EA-CNN: A smart indoor 3D positioning scheme based on Wi-Fi fingerprinting and deep learning

Alitaleshi, Atefe; Jazayeriy, Hamid; Kazemitabar, Javad

doi:10.1016/j.engappai.2022.105509

Cited by 17 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset, employed in previous work including [17] aimed to enhance indoor positioning precision by LSTM algorith ms. The study in [6] achieved a positioning error are range 2.5 meters to 2.7 meters on the public dataset [16]. The paper [16] verified the dataset' s normalization and reliability for indoor localization research.…”

Section: B Indoor Positioning Datasetmentioning

confidence: 71%

“…The dataset was divided into training (16,704 fingerprints fro m 24 reference points) and test sets (46,800 fingerprints fro m 106 reference points), each containing 448 RSSI indicators from access points. Following the approach of [6], our experiments on the www.ijacsa.thesai.org normalized public dataset utilized the Min maxscale() function and Formula (1). min max min scaled XX X XX…”

Section: B Indoor Positioning Datasetmentioning

confidence: 99%

“…Apart from KNN-based methods, deep learning techniques have also been exp lored for indoor positioning. Convolutional Neural Networks (CNN) [6,7] and Long Short-Term Memory (LSTM) [8] networks are notable examples. CNN can effectively extract spatial features from Wi-Fi images, while LSTM can model temporal dependencies in time-series data, such as RSSI signals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dimensionality Reduction with Truncated Singular Value Decomposition and K-Nearest Neighbors Regression for Indoor Localization

Thi,

Manh,

Anh

et al. 2023

IJACSA

View full text Add to dashboard Cite

Indoor localization presents formidable challenges across diverse sectors, encompassing indoor navigation and asset tracking. In this study, we introduce an inventive indoor localization methodology that combines Truncated S ingular Value Decomposition (Truncated S VD) for dimensionality reduction with the K-Nearest Neighbors Regressor (KNN Regression) for precise position prediction. The central objective of this proposed technique is to mitigate the complexity of highdimensional input data while preserving critical information essential for achieving accurate localization outcomes. To validate the effectiveness of our approach, we conducted an extensive empirical evaluation employing a publicly accessible dataset. This dataset covers a wide spectrum of indoor environments, facilitating a comprehensive assessment. The performance evaluation metrics adopted encompass the Root Mean S quared Error (RMS E) and the Euclidean distance error (ED E)-widely embraced in the field of localization. Importantly, the simulated results demonstrated promising performance, yielding an RMS E of 1.96 meters and an average ED E of 2.23 meters. These results surpass the achievements of prevailing state-of-the-art techniques, which typically attain localization accuracies ranging from 2.5 meters to 2.7 meters using the same dataset. The enhanced accuracy in localization can be attributed to the synergy between Truncate d S VD's dimensionality reduction and the proficiency of KNN Regression in capturing intricate spatial relationships among data points. Our proposed approach highlights its potential to deliver heightened precision in indoor localization outcomes, with immediate relevance to real-time scenarios. Future research endeavors involving comprehensive comparative analyses with advanced techniques hold promise in propelling the field of accurate indoor localization solutions forward.

show abstract

Section: B Indoor Positioning Datasetmentioning

confidence: 71%

Section: B Indoor Positioning Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dimensionality Reduction with Truncated Singular Value Decomposition and K-Nearest Neighbors Regression for Indoor Localization

Thi,

Manh,

Anh

et al. 2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…The K-nearest neighbor (KNN) algorithm [14] is considered to be the first machine learning method applied in the field of indoor positioning, and other machine learning methods applied to indoor positioning include support vector machine (SVM) [15], clustering algorithm [16] and neural network [17]. In recent years, deep learning [18] has also been applied to indoor positioning due to its high accuracy, but deep learning requires training with large amounts of data.…”

Section: Introductionmentioning

confidence: 99%

Positioning by floors based on WiFi fingerprint

Hou,

Wang

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

WiFi-based indoor positioning technology has gradually become a hot research topic in the field of indoor positioning, but the development of this technology has been facing the challenge of susceptibility to environmental interference. Therefore, in this paper, the kernel function method (KFM) with stronger interference resistance is used for positioning, and the adaptive σ algorithm is proposed for the time-consuming and laborious problem of manual parameter tuning, which incorporates the ideas of cross-validation and iteration. In addition, too many wireless access points (APs) mean higher computational cost and longer positioning time, so it is necessary to choose reasonable APs for positioning. In this paper, we use the random forest (RF) algorithm to assess the importance of APs and filter out a small number of APs with high importance. Considering the obvious differences in the WiFi signals received on different floors, a system framework for positioning by floors based on WiFi fingerprints is proposed. In the offline phase, the fingerprint library is first divided according to floors, and then perform separately AP selection and parameter tuning for each sub-fingerprint library. In the online phase, support vector machine (SVM) is used to discriminate the floors first, and then KFM is used for planar positioning. Experiments are conducted on the public dataset, and the results show that the proposed algorithm has higher positioning accuracy, more robustness, and less time-consuming compared to several common algorithms.

show abstract

“…In spite of the fact that deep learning and ELM are growing in popularity in the field of indoor positioning, k-nearest neighbors (k-NN) is still used as the core element of many IPS solutions to estimate the user location [10], [18], [19]. However, it is paramount to highlight that these models and algorithms can be, and have been, combined in more complex applications, e.g., Alitaleshi et al [20] used autoencoder extreme learning machine (AE-ELM) with CNN to extract relevant information from the datasets and estimate the device position accurately.…”

mentioning

confidence: 99%

Autoencoder Extreme Learning Machine for Fingerprint-Based Positioning: A Good Weight Initialization is Decisive

Quezada-Gaibor

Klus

et al. 2023

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

Indoor positioning based on machine-learning (ML) models has attracted widespread interest in the last few years, given its high performance and usability. Supervised, semisupervised, and unsupervised models have thus been widely used in this field, not only to estimate the user position, but also to compress, clean, and denoise fingerprinting datasets. Some scholars have focused on developing, improving, and optimizing ML models to provide accurate solutions to the end user. This article introduces a novel method to initialize the input weights in autoencoder extreme learning machine (AE-ELM), namely factorized input data (FID), which is based on the normalized form of the orthogonal component of the input data. AE-ELM with FID weight initialization is used to efficiently reduce the radio map. Once the dimensionality of the dataset is reduced, we use k-nearest neighbors to perform the position estimation. This research work includes a comparative analysis with several traditional ways to initialize the input weights in AE-ELM, showing that FID provide a significantly better reconstruction error. Finally, we perform an assessment with 13 indoor positioning datasets collected from different buildings and in different countries. We show that the dimensionality of the datasets can be reduced more than 11 times on average, while the positioning error suffers only a small increment of 15% (on average) in comparison to the baseline.

show abstract

EA-CNN: A smart indoor 3D positioning scheme based on Wi-Fi fingerprinting and deep learning

Cited by 17 publications

References 37 publications

Dimensionality Reduction with Truncated Singular Value Decomposition and K-Nearest Neighbors Regression for Indoor Localization

Dimensionality Reduction with Truncated Singular Value Decomposition and K-Nearest Neighbors Regression for Indoor Localization

Positioning by floors based on WiFi fingerprint

Autoencoder Extreme Learning Machine for Fingerprint-Based Positioning: A Good Weight Initialization is Decisive

Contact Info

Product

Resources

About