Localization-based Services Research Articles

Deep-Learning-Based Scenario Recognition With GNSS Measurements on Smartphones

Smartphones are in everyone’s hands for applications including navigation- and localization-based services, and scenario recognition is critical for seamless indoor and outdoor navigation. How to use smartphone sensing data to recognize different scenarios is a meaningful but challenging problem. To address this issue, we propose a structured grid-based deep-learning scenario recognition technique that uses smartphone global navigation satellite system (GNSS) measurements (satellite position, pseudorange, Doppler shift, and C/N0). In this work, the scenarios are grouped into four categories: deep indoors, shallow indoors, semioutdoors, and open outdoors. The proposed approach utilizes Voronoi tessellations to obtain structured-grid representations from satellite positions and performs computations using convolutional neural networks (CNNs) and convolutional long short-term memory (ConvLSTM) networks. With only spatial information being considered, the CNN model is used to extract the features of Voronoi tessellations for scenario recognition, achieving a high accuracy of 98.82%. Then, to enhance the robustness of the algorithm, the ConvLSTM network is adopted, which treats the measurements as spatiotemporal sequences, improving the accuracy to 99.92%. Compared with existing methods, the proposed algorithm is simple and efficient, using only GNSS measurements without the need for additional sensors. Furthermore, the latencies of the CNN and ConvLSTM models on a CPU are only 16.82 and 27.94 ms, respectively. Therefore, the proposed algorithm has the potential for real-time applications.

Optimal transmitter location using multi-scale algorithm based on real measurement for outdoor communication

In the era of wireless network communication, the demand for determining the best transmitter (Tx) location is constantly increasing especially in outdoor environments and localization-based services. In this paper, localization optimal location of a Tx has been achieved in electrical engineering technical college by using received signal strength (RSS). We install practical devices in the college to measure the received signal strength in all the college regions. Where each device consists of two pieces which are the AirMAX sector directional antenna and signal broadcast piece (router board). We measured RSS in four directions for each received point in all selected regions using the NetSpot software. An algorithm was created in MATLAB software to determine the average received power (ARP), average signal quality (ASQ) as well as calculate the average coverage (AC) for each Tx device location based on the locations deployed in the real environment. Overall, the results obtained showed that this algorithm effectively demonstrated that it is able to determine the best location of a Tx device compared to other deployed locations in the college. Furthermore, we find large effects when a Tx location changes from one location to another on the RSS because of the surrounding environment effects.

Use of Magnetic Positioning Systems in Industrial and Biomedical Applications

Nowadays the ability to locate people and objects is becoming an important and necessary aspect for the wide range of applications concerning localization-based services. Indeed, applications based on spatial and time awareness of people and objects within certain contexts are being developed. Some application examples in which the positioning problem must be considered and solved are: industrial automation, virtual reality, smart cities, smart health, robot navigation and remote surgery. Although in outdoor environments this does not represent a big issue thanks to the presence and support of Global Navigation Satellite Systems (GNSSs), there is a whole series of scenarios, such as indoors, underground, and underwater environments, in which GNSSs fail due to the complexity of the considered environments with respect to radio propagation. Nowadays, in the considered scenarios, the identification of a reliable method able to satisfy the positioning requirements is an open issue, for which the measurement community can provide a valuable contribution regarding the proposal of measurement methods and procedures, the evaluation of the major causes of uncertainty of the devices and the consideration of these features within positioning algorithms and data processing.

Geometry-Based Cooperative Localization for Connected Vehicle Subject to Temporary Loss of GNSS Signals

Onboard GNSS signal loss is a challenging issue for automated vehicles during driving in urban areas due to the effects of tall and dense buildings, flyovers, tunnels, and vegetation. To improve the vehicle localization accuracy when GNSS signals temporarily lost, this paper proposes a Geometry-based cooperative localization method (GCL) for the Internet of Vehicles. The vehicle position is estimated using mathematical geometry information, including vehicle dynamics and road shapes, which could reduce the environment-aware position constraint of cooperative localization. The relocation approach is enabled by communicating with neighboring vehicles to attenuate GNSS signal loss on localization-based services. The efficiency and scalability of GCL are evaluated in different driving conditions. The results showed that GCL achieved better localization performance than the state-of-the-art techniques in shorter and longer GNSS signal loss situations. The experimental results demonstrated the capabilities and effectiveness of the proposed algorithm to handle typical GNSS signal loss driving scenarios.

Application of solely self-attention mechanism in CSI-fingerprinting-based indoor localization

With the growth of IoT services, there has been an increased demand for indoor localization-based services. Wi-Fi access is omnipresent; its high accuracy and ability to use commodity devices makes it suitable to be widely adopted for localization in indoor environments. Recent sequence transduction models such as recurrent neural network (RNN) and long short-term memory (LSTM) mostly rely on recurrent and convolution. Both LSTM and RNN have achieved tremendous results in the localization tasks, but their sequential character prevents them from effectively performing parallel computing, therefore, limiting their performance in processing extremely long sequences. Lately, there have been different models developed for natural language processing transduction tasks that relied solely on attention mechanism, and they performed remarkably well with less computation. This paper is the first to propose the sole utilization of self-attention mechanism for localization time-series modeling. We introduce a self-attention mechanism fingerprinting-based model (SAMFI) which uses positional encoding and masking mechanism. To capture the temporal ordering information, we used the extended symbolic aggregate approximation strategy. Moreover, the proposed model utilizes calibrated channel state information as location fingerprints. SAMFI's pivotal concept is simple and empirically potent. The obtained results significantly minimized the location error on the collected dataset with an accuracy level score of 86.5% outperforming both RNN and LSTM models which scored 82.6 and 67.5%, respectively.

3D Point Cloud-Based Indoor Mobile Robot in 6-DoF Pose Localization Using a Wi-Fi-Aided Localization System

Six-DoF (Six-degree-of-freedom) pose localization based on 3D point clouds is a challenging task for LBSs (localization-based services). This paper proposes a robust and efficient method that uses multimodal information (vision and Wi-Fi signal information) to estimate the 6-DoF pose of an RGBD camera on a robot with respect to complex 3D textured models of the indoor environment that can contain more than 650,000,000 points. Our developed method narrows the search scope, which delimits boundaries initially using the Wi-Fi location system and applies an environment-adaptive approach to determine the radius of the search sphere based on the signal stability of the Wi-Fi location system. In addition, we propose an algorithm for estimating a novel correspondence between local points with a 3D submap by combining 3D points and surface normals to acquire absolute poses from noisy and outlier-contaminated matching point sets for RGBD sensors in dynamic indoor scenes. Then, a novel two-level spatial verification strategy is used to estimate an accurate pose, which includes the use of a RANSAC (Random Sample Consensus) algorithm for identification and a direct least-square method to acquire the pose from the inliers. The proposed method has been implemented and tested extensively in various indoor scenes. The experimental results demonstrate that the Wi-Fi-aided localization system can efficiently localize a mobile robot in a variety of large-scale 3D point cloud datasets to realize stable time consumption and similar performance to state-of-the-art methods.

Smartphone Based Indoor Path Estimation and Localization Without Human Intervention

The growing commercial interest in indoor localization-based services has stimulated the development of many indoor positioning systems. Despite extensive research on localization, system requirements, such as site survey, user intervention, or specific hardware/software, place limitations on the widespread deployment of localization. To overcome these limitations, we propose a path estimation and localization system for indoor environments, termed <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> , that runs on a smartphone and a server without any human intervention. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> uses an actual floor plan and measurements from widely deployed WiFi access points (APs) and Bluetooth Low Energy (BLE) beacons to estimate the user’s path. It creates virtual rooms according to received signal strength indicator (RSSI) values and matches them to actual rooms in the real-world floor plan. After room mapping, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> uses door passing times to precisely refine a user’s estimated path. Unlike conventional path estimation and localization systems, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> works independently of device types. We implement <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> on five Android smartphones and conduct evaluation with three users in an office building. Our experimental results show that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PYLON</monospace> achieves 97 percent floor plan mapping accuracy with a localization error of 1.42 m.

Generating straight skeleton-based navigation networks with Industry Foundation Classes for indoor way-finding

Indoor navigation networks are the foundation of indoor localization-based services. To build navigation graph networks of buildings, the medial axis is an effective way to represent the paths of indoor spaces, as medial axis-based navigation networks are consistent with common human cognition of paths and satisfy the requirements of spatial queries in most indoor map-matching algorithms. The existing methods for generating medial axis-based indoor navigation networks compute the modified medial axis of indoor spaces to represent indoor paths. However, these methods cannot deal with rooms with irregular shapes or generate detours. Especially, these methods fail to generate path lines to represent floor-to-floor paths accurately. To address these issues, this study develops a novel approach called an improved generation of straight skeletons-based navigation networks (I-GSSNN) to produce straight skeletons based indoor navigation graph networks. The straight skeleton is adopted in I-GSSNN to catch the medial axis of indoor spaces. The Industry Foundation Classes (IFC) model, a widely-used format of Building Information Modeling (BIM), is used as input in the I-GSSNN. The I-GSSNN is a workflow that includes constructing path lines of corridors, connecting doors to corridors, generating floor-to-floor path lines, and removing redundant lines. Compared with existing methods, the I-GSSNN can handle rooms with any polygon shape and produces fewer detours. Novel algorithms are developed in the I-GSSNN to generate path lines for accurately representing stairs and elevators. An educational building is used as a case study to validate the result of I-GSSNN. The case study indicates that the I-GSSNN can generate a complete three-dimensional (3D) navigation network of the educational building. In addition, the accuracy test shows that the route length based on the generated navigation networks is very close to the real length. Significantly, the results show that the I-GSSNN can accurately generate full 3D navigation graph networks of buildings that can serve as indoor maps for indoor route planning and navigation and can also be used in code checking and pedestrian circulation analysis during building design.

Error Analysis on Indoor Localization with Visible Light Communication

Affected by the complexity of the indoor environment, accurate indoor positioning is challenging in many localization based services (LBS). Recently, it has been recognized that, visible light communication (VLC) is promising for indoor navigation and positioning, due to the low implementation cost with marginal modification to the existing infrastructure and the possibility to achieve high accurate positioning results. Provided that the positions of the light emitting diodes (LEDs) are known to the receiver, the angle of arrival (AOA) of the light signal is able to be estimated by a camera embedded in a smart phone, and thus the position of the smart phone can be derived based on the triangulation. In this paper, the performance of the positioning accuracy is analyzed based on indoor positioning with VLC, and the analytical upper bound of location error is derived. Extensive simulation results have verified the theoretical analysis on the VLC-based localization approach in different indoor scenarios. In order to obtain better location performance, the principles of choosing reference LED and localization LED are also given.

A Survey of Localization Systems in Internet of Things

With the rapid development in wireless technologies and the Internet, the Internet of Things (IoT) is envisioned to be an integral part of our daily lives. Localization-based services are among the...

A hybrid outdoor localization scheme with high-position accuracy and low-power consumption

As mobile devices, such as smart phones, become more and more popular, localization based on mobile devices has gained much attention in both the academia and industry. Although global positioning system (GPS) has been widely deployed in many fields, it has several disadvantages such as consuming too much power and requiring the line of sight to satellites. Cellular network-based localization is much more robust. However, this type of localization scheme cannot achieve enough accuracy for some localization-based services. With the existence of densely deployed WiFi access points, WiFi-based localization seems very promising in terms of positioning precision and power consumption. However, different than GPS and cellular network based localization, most of the existing WiFi-based localization schemes are supposed to be used in indoor environments. Note that indoor WiFi-based localization schemes cannot be simply ported to urban outdoor environments due to several factors such as weaker signal and more serious interference. In this paper, we present a hybrid outdoor localization scheme utilizing crowdsourced WiFi signal data and built-in sensors in smart phones, which can achieve high-positioning accuracy and low power consumption. Our experimental results show that the proposed hybrid localization scheme outperforms the widely-adopted GPS-based method in terms of both positioning accuracy and power consumption. In addition, the idea of crowdsourcing fingerprints is effective.

Inter-cell interference mitigation in multi-cellular visible light communications.

Inter-cell interference hinders multi-cellular optical wireless communication to support various applications. We proposed and experimentally demonstrated a multicarrier-based cell partitioning scheme, combined with frequency reuse, which could be effective in optical communications although it is inefficient in RF wireless communications. For multicarrier-based cell partitioning, Orthogonal frequency division multiplexing-based multiple access (OFDMA) was employed to accommodate multi-cellular optical wireless communications without a large guard band between adjacent cells and without additional RF components. Moreover, we employed filter bank-based multicarrier (FBMC) to mitigate inter-cell interference generated in OFDMA-based cell partitioning due to asynchronous signals originated from RF path difference. By using FBMC-based cell partitioning, inter-cell interference could be effectively mitigated as well as capacity and spectral efficiency were improved about 1.5 times compared to those of OFDMA. Because no cyclic prefix (CP) is required in FBMC, the improvement factor could be increased if there is a large RF path difference between lighting cells. Moreover, it could be a stronger solution when many neighboring cells exist causing large interference. The proposed multicarrier-based cell partitioning combined with FBMC will effectively support visible light communication (VLC)-based localization-based services (LBS) and indoor positioning system by transparently providing trilateration-based positioning method.

UbitourAR: A ubiquitous tourism model based on augmented reality

Nowadays, Brazil has an expected growth in the tourism sector due to the FIFA World Cup (which had a huge success) and the Olympics in Rio de Janeiro. However, there is a lack of tourism applications for Brazil, such as Electronic Tourism Guides (ETGs) for mobile devices. The existence of ETGs that takes into account real world environment is still very rare. By taking into account this scenario, this article presents a ubiquitous tourism model based on augmented reality. The proposed architecture, which is called UbitourAR, takes into account the context awareness focusing on localization-based services allied with user profile and restrictions. This article describes the development of UbitourAR enabling users to interact with the real world environment using augmented reality when visiting a place or point of interest (POI). In order to evaluate the model we had taken two approaches. Firstly, we evaluated the ontology proposed using scenarios. Secondly, we evaluated the usability in terms of efficiency, effectiveness and user satisfaction. For doing that, we developed a mobile application for the Caminhos de Pedra itinerary, in Bento Goncalves, Brazil. The proposed model extends the previous work of Ubitour by adding augmented reality. The results of the tests showed a user acceptance higher than 80%, which encourages the research in augmented reality allied with ubiquitous tourism. Keywords: augmented reality, Web Semantics, ubiquitous tourism, ubiquitous computing, mobile computing.

An Indoor Localization of WiFi Based on Support Vector Machines

The recent growing interest for indoor localization-based services has created a need for more accurate and real-time indoor localization solutions. Indoor localization based on existing WiFi signal strength is becoming increasingly prevalent and ubiquity. In this paper, we utilize the information of the signal strength received from the surrounding access points (APs) to determine the user localization. The propose algorithm based on support vector machines (SVM) algorithm, and comparing with three kernel functions, radial basis function (RBF) performs best of all. Experimental results indicate that the proposed algorithm leads to improvement on localization accuracy.

Mitigation of Inter-Cell Interference Utilizing Carrier Allocation in Visible Light Communication System

It is necessary in visible light communication where different information from adjacent cells is distinguishable without inter-cell interference for indoor localization-based services and positioning systems. In order to mitigate inter-cell interference, a carrier allocation-visible light communication system, adopting various carriers among the system's respective cells, is suggested. The effects of inter-cell interference for a single channel and the proposed systems are investigated by experimentation with simultaneous transmissions of QPSK signals.