Improved AdaBoost-based fingerprint algorithm for WiFi indoor localization

Yu, Feng; Jiang, Minghua; Liang, Jing; Qin, Xiao; Hu, Ming; Peng, Tao; Hu, Xinrong

doi:10.1109/itaic.2014.7064997

Cited by 9 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the amount of annotated data is limited in the training phase, the above models may suffer from the overfitting problem in the test phase. Some ensemble learning algorithms such as Adaboost [ 28 ] and random forest [ 29 ] are used to overcome this problem [ 12 , 13 , 30 , 31 ]. They train multiple weak learners (decision trees) by using the boosting or bagging method on the training set, and they integrate these learners into a strong learner for the final prediction.…”

Section: Related Workmentioning

confidence: 99%

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Lin

Gan

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

Indoor localization and navigation have become an increasingly important problem in both industry and academia with the widespread use of mobile smart devices and the development of network techniques. The Wi-Fi-based technology shows great potential for applications due to the ubiquitous Wi-Fi infrastructure in public indoor environments. Most existing approaches use trilateration or machine learning methods to predict locations from a set of annotated Wi-Fi observations. However, annotated data are not always readily available. In this paper, we propose a robot-aided data collection strategy to obtain the limited but high-quality labeled data and a large amount of unlabeled data. Furthermore, we design two deep learning models based on a variational autoencoder for the localization and navigation tasks, respectively. To make full use of the collected data, a hybrid learning approach is developed to train the models by combining supervised, unsupervised and semi-supervised learning strategies. Extensive experiments suggest that our approach enables the models to learn effective knowledge from unlabeled data with incremental improvements, and it can achieve promising localization and navigation performance in a complex indoor environment with obstacles.

show abstract

Section: Related Workmentioning

confidence: 99%

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Lin

Gan

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Standard ML [53], [54], [56], [57], [63], [68]- [72], [79]- [81], [83], [84], [86]- [89], [91], [92], [94], [96], [97], [102], [116]- [118], [120]- [122], [125], [126], [128], [129], [131], [132], [136]- [138], [140], [142], [181]- [184], [244], [249] [60], [61], [72], [75], [76], [104], [106], [108]- [110], [112], [156], [157], [160]- [162], …”

Section: Supervisedmentioning

confidence: 99%

“…Other ensemble learning methods have been used as well, such as gradient boosting regression forest (GBRF) [142], and AdaBoost [57], [92], [96]. Due to fluctuation of the RSSI signals, the RSSI distance might not reflect the true location distance; to address this [142] proposes a fingerprinting method by transforming raw RSSI into features with a learned non-linear mapping function using GBRF.…”

Section: Supervisedmentioning

confidence: 99%

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

Burghal,

Ravi,

Rao

et al. 2020

Preprint

View full text Add to dashboard Cite

The last few decades have witnessed a growing interest in location-based services. Using localization systems based on Radio Frequency (RF) signals has proven its efficacy for both indoor and outdoor applications. However, challenges remain with respect to both complexity and accuracy of such systems. Machine Learning (ML) is one of the most promising methods for mitigating these problems, as ML (especially deep learning) offers powerful practical data-driven tools that can be integrated into localization systems. In this paper, we provide a comprehensive survey of ML-based localization solutions that use RF signals. The survey spans different aspects, ranging from the system architectures, to the input features, the ML methods, and the datasets.A main point of the paper is the interaction between the domain knowledge arising from the physics of localization systems, and the various ML approaches. Besides the ML methods, the utilized input features play a major role in shaping the localization solution; we present a detailed discussion of the different features and what could influence them, be it the underlying wireless technology or standards or the preprocessing techniques. A detailed discussion is dedicated to the different ML methods that have been applied to localization problems, discussing the underlying problem and the solution structure. Furthermore, we summarize the different ways the datasets were acquired, and then list the publicly available ones. Overall, the survey categorizes and partly summarizes insights from almost 400 papers in this field.This survey is self-contained, as we provide a concise review of the main ML and wireless propagation concepts, which shall help the researchers in either field navigate through the surveyed solutions, and suggested open problems.

show abstract

“…For example, David et al [12] used the decision tree as the weak classifier to construct the indoor positioning system with advantages of excellent localization accuracy and lower algorithm complexity. Feng Yu et al [13] proposed an improved Adaboost algorithm to obtain good positioning accuracy by removing the error points in the location fingerprint database, thus improving the indoor positioning accuracy. Oscar et al [14] proposed a WiFi-Boost classification algorithm based on the feature combination between AP pairs, which minimized the adverse effects of WLAN network structure change and AP failure that could not be predicted.…”

Section: Introductionmentioning

confidence: 99%

A Method of WLAN Indoor Location Based on MMDM-Boost

Li¹,

Wen²

2017

Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 201

View full text Add to dashboard Cite

Abstract. Towards the problem of the time-varying AP signal strength degrades the indoor positioning accuracy in Wireless Local Area Network (WLAN), a WLAN indoor positioning method based on multiple mixed distribution model (MMDM) and Adaboost algorithm is adopted. Firstly, in order to describe the probability density distribution of AP signal strength accurately and improve the system suitability, the proposed method employs Gaussian mixture model, Binomial mixture model and Poisson mixture model to make up the MMDM and construct the fingerprint database. Secondly, in order to avoid the insufficient training of positioning model caused by lacking of training samples, the Adaboost is used to comprise the weak classifier based multiple MMDM into a strong classifier and improve the generalization ability of the system. Lastly, the mapping relation between fingerprint data and real position is also built by Adaboost classifier in online positioning stage. The experimental results show that the proposed method is superior to several indoor positioning algorithms with better time shifting adaptability and positioning accuracy.

show abstract

Improved AdaBoost-based fingerprint algorithm for WiFi indoor localization

Cited by 9 publications

References 14 publications

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

Wi-Fi-Based Indoor Localization and Navigation: A Robot-Aided Hybrid Deep Learning Approach

A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals

A Method of WLAN Indoor Location Based on MMDM-Boost

Contact Info

Product

Resources

About