A precise RFID indoor localization system with sensor network assistance

Dian ZHANG; Kezhong LU; Rui MAO

doi:10.1109/CC.2015.7114062

A precise RFID indoor localization system with sensor network assistance

Dian ZHANG, Kezhong LU, Rui MAO

Research output: Journal Publications › Journal Article (refereed)

18 Citations (Scopus)

Abstract

Indoor localization is very critical for medical care applications, e.g., the patient localization or tracking inside the building of the hospital. Traditional Radio Frequency Identification (RFID) technologies are very popular in this area since their cost is very low. In such technologies, each tag acts as the transmitter and the Radio Signal Strength Indicator (RSSI) information is measured from the readers. However, RSSI information suffers severely from the mult i-path phenomenon. As a result, if in a very large area, the localization accuracy will be affected seriously. In order to solve this problem, we introduce Wireless Sensor Networks (WSNs) with only a few nodes, each of which acts as both transmitter and receiver. In such networks, the change of signal strength (referred as dynamic of RSSI) is leveraged to select a cluster of reference tags as candidates. Then the final target location is estimated by using the RSSI relationships between the target tag and candidate reference tags. Thus, the localization accuracy and scalability are able to be improved. We proposed two algorithms, SA-LANDMARC, and COCKTAIL. Experiments show that the localization accuracy of the two algorithms can reach 0.7m and 0.45m, respectively. Compared to most traditional Radio Frequency (RF)-based approaches, the localization accuracy is improved at least 50%.

Original language	English
Pages (from-to)	13-22
Number of pages	10
Journal	China Communications
Volume	12
Issue number	4
DOIs	https://doi.org/10.1109/CC.2015.7114062
Publication status	Published - Apr 2015
Externally published	Yes

Fingerprint

Radio frequency identification (RFID)

Sensor networks

Transmitters

Health care

Scalability

Wireless sensor networks

Costs

Experiments

Keywords

radio frequency
RFID
support vector regression
hybrid

Cite this

ZHANG, D., LU, K., & MAO, R. (2015). A precise RFID indoor localization system with sensor network assistance. China Communications, 12(4), 13-22. https://doi.org/10.1109/CC.2015.7114062

ZHANG, Dian ; LU, Kezhong ; MAO, Rui. / A precise RFID indoor localization system with sensor network assistance. In: China Communications. 2015 ; Vol. 12, No. 4. pp. 13-22.

@article{dc0b560d80d6497e94970b7fe8e6f108,

title = "A precise RFID indoor localization system with sensor network assistance",

abstract = "Indoor localization is very critical for medical care applications, e.g., the patient localization or tracking inside the building of the hospital. Traditional Radio Frequency Identification (RFID) technologies are very popular in this area since their cost is very low. In such technologies, each tag acts as the transmitter and the Radio Signal Strength Indicator (RSSI) information is measured from the readers. However, RSSI information suffers severely from the mult i-path phenomenon. As a result, if in a very large area, the localization accuracy will be affected seriously. In order to solve this problem, we introduce Wireless Sensor Networks (WSNs) with only a few nodes, each of which acts as both transmitter and receiver. In such networks, the change of signal strength (referred as dynamic of RSSI) is leveraged to select a cluster of reference tags as candidates. Then the final target location is estimated by using the RSSI relationships between the target tag and candidate reference tags. Thus, the localization accuracy and scalability are able to be improved. We proposed two algorithms, SA-LANDMARC, and COCKTAIL. Experiments show that the localization accuracy of the two algorithms can reach 0.7m and 0.45m, respectively. Compared to most traditional Radio Frequency (RF)-based approaches, the localization accuracy is improved at least 50{\%}.",

keywords = "radio frequency, RFID, support vector regression, hybrid",

author = "Dian ZHANG and Kezhong LU and Rui MAO",

year = "2015",

month = "4",

doi = "10.1109/CC.2015.7114062",

language = "English",

volume = "12",

pages = "13--22",

journal = "China Communications",

issn = "1673-5447",

publisher = "China Institute of Communication",

number = "4",

}

ZHANG, D, LU, K & MAO, R 2015, 'A precise RFID indoor localization system with sensor network assistance', China Communications, vol. 12, no. 4, pp. 13-22. https://doi.org/10.1109/CC.2015.7114062

A precise RFID indoor localization system with sensor network assistance. / ZHANG, Dian; LU, Kezhong; MAO, Rui.

In: China Communications, Vol. 12, No. 4, 04.2015, p. 13-22.

Research output: Journal Publications › Journal Article (refereed)

TY - JOUR

T1 - A precise RFID indoor localization system with sensor network assistance

AU - ZHANG, Dian

AU - LU, Kezhong

AU - MAO, Rui

PY - 2015/4

Y1 - 2015/4

N2 - Indoor localization is very critical for medical care applications, e.g., the patient localization or tracking inside the building of the hospital. Traditional Radio Frequency Identification (RFID) technologies are very popular in this area since their cost is very low. In such technologies, each tag acts as the transmitter and the Radio Signal Strength Indicator (RSSI) information is measured from the readers. However, RSSI information suffers severely from the mult i-path phenomenon. As a result, if in a very large area, the localization accuracy will be affected seriously. In order to solve this problem, we introduce Wireless Sensor Networks (WSNs) with only a few nodes, each of which acts as both transmitter and receiver. In such networks, the change of signal strength (referred as dynamic of RSSI) is leveraged to select a cluster of reference tags as candidates. Then the final target location is estimated by using the RSSI relationships between the target tag and candidate reference tags. Thus, the localization accuracy and scalability are able to be improved. We proposed two algorithms, SA-LANDMARC, and COCKTAIL. Experiments show that the localization accuracy of the two algorithms can reach 0.7m and 0.45m, respectively. Compared to most traditional Radio Frequency (RF)-based approaches, the localization accuracy is improved at least 50%.

AB - Indoor localization is very critical for medical care applications, e.g., the patient localization or tracking inside the building of the hospital. Traditional Radio Frequency Identification (RFID) technologies are very popular in this area since their cost is very low. In such technologies, each tag acts as the transmitter and the Radio Signal Strength Indicator (RSSI) information is measured from the readers. However, RSSI information suffers severely from the mult i-path phenomenon. As a result, if in a very large area, the localization accuracy will be affected seriously. In order to solve this problem, we introduce Wireless Sensor Networks (WSNs) with only a few nodes, each of which acts as both transmitter and receiver. In such networks, the change of signal strength (referred as dynamic of RSSI) is leveraged to select a cluster of reference tags as candidates. Then the final target location is estimated by using the RSSI relationships between the target tag and candidate reference tags. Thus, the localization accuracy and scalability are able to be improved. We proposed two algorithms, SA-LANDMARC, and COCKTAIL. Experiments show that the localization accuracy of the two algorithms can reach 0.7m and 0.45m, respectively. Compared to most traditional Radio Frequency (RF)-based approaches, the localization accuracy is improved at least 50%.

KW - radio frequency

KW - RFID

KW - support vector regression

KW - hybrid

UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930730941&doi=10.1109%2fCC.2015.7114062&partnerID=40&md5=0dfbd9b77739d495475284a60b6695c0

U2 - 10.1109/CC.2015.7114062

DO - 10.1109/CC.2015.7114062

M3 - Journal Article (refereed)

VL - 12

SP - 13

EP - 22

JO - China Communications