Machine-Learning-Based Indoor Mobile Positioning Using Wireless Access Points with Dual SSIDs—An Experimental Study

Paudel, Krishna; Kadel, Rajan; Guruge, Deepani B.

doi:10.3390/jsan11030042

Cited by 4 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may have led to low accuracy in the location estimation being provided. Related works show some low accuracies, such as 50-60% in algorithms, due to the number of samples in the dataset and the due unavailability of RSSI filtering [18][19][20]. During the experiments, we considered the hyperparameter tuning of the SVM, kNN, and FFNN algorithms.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Improved RSSI Indoor Localization in IoT Systems with Machine Learning Algorithms

Maduranga,

Tilwari,

Abeysekera

2023

Signals

View full text Add to dashboard Cite

Recent developments in machine learning algorithms are playing a significant role in wireless communication and Internet of Things (IoT) systems. Location-based Internet of Things services (LBIoTS) are considered one of the primary applications among those IoT applications. The key information involved in LBIoTS is finding an object’s geographical location. The Global Positioning System (GPS) technique does not perform better in indoor environments due to multipath. Numerous methods have been investigated for indoor localization scenarios. However, the precise location estimation of a moving object in such an application is challenging due to the high signal fluctuations. Therefore, this paper presents machine learning algorithms to estimate the object’s location based on the Received Signal Strength Indicator (RSSI) values collected through Bluetooth low-energy (BLE)-based nodes. In this experiment, we utilize a publicly available RSSI dataset. The RSSI data are collected from different BLE ibeacon nodes installed in a complex indoor environment with labels. Then, the RSSI data are linearized using the weighted least-squares method and filtered using moving average filters. Moreover, machine learning algorithms are used for training and testing the dataset to estimate the precise location of the objects. All the proposed algorithms were tested and evaluated under their different hyperparameters. The tested models provided approximately 85% accuracy for KNN, 84% for SVM and 76% accuracy in FFNN.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Specific algorithms require a bare minimum number of anchor nodes. For instance, trilateration requires at least three anchor nodes in the system [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Improved RSSI Indoor Localization in IoT Systems with Machine Learning Algorithms

Maduranga,

Tilwari,

Abeysekera

2023

Signals

View full text Add to dashboard Cite

show abstract

“…More comprehensive research can be found in [ 14 ], where a neural network was used to estimate the position in a fingerprinting-based system that used measurements from two Wi-Fi bands. Different scenarios were tested in [ 14 ], with different neural network structures and network training datasets, with the conclusion that the quality of position estimation using data from two Wi-Fi bands outperforms the single band case. In [ 15 ], the position of the mobile terminal was estimated using the downlink signals of both Wi-Fi and LTE.…”

Section: Related Workmentioning

confidence: 99%

A Selection of Starting Points for Iterative Position Estimation Algorithms Using Feedforward Neural Networks

Sadowski,

Stefanski

2024

Sensors

View full text Add to dashboard Cite

This article proposes the use of a feedforward neural network (FNN) to select the starting point for the first iteration in well-known iterative location estimation algorithms, with the research objective of finding the minimum size of a neural network that allows iterative position estimation algorithms to converge in an example positioning network. The selected algorithms for iterative position estimation, the structure of the neural network and how the FNN is used in 2D and 3D position estimation process are presented. The most important results of the work are the parameters of various FNN network structures that resulted in a 100% probability of convergence of iterative position estimation algorithms in the exemplary TDoA positioning network, as well as the average and maximum number of iterations, which can give a general idea about the effectiveness of using neural networks to support the position estimation process. In all simulated scenarios, simple networks with a single hidden layer containing a dozen non-linear neurons turned out to be sufficient to solve the convergence problem.

show abstract

“…The research paper in [35] investigates the impact of using dual-frequency SSIDs from Wi-Fi Access Points on indoor localization accuracy using machine learning regression algorithms. The findings indicate that dual-frequency SSIDs significantly improve location prediction accuracy, and the Support Vector Regression (SVR) algorithm outperforms other classical machine learning methods.…”

Section: Related Workmentioning

confidence: 99%

Indoor Localization of Industrial IoT Devices and Applications Based on Recurrent Neural Networks

Marasović,

Majić,

Škalic

et al. 2024

JCOMSS

View full text Add to dashboard Cite

Industrial Internet of Things (IIoT) has become an indispensable element of smart industrial facilities, predicted to continue to grow at a rapid rate. Wireless technologies have become a standard part of today's industrial facilities with applications including programming and control of electric drives, remote system and environment monitoring and fault diagnostics of industrial equipment. However, installation of physical connections can be time consuming and require substantial economic resources, especially when considering long-term maintenance costs. With that regard, IoT applications that use sensor technology, RFID technology, network communication, data mining and machine learning could prove to be quite efficient in solving the previously presented problem of localization. A new indoor localization algorithm has been introduced based on recurring neural networks (RNNs) for the positioning of indoor devices. Experiments were conducted in relatively complex surroundings of a faculty building. According to experimental results, the presented system surpasses the state-of-the-art algorithms and can achieve 98.6% localization accuracy of indoor devices.

show abstract

Machine-Learning-Based Indoor Mobile Positioning Using Wireless Access Points with Dual SSIDs—An Experimental Study

Cited by 4 publications

References 32 publications

Improved RSSI Indoor Localization in IoT Systems with Machine Learning Algorithms

Improved RSSI Indoor Localization in IoT Systems with Machine Learning Algorithms

A Selection of Starting Points for Iterative Position Estimation Algorithms Using Feedforward Neural Networks

Indoor Localization of Industrial IoT Devices and Applications Based on Recurrent Neural Networks

Contact Info

Product

Resources

About