Conformal Prediction for Indoor Localisation with Fingerprinting Method

Khuong Nguyen; Zhiyuan Luo

doi:10.1007/978-3-642-33412-2_22

Conformal Prediction for Indoor Localisation with Fingerprinting Method

Khuong Nguyen
, Zhiyuan Luo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Indoor localisation is the state-of-the-art to identify and observe a moving human or object inside a building. Location Fingerprinting is a cost-effective software-based solution utilising the built-in wireless signal of the building to estimate the most probable position of a real-time signal data. In this paper, we apply the Conformal Prediction (CP) algorithm to further enhance the Fingerprinting method. We design a new nonconformity measure with the Weighted K-nearest neighbours (W-KNN) as the underlying algorithm. Empirical results show good performance of the CP algorithm.

Original language	English
Title of host publication	Artificial Intelligence Applications and Innovations
Subtitle of host publication	First Conformal Prediction and Its Applications Workshop (COPA 2012)
Place of Publication	Halkidiki, Greece
Publisher	Springer
Pages	214-223
Number of pages	10
ISBN (Print)	978-3-642-33411-5
DOIs	https://doi.org/10.1007/978-3-642-33412-2_22
Publication status	Published - Sept 2012

Keywords

indoor localisation
fingerprinting
Conformal Prediction

Access to Document

10.1007/978-3-642-33412-2_22

http://www.springerlink.com/content/v80663x408707427/

Cite this

@inproceedings{390bf35142c948d286614269f3e9818f,

title = "Conformal Prediction for Indoor Localisation with Fingerprinting Method",

abstract = "Indoor localisation is the state-of-the-art to identify and observe a moving human or object inside a building. Location Fingerprinting is a cost-effective software-based solution utilising the built-in wireless signal of the building to estimate the most probable position of a real-time signal data. In this paper, we apply the Conformal Prediction (CP) algorithm to further enhance the Fingerprinting method. We design a new nonconformity measure with the Weighted K-nearest neighbours (W-KNN) as the underlying algorithm. Empirical results show good performance of the CP algorithm. ",

keywords = "indoor localisation, fingerprinting, Conformal Prediction",

author = "Khuong Nguyen and Zhiyuan Luo",

year = "2012",

month = sep,

doi = "10.1007/978-3-642-33412-2\_22",

language = "English",

isbn = "978-3-642-33411-5",

pages = "214--223",

booktitle = "Artificial Intelligence Applications and Innovations",

publisher = "Springer",

}

TY - GEN

T1 - Conformal Prediction for Indoor Localisation with Fingerprinting Method

AU - Nguyen, Khuong

AU - Luo, Zhiyuan

PY - 2012/9

Y1 - 2012/9

N2 - Indoor localisation is the state-of-the-art to identify and observe a moving human or object inside a building. Location Fingerprinting is a cost-effective software-based solution utilising the built-in wireless signal of the building to estimate the most probable position of a real-time signal data. In this paper, we apply the Conformal Prediction (CP) algorithm to further enhance the Fingerprinting method. We design a new nonconformity measure with the Weighted K-nearest neighbours (W-KNN) as the underlying algorithm. Empirical results show good performance of the CP algorithm.

AB - Indoor localisation is the state-of-the-art to identify and observe a moving human or object inside a building. Location Fingerprinting is a cost-effective software-based solution utilising the built-in wireless signal of the building to estimate the most probable position of a real-time signal data. In this paper, we apply the Conformal Prediction (CP) algorithm to further enhance the Fingerprinting method. We design a new nonconformity measure with the Weighted K-nearest neighbours (W-KNN) as the underlying algorithm. Empirical results show good performance of the CP algorithm.

KW - indoor localisation

KW - fingerprinting

KW - Conformal Prediction

U2 - 10.1007/978-3-642-33412-2_22

DO - 10.1007/978-3-642-33412-2_22

M3 - Conference contribution

SN - 978-3-642-33411-5

SP - 214

EP - 223

BT - Artificial Intelligence Applications and Innovations

PB - Springer

CY - Halkidiki, Greece

ER -