Received Signal Strength Indicator Measurements Research Articles

Improved-RSSI-based indoor localization by using pseudo-linear solution with machine learning algorithms

With the rapid advancement of the Internet of Things and the popularization of mobile Internet-based applications, the location-based service (LBS) has attracted much attention from commercial developers and researchers. Received signal strength indicator (RSSI)-based indoor localization technology has irreplaceable advantages for many LBS applications. However, due to multipath fading, noise, and the limited dynamic range of the RSSI measurements, precise localization based on a path-loss model and multiliterate becomes highly challenging. Therefore, this study proposes a machine learning (ML)-based improved RSSI-based indoor localization approach in which RSSI data is first augmented and then classified using ML algorithms. In addition, we implement an experimental testbed to collect the RSSI value based on Wi-Fi using various reference and target nodes. The received RSSI measurements undergo pre-processing using pseudo-linear solution techniques for closed-form solutions, approximating the original system of nonlinear RSSI measurement equations with a system of linear equations. Finally, the RSSI measurement are trained using ML models such as linear regression, polynomial regression, support vector regression, random forest regression, and decision tree regression. Consequently, the experimental results express in terms of root mean square error and coefficient of determinant compared with various machine learning models with hyper-parameter tuning.

An improved indoor positioning based on crowd-sensing data fusion and particle filter

Due to the lack of global positioning system (GPS) signals in some enclosed areas, indoor localisation has recently gained significant importance for academics. However, indoor localisation has a number of challenges and defects, including accuracy, cost, coverage, and ease of use. This paper explores the integration between the inertial measurement unit (IMU) and Wi-Fi-based received signal strength indicator (RSSI) measurements, demonstrating their combined potential for robust indoor localisation. IMUs excel at capturing precise short-term motion dynamics, offering insights into an object’s acceleration and orientation. Conversely, RSSI measurements serve as valuable indicators for relative positioning within indoor environments. By fusing data from these sources, our approach compensates for the inherent weaknesses of each sensor type. To achieve accurate indoor positioning, we employ techniques such as sensor fusion, Wi-Fi fingerprinting, and dead reckoning. Wi-Fi fingerprinting allows us to create a database that maps RSSI measurements to specific locations, while dead reckoning helps mitigate drift and inaccuracies. By combining these methods, we estimate a device’s position with increased precision. Through experimental evaluation, we assess the performance and efficiency of our integrated approach, comparing the estimated path or new location with a predefined reference path. The findings emphasise a significant improvement in accuracy, with the integration of crowd-sensing, particle filtering, and magnetic fingerprinting techniques resulting in a notable increase from 80.49% to 96.32% accuracy.

Damage localization using acoustic emission sensors via convolutional neural network and continuous wavelet transform

Due to aging structures, deterioration is becoming an essential issue in the engineering and facility management industry. Especially for nuclear power plants, the deterioration of structures could be directly related to safety issues. One of the popular methods for localizing damage such as cracks in nuclear power plants in the early stage is using acoustic emission sensors. The conventional methods for localizing damage using the acoustic emission sensor include methods such as time of arrival, time difference of arrival, and received signal strength indicator measurements. However, the conventional methods have large errors especially when the material is not homogeneous, or the propagation path of signals is non-straight. In this study, we propose a new deep learning-based damage localization method using acoustic emission sensors to automate the damage localization process and improve accuracy. First, the signals from acoustic emission sensors were collected and transformed into time–frequency domain images using continuous wavelet transform. Next, the convolutional neural networks were designed to localize the damage using the continuous wavelet transform images as the input. Finally, the trained convolutional neural networks were used to estimate the location or coordinates of damages. To validate the performance of the proposed method, experimental tests were conducted in the concrete panel and cube with artificially generated damages. The results express that the proposed method is effective and progressive.

Probabilistic indoor tracking of Bluetooth Low-Energy beacons

We construct a practical and real-time probabilistic framework for fine target tracking. In our scenario, a Bluetooth Low-Energy (BLE) device navigating in the environment publishes BLE packets that are captured by stationary BLE sensors. The aim is to accurately estimate the live position of the BLE device emitting these packets. The framework is built upon a hidden Markov model (HMM), the components of which are determined with a combination of heuristic and data-driven approaches. In the data-driven part, we rely on the fingerprints formed priorly by extracting received signal strength indicators (RSSI) from the packets. These data are then transformed into probabilistic radio-frequency maps that are used for measuring the likelihood between an RSSI data and a position. The heuristic part involves the movement of the tracked object. Having no access to any inertial information of the object, this movement is modeled with Gaussian densities with variable model parameters that are to be determined heuristically. The practicality of the framework comes from the associated small parameter set used to discretize the components of the HMM. By tuning these parameters, such as the grid size of the area, the mask size and the covariance of the Gaussian; a probabilistic filtering becomes tractable for discrete state spaces. The filtering is then performed by the forward algorithm given the instantaneous sequential RSSI measurements. The performance of the system is evaluated by taking the mean squared errors of the most probable positions at each time step to their corresponding ground-truth positions. We report the statistics of the error distributions and see that we achieve promising results. The approach is also finally evaluated by its runtime and memory usage.

Path loss model based on exponential water cycle algorithm for wireless sensor network

SummaryWireless sensor networks (WSNs) are frequently employed in the agriculture field to improve the quality and crop yield. The WSN might reduce the quality of the communication link because of the absorption, dispersion, and attenuation through the leaves of plants. Therefore, estimating the path loss due to signal attenuation before WSN deployment is crucial for the smooth operation of the network. In this research paper, three innovative path loss models are defined based on the MATLAB curve fitting tool: polynomial water cycle (PWC), exponential water cycle (EWC), and Gaussian water cycle (GWC) algorithm. Here, the path loss between the router node and the coordinator node is modeled on the basis of the received signal strength indicator (RSSI) and time of arrival (TOA) measurements in a sugarcane field. The correlation coefficient between the RSSI measurement and the distance must be increased to create a precise path loss model. This paper integrates the exponential, polynomial, and Gaussian functions with the water cycle algorithm (WCA) to evaluate the optimal coefficients that would lead to precise path loss models. The performance of the proposed models that determines the optimum linear fit between RSSI and distance is validated using the correction coefficient . The results show that the proposed path loss model is superior to existing path loss models. The correlation coefficient of the proposed EWC model is 0.9993, whereas the existing PE‐PSO, LNSM, and PSO‐Exponential models yield 0.98, 0.87, and 0.93, respectively. Also, the proposed models attain the best mean absolute error (MAE) of 0.2187, 0.2951, and 0.3457 dBm for EWC, PWC, and GWC algorithms, respectively.

Novel integrated matching algorithm using a deep learning algorithm for Wi-Fi fingerprint-positioning technique in the indoors-IoT era.

The Internet-of-Things (IoT) has been used with greater frequency to track peoples' daily activities, particularly those conducted indoors. Wi-Fi technology has been also been used as an alternative to global navigation satellite system (GNSS) technologies to track indoor activities. The received signal strength indicator (RSSI) is widely used to assist in the positioning of Wi-Fi signals. However, the RSSI-based technique suffers from multipath, non-line-of-sight (NLOS) problems and the fluctuation of RSSI measurements via Wi-Fi chipsets. One of the most well-known RSSI-based approaches is to apply the fingerprinting method to do the positioning. However, the fingerprinting-based form has an additional problem due to the lack of RSSI data samples, specifically in harsh area with a huge number of classes or reference points (RPs) and an unstable matching process algorithm. To mitigate the problems of the RSSI-based fingerprinting approach, this research proposes a novel matching process algorithm called Norm_MSATE_LSTM. We first performed the augmentation process to increase the RSSI data records via the Mean Stander deviation Augmentation TEchnique (MSATE). The RSSI records were normalized (norm), and the long short-term memory (LSTM) technique was applied to estimate the correct positions. Finally, the proposed matching algorithm was compared with the stand-alone matching algorithms, including the weighted k-nearest neighbors (WkNN) and LSTM. The results obtained from the experiments and the simulated experiments using OMNeT++ show that the proposed matching algorithm may improve positioning accuracy by 33.1% and 57.5% when only augmentation and augmentation with normalization are applied, respectively.

Exploring Spatial Patterns in Sensor Data for Humidity, Temperature, and RSSI Measurements

The Internet of Things (IoT) is one of the fastest-growing research areas in recent years and is strongly linked to the development of smart cities, smart homes, and factories. IoT can be defined as connecting devices, sensors, and physical objects that can collect and transmit data across a network, enabling increased automation and better decision-making. In several IoT applications, humidity and temperature are some of the most used variables for adjusting system configurations and understanding their performance because they are related to various physical processes, human comfort, manufacturing processes, and 3D printing, among other things. In addition, one of the biggest problems associated with IoT is the excessive production of data, so it is necessary to develop methodologies to optimize the process of collecting information. This work presents a new dataset comprising almost 55 million values of temperature, relative humidity, and RSSI (Received Signal Strength Indicator) collected in two indoor spaces for longer than 3915 h at 10 s intervals. For each experiment, we captured the information from 13 previously calibrated sensors suspended from the ceiling at the same height and with a known relative position. The proposed dataset aims to contribute a benchmark for evaluating indoor temperature and humidity-controlled systems. The collected data allow the validation and improvement of the acquisition process for IoT applications.

RSSI–CSI Measurement and Variation Mitigation With Commodity Wi-Fi Device

Owing to the plentiful information released by the commodity devices, WiFi signals have been widely studied for various wireless sensing applications. In many works, both received signal strength indicator (RSSI) and the channel state information (CSI) are utilized as the key factors for precise sensing. However, the calculation and relationship between RSSI and CSI is not explained in detail. Furthermore, there are few works focusing on the measurement variation of the WiFi signal which impacts the sensing results. In this paper, the relationship between RSSI and CSI is studied in detail and the measurement variation of amplitude and phase information is investigated by extensive experiments. In the experiments, transmitter and receiver are directly connected by power divider and RF cables and the signal transmission is quantitatively controlled by RF attenuators. By changing the intensity of attenuation, the measurement of RSSI and CSI is carried out under different conditions. From the results, it is found that in order to get a reliable measurement of the signal amplitude and phase by commodity WiFi, the attenuation of the channels should not exceed 60 dB. Meanwhile, the difference between two channels should be lower than 10 dB. An active control mechanism is suggested to ensure the measurement stability. The findings and criteria of this work is promising to facilitate more precise sensing technologies with WiFi signal.

Energy-Constrained Target Localization Scheme for Wireless Sensor Networks Using Radial Basis Function Neural Network

The indoor object tracking by utilizing received signal strength indicator (RSSI) measurements with the help of wireless sensor network (WSN) is an interesting and important topic in the domain of location-based applications. Without the knowledge of location, the measurements obtained with WSN are of no use. The trilateration is a widely used technique to get location updates of target based on RSSI measurements from WSN. However, it suffers with high location estimation errors arising due to random variations in RSSI measurements. This paper presents a range-free radial basis function neural network (RBFN) and Kalman filtering- (KF-) based algorithm named RBFN+KF. The performance of the RBFN+KF algorithm is evaluated using simulated RSSIs and is compared against trilateration, multilayer perceptron (MLP), and RBFN-based estimations. The simulation results reveal that the proposed RBFN+KF algorithm shows very low location estimation errors compared to the rest of the three approaches. Additionally, it is also seen that RBFN-based approach is more energy efficient than trilateration and MLP-based localization approaches.

Visible Light Positioning With Lens Compensation for Non-Lambertian Emission

With greater demands for cost-effective, reliable, and highly accurate positioning, indoor wireless localisation using Visible Light Positioning (VLP) is a promising solution for future networks. One can expect VLP solutions to appear in all environments, from homes to industry; however, the existing literature primarily considers Visible Light Communication (VLC) sources with purely Lambertian emission patterns. To facilitate greater versatility within VLP solutions, this paper considers non-Lambertian sources. It evaluates practical Received Signal Strength Indicator (RSSI) data obtained during the Internet of Radio Light (IoRL) 5G Measurement Campaign conducted in a home environment using non-Lambertian Total Internal Reflection (TIR) lenses, which produce a halo lighting effect. The initial analysis explores the calibration of Lambertian source parameters against datasheet values leading to reductions in the average Positioning Error (PE) of 17% and 3% for averaged and individual RSSI measurement sets, respectively. While this highlights improvements from correct calibration, the Lambertian model proved to be unsuitable for non-Lambertian sources. In the absence of any existing non-Lambertian models, the authors proposed the Halo Lens Compensation (HLC) method to calibrate the considered non-Lambertian TIR sources correctly. The HLC further reduced PE in the calibrated results by 50% and 39%, with mean PE of 3.1 cm and 4.6 cm for averaged and individual RSSI measurement sets, respectively. In conclusion, for VLP using non-Lambertian sources, the existing Lambertian model is unsuitable. However, the proposed HLC is highly effective and achieves positioning accuracy comparable to existing literature using Lambertian sources.

Smartphone-Based Indoor Localization via Network Learning With Fusion of FTM/RSSI Measurements

This letter proposes a deep neural network (DNN)-based indoor localization approach that leverages WiFi Fine Timing Measurement (FTM) and Received Signal Strength Indicator (RSSI) as environment features to provide accurate location estimation. Our method uses DNN with raw FTM and RSSI measurements for self-learning and produces enhanced ranging information in the presence of measurement noise. Experimental data was obtained from real-world settings using commercial off-the-shelf devices in two different indoor office environments. The proposed solution was evaluated regarding the localization Mean Squared Error, demonstrating remarkable accuracy and outperforming state-of-the-art methods.

Indoor 2D Positioning Method for Mobile Robots Based on the Fusion of RSSI and Magnetometer Fingerprints.

Received signal strength indicator (RSSI)-based fingerprinting is a widely used technique for indoor localization, but these methods suffer from high error rates due to various reflections, interferences, and noises. The use of disturbances in the magnetic field in indoor localization methods has gained increasing attention in recent years, since this technology provides stable measurements with low random fluctuations. In this paper, a novel fingerprinting-based indoor 2D positioning method, which utilizes the fusion of RSSI and magnetometer measurements, is proposed for mobile robots. The method applies multilayer perceptron (MLP) feedforward neural networks to determine the 2D position, based on both the magnetometer data and the RSSI values measured between the mobile unit and anchor nodes. The magnetic field strength is measured on the mobile node, and it provides information about the disturbance levels in the given position. The proposed method is validated using data collected in two realistic indoor scenarios with multiple static objects. The magnetic field measurements are examined in three different combinations, i.e., the measurements of the three sensor axes are tested together, the magnetic field magnitude is used alone, and the Z-axis-based measurements are used together with the magnitude in the X-Y plane. The obtained results show that significant improvement can be achieved by fusing the two data types in scenarios where the magnetic field has high variance. The achieved results show that the improvement can be above 35% compared to results obtained by utilizing only RSSI or magnetic sensor data.

Energy Efficient Received Signal Strength-Based Target Localization and Tracking Using Support Vector Regression

The unpredictable noise in received signal strength indicator (RSSI) measurements in indoor environments practically causes very high estimation errors in target localization. Dealing with high noise in RSSI measurements and ensuring high target-localization accuracy with RSSI-based localization systems is a very popular research trend nowadays. This paper proposed two range-free target-localization schemes in wireless sensor networks (WSN) for an indoor setup: first with a plain support vector regression (SVR)-based model and second with the fusion of SVR and kalman filter (KF). The fusion-based model is named as the SVR+KF algorithm. The proposed localization solutions do not require computing distances using field measurements; rather, they need only three RSSI measurements to locate the mobile target. This paper also discussed the energy consumption associated with traditional Trilateration and the proposed SVR-based target-localization approaches. The impact of four kernel functions, namely, linear, sigmoid, RBF, and polynomial were evaluated with the proposed SVR-based schemes on the target-localization accuracy. The simulation results showed that the proposed schemes with linear and polynomial kernel functions were highly superior to trilateration-based schemes.

A Light Solution for Device Diversity Problem in a Wireless Local Area Network Fingerprint Indoor Positioning System

The development of location-based services requires an increasingly accurate positioning system technology. Research on outdoor positioning systems has achieved satisfactory accuracy and has been commonly used in various location-based services. The research trend is now shifting toward the Indoor Positioning System (IPS). One technique that is widely used in Wi-Fi-based IPS is fingerprinting. The fingerprinting technique on Wi-Fi uses the Received Signal Strength Indicator (RSSI) value. The problem that occurs is that the results of RSSI measurements on smartphones of different brands will produce different RSSI values, also known as device diversity. Device diversity will cause a decrease in system accuracy. This study aims to offer a solution to the problem of device diversity in Wi-Fi IPS based on RSSI Fingerprinting, i.e., to get a minor distance error. The proposed solution is to modify the original database radio map into two new databases: the difference database and the ratio database. The Difference Database Radiomap was able to reduce the average value of distance errors by 24.3% in Meizu and 28% in OPPO. Then, using the Radiomap database ratio, the average value of distance errors could be reduced by 13% in Meizu and 24% in OPPO. From the calculation, Radiomap database ratio can provide solutions to the problem of device diversity for an Indoor Positioning System better than the difference database radiomap if we looked at reduced distance error.

Accuracy Analysis of the Indoor Location System Based on Bluetooth Low-Energy RSSI Measurements

Systems for determining the position of objects inside buildings have a wide range of applications, such as the surveillance of people’s movements in hospitals, and of goods or mobile robots in warehouse spaces or production halls. Hence, there is a need for the development of methods that could be applied for those purposes. This paper presents the results of research on an experimental system for localizing people being evacuated from a building. The proposed solution was designed as a part of the building evacuation management system. The method used for finding location belongs to the class of proximity-type methods and is based on Received Signal Strength Indicator (RSSI) information of Bluetooth Low-Energy (BLE) devices. The devices used to build the system (BLE receivers) and the evacuee’s wristband (BLE transmitters) are low-budget electronic modules. The paper presents preliminary research and the process of selecting data processing methods, as well as the results of tests of the experimental network created for the evacuation system. The results of measurements and statistical analyses of the properties of the RSSI parameter of the BLE signal transmission between the modules used in the designed system are presented. In addition, the results of RSSI measurements and the analyses of RSSI recorded under varying environmental conditions in the building are presented. The choice of the data processing method and its parameters was made with the use of the determined probabilities of the nearest locator node detection. Finally, the performance of the experimental installation of the evacuee tracking system was tested and the effectiveness of the proximity method was evaluated. The experimental tests aimed to analyze the detection range and the impact of shading. They also allowed for determining the mean error and for estimating the maximum position determination error. It should be emphasized that the proposed position estimation method has a very low computational load, allowing the implementation of an extensive real-time system on a typical personal computer. Although the proposed system should be classified as a coarse positioning system, its features such as low cost, simplicity, flexibility, the use of commonly available components and low requirements for computational load make it attractive. Such a system is directly transferable to other applications in, for example, Industry 4.0.

Bluetooth low energy indoor localization for large industrial areas and limited infrastructure

Systems using Bluetooth Low Energy (BLE) communication are widely used in various industrial applications, which benefit from the efficient low-power operation and pervasive availability of BLE transceivers in a large number of devices and sensors. It is no different in Smart Factory and Smart Farming settings, where BLE systems are already used for asset monitoring, management, tracking, and localization. The existing BLE-based localization systems aim at high accuracy and precision using radio propagation models and multilateration, or radio fingerprinting. Both methods use the received signal strength indicator (RSSI) measurements and the dependency of RSSI on the distance between the transmitter and the receiver. Because RSSI measurements are highly inaccurate and susceptible to radio propagation phenomena, high localization accuracy is only possible if the anchor devices are densely deployed, and the propagation conditions are stable. Unfortunately, these requirements do not hold in industrial systems where radio propagation is complex, the number of anchors is limited, and propagation conditions change because the environment is dynamic. Therefore, localization methods for industrial applications have to balance system complexity (e.g., anchor density, energy cost) and localization accuracy so that practical benefits can be attained. This paper presents a set of localization algorithms that require limited infrastructure, have low complexity, and can provide valuable location information at low costs. The proposed algorithms were verified in a real-life Smart Farming application where BLE is used to monitor well-being of farm animals. The animal localization was integrated with the already existing system and proved to operate reliably despite system-level constraints and varying propagation conditions — interference, signal attenuation, and unavailability of raw radio signal measurements. The proposed approaches allow localizing animals in the cowshed of 1600m2, using only 10 anchors with an average positioning error below 8m. The algorithms are based on signal strength measurement, so they can be applied to other radio technologies.

Combining Multichannel RSSI and Vision with Artificial Neural Networks to Improve BLE Trilateration

The demands for accurate positioning and navigation applications in complex indoor environments such as emergency call positioning, fire-fighting services, and rescue operations are increasing continuously. Indoor positioning approaches apply different types of sensors to increase the accuracy of the user’s position. Among these technologies, Bluetooth Low Energy (BLE) appeared as a popular alternative due to its low cost and energy efficiency. However, BLE faces challenges related to Received Signal Strength Indicator (RSSI) fluctuations caused by human body shadowing. This work presents a method to compensate RSSI values by applying Artificial Neural Network (ANN) algorithms to RSSI measurements from three BLE advertising channels and a wearable camera as an additional source of information for the presence or absence of human obstacles. The resulting improved RSSI values are then converted into ranges using path loss models, and trilateration is applied to obtain indoor localization. The proposed artificial system provides significantly better localization solutions than fingerprinting or trilateration using uncorrected RSSI values.

An accurate target tracking method in wireless sensor networks

<span>Localization is a challenging research issue in various sectors of activity, particularly in dynamic indoor environment with high perturbation. Many existing localization techniques in wireless sensor networks are not efficient because of many constraints such as the high cost, the memory and energy limitation and the environmental noise effects. Thus, the development of novel methods of localization has become a great concern for the wireless sensor networks. In this paper, we propose a tracking method that combines regression tree and Kalman smoother filtering. Previously, regression tree has been suggested for static positioning by means of received signal strength indicator measurements. In this work, we employ this strategy to solve the mapping relation between these measurements and the target position by means of an optimized propagation model. Moreover, the predicted position considered as the observed information is introduced to the Kalman smoother algorithm, to have more precise state of the moving target. The proposed algorithm has been assessed and compared to other existing methods using real measurements of the received power by the moving target in an indoor environment. The evaluation shows that our solution outperforms other methods regarding localization accuracy.</span>

Evaluating Android smartphone’s Bluetooth received signal strength indicator measurements for social distancing

<span>This paper presents a digital solution to reduce transmission of coronavirus disease 2019 (COVID-19) by maintaining social distance between the general public. The object is achieved by using Bluetooth, which is already handy for almost everyone in the general public and comes as a standard feature in smartphones. The present technique uses an indirect method to calculate the range between the two objects. 5,300 samples were collected by adjusting the receiver at a range of angles to calculate the intensity of the Bluetooth signal. The observations are presented in the form of plotted graphs between the number of samples and the average received signal strength indicator (RSSI) value at a particular angle of rotation.</span>

A Survey of Recent Indoor Localization Scenarios and Methodologies.

Recently, various novel scenarios have been studied for indoor localization. The trilateration is known as a classic theoretical model of geometric-based indoor localization, with uniform RSSI data that can be transferred directly into distance ranges. Then, a trilateration solution can be algebraically acquired from theses ranges, in order to fix user’s actual location. However, the collected RSSI or other measurement data should be further processed and classified to lower the localization error rate, instead of using the raw data influenced by multi-path effect, multiple nonlinear interference and noises. In this survey, a large number of existing techniques are presented for different indoor network structures and channel conditions, divided as LOS (light-of-sight) and NLOS (non light-of-sight). Besides, the input measurement data such as RSSI (received signal strength indication), TDOA (time difference of arrival), DOA (distance of arrival), and RTT (round trip time) are studied towards different application scenarios. The key localization techniques like RSSI-based fingerprinting technique are presented using supervised machine learning methods, namely SVM (support vector machine), KNN (K nearest neighbors) and NN (neural network) methods, especially in an offline training phase. Other unsupervised methods as isolation forest, k-means, and expectation maximization methods are utilized to further improve the localization accuracy in online testing phase. For Bayesian filtering methods, apart from the basic linear Kalman filter (LKF) methods, nonlinear stochastic filters such as extended KF, cubature KF, unscented KF and particle filters are introduced. These nonlinear methods are more suitable for dynamic localization models. In addition to the localization accuracy, the other important performance features and evaluation aspects are presented in our paper: scalability, stability, reliability, and the complexity of proposed algorithms is compared in this survey. Our paper provides a comprehensive perspective to compare the existing techniques and related practical localization models, with the aim of improving localization accuracy and reducing the complexity of the system.