A Survey of Recent Indoor Localization Scenarios and Methodologies

Performance evaluation on extended neural network localization algorithm on 5 g new radio technology

With the rapid growth of fifth-generation (5G) networks, there is an increasing demand for high-precision localisation, achieving which is a major challenge in real-time applications in dynamic and noisy environments. Signal noise and incomplete data, including time difference of arrival (TDoA), angle of arrival (AoA), and frequency of arrival (FoA), often limit traditional methods from achieving improved localization. This research proposes an advanced hybrid localisation method combining Extended Kalman Filter (EKF) and Extended Neural Network (ENN) with HackRF-based software-defined radios (SDRs) to improve the real-time localization in 5G environments. The method achieves a better localization accuracy by using EKF for noise reduction and ENN for localization data fusion and combining FoA, AoA, and TDoA measurements. Experiments using real-time 5G signal data show that the proposed EKF-ENN fusion outperforms the existing methods. It obtains an AoA mean of 0.08 radians (SD = 0.014 rad), a TDoA mean of 0.020 s (SD = 0.003 s), and a FoA mean of 0.49 Hz (SD = 0.09 Hz). Its Mean Squared Error (MSE) of 1.06e6 and Signal-to-Noise Ratio (SNR) of 11.7 dB show that it attains better performance than existing ones. Its increased localisation accuracy and signal processing efficiency qualifies it for real-time usage in next-generation wireless networks.

Cost-Efficient RSSI-Based Indoor Proximity Positioning, for Large/Complex Museum Exhibition Spaces

RSSI-based proximity positioning is a well-established technique for indoor localization, featuring simplicity and cost-effectiveness, requiring low-price and off-the-shelf hardware. However, it suffers from low accuracy (in NLOS traffic), noise, and multipath fading issues. In large complex spaces, such as museums, where heavy visitor traffic is expected to seriously impact the ability to maintain LOS, RSSI coupled with Bluetooth Low Energy (BLE) seems ideal in terms of market availability, cost-/energy-efficiency and scalability that affect competing technologies, provided it achieves adequate accuracy. Our work reports and discusses findings of a BLE/RSSI-based pilot, implemented at the Museum of Modern Greek Culture in Athens, involving eight buildings with 47 halls with diverse areas, shapes, and showcase layouts. Wearable visitor BLE beacons provided cell-level location determined by a prototype tool (VTT), integrating in its architecture different functionalities: raw RSSI data smoothing with Kalman filters, hybrid positioning provision, temporal methods for visitor cell prediction, spatial filtering, and prediction based on popular machine learning classifiers. Visitor movement modeling, based on critical parameters influencing signal measurements, provided scenarios mapped to popular behavioral models. One such model, "ant", corresponding to relatively slow nomadic cell roaming, was selected for basic experimentation. Pilot implementation decisions and methods adopted at all layers of the VTT architecture followed the overall concept of simplicity, availability, and cost-efficiency, providing a maximum infrastructure cost of 8 Euro per m2 covered. A total 15 methods/algorithms were evaluated against prediction accuracy across 20 RSSI datasets, incorporating diverse hall cell allocations and visitor movement patterns. RSSI data, temporal and spatial management with simple low-processing methods adopted, achieved a maximum prediction accuracy average of 81.53% across all datasets, while ML algorithms (Random Forest) achieved a maximum prediction accuracy average of 87.24%.

Multi-Band Analog Radio-over-Fiber Mobile Fronthaul System for Indoor Positioning, Beamforming, and Wireless Access

In response to the urgent demands of the Internet of Things for precise indoor target positioning and information interaction, this paper proposes a multi-band analog radio-over-fiber mobile fronthaul system. The objective is to obtain the target's location in indoor environments while integrating remote beamforming capabilities to achieve wireless access to the targets. Vector signals centered at 3, 4, 5, and 6 GHz for indoor positioning and centered at 30 GHz for wireless access are generated centrally in the distributed unit (DU) and fiber-distributed to the active antenna unit (AAU) in the multi-band analog radio-over-fiber mobile fronthaul system. Target positioning is achieved by radiating electromagnetic waves indoors through four omnidirectional antennas in conjunction with a pre-trained neural network, while high-speed wireless communication is realized through a phased array antenna (PAA) comprising four antenna elements. Remote beamforming for the PAA is implemented through the integration of an optical true time delay pool in the multi-band analog radio-over-fiber mobile fronthaul system. This integration decouples the weight control of beamforming from the AAU, enabling centralized control of beam direction at the DU and thereby reducing the complexity and cost of the AAU. Simulation results show that the average accuracy of localization classification can reach 86.92%, and six discrete beam directions are achieved via the optical true time delay pool. In the optical transmission layer, when the received optical power is 10 dBm, the error vector magnitudes (EVMs) of vector signals in all frequency bands remain below 3%. In the wireless transmission layer, two beam directions were selected for verification. Once the beam is aligned with the target device at maximum gain and the received signal is properly processed, the EVM of millimeter-wave vector signals remains below 11%.

High-Accuracy and Real-Time Fingerprint-Based Continual Learning Localization System in Dynamic Environment

In dynamic environments, localization accuracy often deteriorates due to an outdated or invalid database. Traditional approaches typically use Transfer Learning (TL) to address this issue, but TL suffers from the problem of catastrophic forgetting. This paper proposes a fingerprint-based Continual Learning (CL) localization system designed to retain old data while enhancing the accuracy for new data. The system works by rehearsing parameters in the lower network layers and reducing the training rate in the upper layers. Simulations conducted with fused data show that the proposed approach improves accuracy by 16% for new data and 29% for old data compared to TL in smaller rooms. In larger rooms, it achieves a 14% improvement for new data and a 44% improvement for old data over TL. These results demonstrate that the proposed CL approach not only enhances localization accuracy but also effectively mitigates the issue of catastrophic forgetting.

An Integration of Deep Neural Network-Based Extended Kalman Filter (DNN-EKF) Method in Ultra-Wideband (UWB) Localization for Distance Loss Optimization

This paper examines the critical role of indoor positioning for robots, with a particular focus on small and confined spaces such as homes, warehouses, and similar environments. We develop an algorithm by integrating deep neural networks (DNNs) with the extended Kalman filter (EKF) method, which is known as DNN-EKF, to obtain an accurate indoor localization for ensuring precise and reliable robot movements within the use of Ultra-Wideband (UWB) technology. The study introduces a novel methodology that combines advanced technology, including DNN, filtering techniques, specifically the EKF and UWB technology, with the objective of enhancing the accuracy of indoor localization systems. The objective of integrating these technologies is to develop a more robust and dependable solution for robot navigation in challenging indoor environments. The proposed approach combines a DNN with the EKF to significantly improve indoor localization accuracy for mobile robots. The results clearly show that the proposed model outperforms existing methods, including NN-EKF, LPF-EKF, and other traditional approaches. In particular, the DNN-EKF method achieves optimal performance with the least distance loss compared to NN-EKF and LPF-EKF. These results highlight the superior effectiveness of the DNN-EKF method in providing precise localization in indoor environments, especially when utilizing UWB technology. This makes the model highly suitable for real-time robotic applications, particularly in dynamic and noisy environments.

Interval Split Covariance Intersection Filter: Theory and Its Application to Cooperative Localization in a Multi-Sensor Multi-Vehicle System

The data incest problem causes inter-estimate correlation during data fusion processes, which yields inconsistent data fusion results. Especially in the multi-sensor multi-vehicle (MSMV) system, the data incest problem is serious due to multiple relative position estimations, which not only lead to pessimistic estimation but also cause additional computational overhead. In order to address the data incest problem, we propose a new data fusion method termed the interval split covariance intersection filter (ISCIF). The general consistency of the ISCIF is proven, serving as supplementary proof for the split covariance intersection filter (SCIF). Moreover, a decentralized MSMV localization system including absolute and relative positioning stages is designed. In the absolute positioning stage, each vehicle uses the ISCIF algorithm to update its own position based on absolute measurements. In the relative position stage, the interval constraint propagation (ICP) method is implemented to preprocess multiple relative position estimates and initially prepare input data for ISCIF. Then, the proposed ISCIF algorithm is employed to realize relative positioning. In addition, comparative simulations demonstrate that the proposed method can achieve both accurate and consistent results compared with the state-of-the-art methods.

Comparative Analysis of Integrated Filtering Methods Using UWB Localization in Indoor Environment

This research delves into advancing an ultra-wideband (UWB) localization system through the integration of filtering technologies (moving average (MVG), Kalman filter (KF), extended Kalman filter (EKF)) with a low-pass filter (LPF). We investigated new approaches to enhance the precision and reduce noise of the current filtering methods-MVG, KF, and EKF. Using a TurtleBot robotic platform with a camera, our research thoroughly examines the UWB system in various trajectory situations (square, circular, and free paths with 2 m, 2.2 m, and 5 m distances). Particularly in the square path trajectory with the lowest root mean square error (RMSE) values (40.22 mm on the X axis, and 78.71 mm on the Y axis), the extended Kalman filter with low-pass filter (EKF + LPF) shows notable accuracy. This filter stands out among the others. Furthermore, we find that integrated method using LPF outperforms MVG, KF, and EKF consistently, reducing the mean absolute error (MAE) to 3.39% for square paths, 4.21% for circular paths, and 6.16% for free paths. This study highlights the effectiveness of EKF + LPF for accurate indoor localization for UWB systems.

Few-Shot Learning for WiFi Fingerprinting Indoor Positioning

In recent years, deep-learning-based WiFi fingerprinting has been intensively studied as a promising technology for providing accurate indoor location services. However, it still demands a time-consuming and labor-intensive site survey and suffers from the fluctuation of wireless signals. To address these issues, we propose a prototypical network-based positioning system, which explores the power of few-shot learning to establish a robust RSSI-position matching model with limited labels. Our system uses a temporal convolutional network as the encoder to learn an embedding of the individual sample, as well as its quality. Each prototype is a weighted combination of the embedded support samples belonging to its position. Online positioning is performed for an embedded query sample by simply finding the nearest position prototype. To mitigate the space ambiguity caused by signal fluctuation, the Kalman Filter estimates the most likely current RSSI based on the historical measurements and current measurement in the online stage. The extensive experiments demonstrate that the proposed system performs better than the existing deep-learning-based models with fewer labeled samples.

Range-Extension Algorithms and Strategies for TDOA Ultra-Wideband Positioning System

The Internet of Things (IoT) for smart industry requires the surveillance and management of people and objects. The ultra-wideband positioning system is an attractive solution for achieving centimeter-level accuracy in target location. While many studies have focused on improving the accuracy of the anchor coverage range, it is important to note that in practical applications, positioning areas are often limited and obstructed by furniture, shelves, pillars, or walls, which can restrict the placement of anchors. Furthermore, some positioning regions are located beyond anchor coverage, and a single group with few anchors may not be able to cover all rooms and aisles on a floor due to non-line-of-sight errors causing severe positioning errors. In this work, we propose a dynamic-reference anchor time difference of arrival (TDOA) compensation algorithm to enhance accuracy beyond anchor coverage by eliminating local minima of the TDOA loss function near anchors. We designed a multidimensional and multigroup TDOA positioning system with the aim of broadening the coverage of indoor positioning and accommodating complex indoor environments. By employing an address-filter technique and group-switching process, tags can seamlessly move between groups with a high positioning rate, low latency, and high accuracy. We deployed the system in a medical center to locate and manage researchers with infectious medical waste, demonstrating its usefulness for practical healthcare institutions. Our proposed positioning system can thus facilitate precise and wide-range indoor and outdoor wireless localization.

Improving BLE-Based Passive Human Sensing with Deep Learning

Passive Human Sensing (PHS) is an approach to collecting data on human presence, motion or activities that does not require the sensed human to carry devices or participate actively in the sensing process. In the literature, PHS is generally performed by exploiting the Channel State Information variations of dedicated WiFi, affected by human bodies obstructing the WiFi signal propagation path. However, the adoption of WiFi for PHS has some drawbacks, related to power consumption, large-scale deployment costs and interference with other networks in nearby areas. Bluetooth technology and, in particular, its low-energy version Bluetooth Low Energy (BLE), represents a valid candidate solution to the drawbacks of WiFi, thanks to its Adaptive Frequency Hopping (AFH) mechanism. This work proposes the application of a Deep Convolutional Neural Network (DNN) to improve the analysis and classification of the BLE signal deformations for PHS using commercial standard BLE devices. The proposed approach was applied to reliably detect the presence of human occupants in a large and articulated room with only a few transmitters and receivers and in conditions where the occupants do not directly occlude the Line of Sight between transmitters and receivers. This paper shows that the proposed approach significantly outperforms the most accurate technique found in the literature when applied to the same experimental data.

A Survey of the Performance-Limiting Factors of a 2-Dimensional RSS Fingerprinting-Based Indoor Wireless Localization System

A receive signal strength (RSS) fingerprinting-based indoor wireless localization system (I-WLS) uses a localization machine learning (ML) algorithm to estimate the location of an indoor user using RSS measurements as the position-dependent signal parameter (PDSP). There are two stages in the system's localization process: the offline phase and the online phase. The offline phase starts with the collection and generation of RSS measurement vectors from radio frequency (RF) signals received at fixed reference locations, followed by the construction of an RSS radio map. In the online phase, the instantaneous location of an indoor user is found by searching the RSS-based radio map for a reference location whose RSS measurement vector corresponds to the user's instantaneously acquired RSS measurements. The performance of the system depends on a number of factors that are present in both the online and offline stages of the localization process. This survey identifies these factors and examines how they impact the overall performance of the 2-dimensional (2-D) RSS fingerprinting-based I-WLS. The effects of these factors are discussed, as well as previous researchers' suggestions for minimizing or mitigating them and future research trends in RSS fingerprinting-based I-WLS.

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.

Low-Cost UWB Based Real-Time Locating System: Development, Lab Test, Industrial Implementation and Economic Assessment

This paper presents the technical development and subsequent testing of a Real-Time Locating System based on Ultra-Wideband signals, with the aim to appraise its potential implementation in a real industrial case. The system relies on a commercial Radio Indoor Positioning System, called Qorvo MDEK1001, which makes use of UWB RF technology to determine the position of RF-tags placed on an item of interest, which in turn is located in an area covered by specific fixed antennas (anchors). Testing sessions were carried out both in an Italian laboratory and in a real industrial environment, to determine the best configurations according to some selected performance indicators. The results support the adoption of the proposed solution in industrial environments to track assets and work in progress. Moreover, most importantly, the solution developed is cheap in nature: indeed, normally tracking solutions involve a huge investment, quite often not affordable above all by small-, medium- and micro-sized enterprises. The proposed low-cost solution instead, as demonstrated by the economic assessment completing the work, justifies the feasibility of the investment. Hence, results of this paper ultimately constitute a guidance for those practitioners who intend to adopt a similar system in their business.

Multiple Fingerprinting Localization by an Artificial Neural Network

Fingerprinting localization is a promising indoor positioning methods thanks to its advantage of using preinstalled infrastructure. For example, WiFi signal strength can be measured by pre-existing WiFi routers. In the offline phase, the fingerprinting localization method first stores of position and RSSI measurement pairs in a dataset. Second, it predicts a target's location by comparing the stored fingerprint database to the current measurement. The database size is normally huge, and data patterns are complicated; thus, an artificial neural network is used to model the relationship of fingerprints and locations. The existing fingerprinting locations, however, have been developed to predict only single locations. In practice, many users may require positioning services, and as such, the core algorithm should be capable of multiple localizations, which is the main contribution of this paper. In this paper, multiple fingerprinting localization is developed based on an artificial neural network and an analysis of the number of targets that can be estimated without loss of accuracy is conducted by experiments.

Smartphone-Based Social Distance Detection Technology with Near-Ultrasonic Signal

With the emergence of COVID-19, social distancing detection is a crucial technique for epidemic prevention and control. However, the current mainstream detection technology cannot obtain accurate social distance in real-time. To address this problem, this paper presents a first study on smartphone-based social distance detection technology based on near-ultrasonic signals. Firstly, according to auditory characteristics of the human ear and smartphone frequency response characteristics, a group of 18 kHz-23 kHz inaudible Chirp signals accompanied with single frequency signals are designed to complete ranging and ID identification in a short time. Secondly, an improved mutual ranging algorithm is proposed by combining the cubic spline interpolation and a two-stage search to obtain robust mutual ranging performance against multipath and NLoS affect. Thirdly, a hybrid channel access protocol is proposed consisting of Chirp BOK, FDMA, and CSMA/CA to increase the number of concurrencies and reduce the probability of collision. The results show that in our ranging algorithm, 95% of the mutual ranging error within 5 m is less than 10 cm and gets the best performance compared to the other traditional methods in both LoS and NLoS. The protocol can efficiently utilize the limited near-ultrasonic channel resources and achieve a high refresh rate ranging under the premise of reducing the collision probability. Our study can realize high-precision, high-refresh-rate social distance detection on smartphones and has significant application value during an epidemic.

Graph Optimization Model Fusing BLE Ranging with Wi-Fi Fingerprint for Indoor Positioning

To improve the user's positioning accuracy of a Wi-Fi fingerprint-based positioning algorithm, this study proposes a graph optimization model based on the framework of g2o that fuses a Wi-Fi fingerprint and Bluetooth Low Energy (BLE) ranging technologies. In our model, the improvement in positioning can be formulated as a nonlinear least-squares optimization problem that a graph can represent. The graph regards users as nodes and our self-designed error functions between users as edges. In the graph, the nodes obtain the initial coordinates through Wi-Fi fingerprint positioning, and all error functions aggregate to a total error function to be solved. To improve the solution effect of the total error function and weaken the influence of measurement error, an information matrix, an edge selection principle, and a Huber kernel function are introduced. The Levenberg-Marquardt (LM) algorithm is used to solve the total error function and the affine transformation estimation is used for the drifting solution. Through experiments, the influence of the threshold in the Huber kernel function is explored, the relationship between the number of nodes in the graph and the optimization effect is analyzed, and the impact of the distribution of nodes is researched. The experimental results show improvements in the positioning accuracy of four common Wi-Fi fingerprint-matching algorithms: KNN, WKNN, GK, and Stg.