Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization
In the era of the Internet of Things and Artificial Intelligence, the Wi-Fi fingerprinting-based indoor positioning system (IPS) has been recognized as the most promising IPS for various applications. Fingerprinting-based algorithms critically rely on a fingerprint database built from machine learni...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/19/1/125 |
id |
doaj-96f0d520a5ef453b9b80c229d529077a |
---|---|
record_format |
Article |
spelling |
doaj-96f0d520a5ef453b9b80c229d529077a2020-11-25T00:58:12ZengMDPI AGSensors1424-82202019-01-0119112510.3390/s19010125s19010125Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor LocalizationLingwen Zhang0Ning Xiao1Wenkao Yang2Jun Li3School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaTandon School of Engineering, New York University, New York, NY 11201, USAIn the era of the Internet of Things and Artificial Intelligence, the Wi-Fi fingerprinting-based indoor positioning system (IPS) has been recognized as the most promising IPS for various applications. Fingerprinting-based algorithms critically rely on a fingerprint database built from machine learning methods. However, currently methods are based on single-feature Received Signal Strength (RSS), which is extremely unstable in performance in terms of precision and robustness. The reason for this is that single feature machines cannot capture the complete channel characteristics and are susceptible to interference. The objective of this paper is to exploit the Time of Arrival (TOA) feature and propose a heterogeneous features fusion model to enhance the precision and robustness of indoor positioning. Several challenges are addressed: (1) machine learning models based on heterogeneous features, (2) the optimization of algorithms for high precision and robustness, and (3) computational complexity. This paper provides several heterogeneous features fusion-based localization models. Their effectiveness and efficiency are thoroughly compared with state-of-the-art methods.http://www.mdpi.com/1424-8220/19/1/125indoor localizationheterogeneous features fusion (HFF)machine learningoptimization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lingwen Zhang Ning Xiao Wenkao Yang Jun Li |
spellingShingle |
Lingwen Zhang Ning Xiao Wenkao Yang Jun Li Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization Sensors indoor localization heterogeneous features fusion (HFF) machine learning optimization |
author_facet |
Lingwen Zhang Ning Xiao Wenkao Yang Jun Li |
author_sort |
Lingwen Zhang |
title |
Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization |
title_short |
Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization |
title_full |
Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization |
title_fullStr |
Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization |
title_full_unstemmed |
Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization |
title_sort |
advanced heterogeneous feature fusion machine learning models and algorithms for improving indoor localization |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-01-01 |
description |
In the era of the Internet of Things and Artificial Intelligence, the Wi-Fi fingerprinting-based indoor positioning system (IPS) has been recognized as the most promising IPS for various applications. Fingerprinting-based algorithms critically rely on a fingerprint database built from machine learning methods. However, currently methods are based on single-feature Received Signal Strength (RSS), which is extremely unstable in performance in terms of precision and robustness. The reason for this is that single feature machines cannot capture the complete channel characteristics and are susceptible to interference. The objective of this paper is to exploit the Time of Arrival (TOA) feature and propose a heterogeneous features fusion model to enhance the precision and robustness of indoor positioning. Several challenges are addressed: (1) machine learning models based on heterogeneous features, (2) the optimization of algorithms for high precision and robustness, and (3) computational complexity. This paper provides several heterogeneous features fusion-based localization models. Their effectiveness and efficiency are thoroughly compared with state-of-the-art methods. |
topic |
indoor localization heterogeneous features fusion (HFF) machine learning optimization |
url |
http://www.mdpi.com/1424-8220/19/1/125 |
work_keys_str_mv |
AT lingwenzhang advancedheterogeneousfeaturefusionmachinelearningmodelsandalgorithmsforimprovingindoorlocalization AT ningxiao advancedheterogeneousfeaturefusionmachinelearningmodelsandalgorithmsforimprovingindoorlocalization AT wenkaoyang advancedheterogeneousfeaturefusionmachinelearningmodelsandalgorithmsforimprovingindoorlocalization AT junli advancedheterogeneousfeaturefusionmachinelearningmodelsandalgorithmsforimprovingindoorlocalization |
_version_ |
1725221087185207296 |