"582-590"},"PeriodicalIF":2.3000,"publicationDate":"2023-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Monitoring Head Orientation Using Passive RFID Tags\",\"authors\":\"Guilherme Figueiredo;Brandon Hubbs;Adarsh D. Radadia\",\"doi\":\"10.1109/JRFID.2023.3323948\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper describes an RFID system for head orientation tracking (R-SHOT), a novel wireless and battery-free approach for monitoring head kinematics. R-SHOT uses two linear polarized antennas mounted on a metal frame backpack, three commercial RFID tags placed orthogonally on the subject’s head, an RFID reader, software for data collection and processing, and an IMU for calibration. Training datasets were collected using stationary head positions with varying yaw, pitch, and roll, which were then used to develop a second-order multi-variate model to predict the Euler angles (R2 = 0.997 and standard error = 1–3°). Attempts to use a first-order model, reduce variables, and increase the number of static head positions for model training did not yield favorable results. Challenges in model development due to noise and asynchronous sampling were overcome using a Kalman filter and linear interpolation. The R-SHOT model developed using static head positions was found to predict Euler angles - when applied to full head motion - with low error, especially when the head position was closer to an extreme. The development of this model holds the keys to future real-time application of R-SHOT for patient care and mobility aid solutions.\",\"PeriodicalId\":73291,\"journal\":{\"name\":\"IEEE journal of radio frequency identification\",\"volume\":\"7 \",\"pages\":\"582-590\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2023-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE journal of radio frequency identification\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10286163/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE journal of radio frequency identification","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10286163/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Monitoring Head Orientation Using Passive RFID Tags
This paper describes an RFID system for head orientation tracking (R-SHOT), a novel wireless and battery-free approach for monitoring head kinematics. R-SHOT uses two linear polarized antennas mounted on a metal frame backpack, three commercial RFID tags placed orthogonally on the subject’s head, an RFID reader, software for data collection and processing, and an IMU for calibration. Training datasets were collected using stationary head positions with varying yaw, pitch, and roll, which were then used to develop a second-order multi-variate model to predict the Euler angles (R2 = 0.997 and standard error = 1–3°). Attempts to use a first-order model, reduce variables, and increase the number of static head positions for model training did not yield favorable results. Challenges in model development due to noise and asynchronous sampling were overcome using a Kalman filter and linear interpolation. The R-SHOT model developed using static head positions was found to predict Euler angles - when applied to full head motion - with low error, especially when the head position was closer to an extreme. The development of this model holds the keys to future real-time application of R-SHOT for patient care and mobility aid solutions.