Figure 4 - uploaded by Joaquín Torres-Sospedra
Content may be subject to copyright.
Source publication
Nowadays, there are a multitude of solutions for indoor positioning, as opposed to standards for outdoor positioning such as GPS. Among the different existing studies on indoor positioning, the use of Wi-Fi signals together with Machine Learning algorithms is one of the most important, as it takes advantage of the current deployment of Wi-Fi networ...
Citations
... A similar approach can be found in [21], where RSS measurements from the EnOcean radio network (922 MHz) were used to detect in which room the mobile terminal was placed. Many more examples of using machine learning in indoor positioning using the Wi-Fi radio interface can be found in very extensive review articles [22,23]. It is somehow interesting that majority of the solutions mentioned in both these publications rely on RSS and channel state information (CSI) estimation, with no angle-or time-based solutions. ...
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.
... where , ( ) is the i-th estimate of the RSSI mean obtained according to (15) for the signal transmitted by the wristband located in the position and received by locator node, is the number of RSSI measurements acquired by locator node for each Pn wristband position. Then, the parameters a, b of the model can be identified using the non-linear method of least squares. ...
... First, it was necessary to identify the parameters a, b of the logarithmic model (12) of the relationship between the estimated RSSI mean value (15) and the transmitter-receiver distance d (RSSI = f(d)). The parameters a, b of the model were identified according to (17) and (18) using the non-linear method of least squares with the Levenberg-Marquardt algorithm. ...
... The parameters a, b of the model were identified according to (17) and (18) using the non-linear method of least squares with the Levenberg-Marquardt algorithm. Figure 9 illustrates the identification process of a , b parameters for M = 10, parameter of estimator (15). The blue dots on the graph, marked as mRSSIm,n, represent the average values of the RSSI mean estimates obtained by the m-th locator node (Locm) of the signal from the wristband located in Pn position. ...
The novel approach of the Low Energy Bluetooth RSSI (Received Signal Strength Indicator) examination for a personal location during the evacuation process is presented in this paper. The presented system is based on stationary locating localization nodes installed inside the facility and portable wristbands worn by people. A method based on the propagation model and preliminary determination of its characteristics is used to calculate the wristband-locator distance. The accuracy of the distance estimations is increased by assuming Gaussian model of RSSI measurements and using the estimator of RSSI mean value. A modified multilateration approach is used to estimate the person’s position in the 2D Cartesian coordinate system. The paper also includes the outcomes of experiments conducted on the proposed approach as it was applied to the prototype evacuation supervision system. The paper presents a comparison of the position estimation error for the proposed method based on the mean RSSI value estimator with the results obtained when raw RSSI values were used. Analysis and discussion of wristband position estimation error are also included.
... Kim et al. [19] proposed an SAE based deep neural networks (DNN) architecture. Bellavista-Parent, Torres-Sospedra, and Pérez-Navarro conducted a comprehensive research of the studies carried out with machine learning methods in Wi-Fi-based indoor positioning [20]. Ayınla et al. proposed a method based on SAE and LSTM framework in WiFi fingerprintbased indoor localization. ...
Nowadays, studies on indoor localization systems based on wireless systems are increasing widely. Indoor localization is the process of determining the location of objects or people inside a building. Global Navigation Satellite System (GPS) signals do not provide sufficient location data indoors because they are interrupted or completely lost in closed areas. For this reason, studies on indoor localization system design with machine learning and deep learning techniques based on Wi-Fi technology are increasing. In this study, we propose a method and training strategy that is entirely based on a Convolutional Neural Network (CNN) and a combined autoencoder that automatically extracts features from Wi-Fi fingerprint samples. In this model, we coupled an autoencoder and a CNN and we trained them simultaneously. Thus, we guarantee that the encoder and the CNN are trained simultaneously. The proposed system was evaluated on the UJIIndoorLoc and Tampere datasets. The experimental results show that the proposed model performs significantly better than the current state-of-the-art methods in terms of location coordinates (x, y) localization. In our study, runtime analysis is also presented to show the real-time performance of the network we proposed.
... This is achieved by analyzing the received signal strength indicator (RSSI) or channel state information (CSI) of the wireless signals received by different antennas. We can use wireless signals to work in LOS or non-LOS (NLOS) environments even in dark conditions [12] and thus preserve users' privacy [8][9][10]13,15,16,21,22,24,[26][27][28]. ...
The use of wireless signals for device-free activity recognition and precise indoor positioning has gained significant popularity recently. By taking advantage of the characteristics of the received signals, it is possible to establish a mapping between these signals and human activities. Existing approaches for detecting human walking direction have encountered challenges in adapting to changes in the surrounding environment or different people. In this paper, we propose a new approach that uses the channel state information of received wireless signals, a Hampel filter to remove the outliers, a Discrete wavelet transform to remove the noise and extract the important features, and finally, machine and deep learning algorithms to identify the walking direction for different people and in different environments. Through experimentation, we demonstrate that our approach achieved accuracy rates of 92.9%, 95.1%, and 89% in detecting human walking directions for untrained data collected from the classroom, the meeting room, and both rooms, respectively. Our results highlight the effectiveness of our approach even for people of different genders, heights, and environments, which utilizes machine and deep learning algorithms for low-cost deployment and device-free detection of human activities in indoor environments.
... Considering that fingerprint localization methods can essentially be modeled as supervised learning problems, several traditional machine learning algorithms have been successfully applied to solve the challenges in fingerprint localization [12]. To further improve the accuracy of localization, deep learning (DL)-based models have also been used to improve the performance of fingerprint localization. ...
Given that fingerprint localization methods can be effectively modeled as supervised learning problems, machine learning has been employed for indoor localization tasks based on fingerprint methods. However, it is often challenging for popular machine learning models to effectively capture the unstructured data features inherent in fingerprint data that are generated in diverse propagation environments. In this paper, we propose an indoor localization algorithm based on a high-order graph neural network (HoGNNLoc) to enhance the accuracy of indoor localization and improve localization stability in dynamic environments. The algorithm first designs an adjacency matrix based on the spatial relative locations of access points (APs) to obtain a graph structure; on this basis, a high-order graph neural network is constructed to extract and aggregate the features; finally, the designed fully connected network is used to achieve the regression prediction of the location of the target to be located. The experimental results on our self-built dataset show that the proposed algorithm achieves localization accuracy within 1.29 m at 80% of the cumulative distribution function (CDF) points. The improvements are 59.2%, 51.3%, 36.1%, and 22.7% compared to the K-nearest neighbors (KNN), deep neural network (DNN), simple graph convolutional network (SGC), and graph attention network (GAT). Moreover, even with a 30% reduction in fingerprint data, the proposed algorithm exhibits stable localization performance. On a public dataset, our proposed localization algorithm can also show better performance.
... Notably, the most prevalent technologies utilized for fingerprinting are Wi-Fi [3] and Bluetooth Low Energy (BLE) [4]. However, the scanning process for Wi-Fi in Android smartphones has encountered limitations, consequently restricting the available Received Signal Strength (RSS) measurements available to provide positioning estimations. ...
... Machine learning, such as support vector machines or random forests, are often used to handle nonlinear functions and noisy data from Wi-Fi signal fingerprinting for indoor person localization [25]. Ye et al. [26] have used CAPSNET for indoor localization using a Wi-Fi network spread over 3 rooms with an average error of 0.68 m, outperforming machine learning based on CNN, support vector machine, CNN with stacked autoencoders, and k-nearest neighbor. ...
... Machine learning in WiFi-based indoor positioning was reviewed by Bellavista-Parent, Torres-Sospedra, and Pérez-Navarro [20]. The authors conducted a literature review and categorized existing methods based on machine learning techniques such as deep reinforcement learning (DRL), extreme learning machine (ELM), convolutional neural networks (CNNs), deep neural networks (DNNs), backpropagation neural networks (BPNNs), capsule neural networks (CapsNets), stacked denoising autoencoders (SDAs), variational autoencoder (VAEs), and deep belief networks (DQNs). ...
The widespread use of the internet and the exponential growth in small hardware diversity enable the development of Internet of things (IoT)-based localization systems. We review machine-learning-based approaches for IoT localization systems in this paper. Because of their high prediction accuracy, machine learning methods are now being used to solve localization problems. The paper's main goal is to provide a review of how learning algorithms are used to solve IoT localization problems, as well as to address current challenges. We examine the existing literature for published papers released between 2020 and 2022. These studies are classified according to several criteria, including their learning algorithm, chosen environment, specific covered IoT protocol, and measurement technique. We also discuss the potential applications of learning algorithms in IoT localization, as well as future trends.
... The aim of this paper is to fill the gap that still exists in the literature. In [33], which was published in June 2022, the authors surveyed 119 papers on machine learning (ML) algorithms applied to indoor positioning. In 114 of the 119 papers published between 2016 and 2021, the metric used for positioning was the RSS. ...
... In 114 of the 119 papers published between 2016 and 2021, the metric used for positioning was the RSS. In fact, the survey [33] does not mention any work that uses the FTM by assessing the performance of several state of the art (SoA) ML classifiers when applied to an RTT-based fingerprinting solution. The results shown in this paper are also compared with SoA RSS-based fingerprinting approaches. ...
... To the best of the authors' knowledge, this paper is the first in the literature at studying whether the IEEE 802.11mc FTM can contribute as an observable to fingerprint-based positioning [7,33], rather than providing a complete location system definition. The raw performance of six of the most popular supervised learning techniques [34] when applied to FTM observables is assessed and compared to what RSS-based fingerprinting solutions would achieve under the same conditions. ...
Received signal strength (RSS) has been one of the most used observables for location purposes due to its availability at almost every wireless device. However, the volatile nature of RSS tends to yield to non-reliable location solutions. IEEE 802.11mc enabled the use of the round trip time (RTT) for positioning, which is expected to be a more consistent observable for location purposes. This approach has been gaining support from several companies such as Google, which introduced that feature in the Android O.S. As a result, RTT estimation is now available in several recent off-the-shelf devices, opening a wide range of new approaches for computing location. However, RTT has been traditionally addressed to multilateration solutions. Few works exist that assess the feasibility of the RTT as an accurate feature in positioning methods based on classification algorithms. An attempt is made in this paper to fill this gap by investigating the performance of several classification models in terms of accuracy and positioning errors. The performance is assessed using different AP layouts, distinct AP vendors, and different frequency bands. The accuracy and precision of the RTT-based position estimation is always better than the one obtained with RSS in all the studied scenarios, and especially when few APs are available. In addition, all the considered ML algorithms perform pretty well. As a result, it is not necessary to use more complex solutions (e.g., SVM) when simpler ones (e.g., nearest neighbor classifiers) achieve similar results both in terms of accuracy and location error.
