Smartphone Sensor Based Indoor Positioning: Current Status, Opportunities, and Future Challenges

Indoor Scene Recognition Mechanism Based on Direction-Driven Convolutional Neural Networks

Indoor location-based services constitute an important part of our daily lives, providing position and direction information about people or objects in indoor spaces. These systems can be useful in security and monitoring applications that target specific areas such as rooms. Vision-based scene recognition is the task of accurately identifying a room category from a given image. Despite years of research in this field, scene recognition remains an open problem due to the different and complex places in the real world. Indoor environments are relatively complicated because of layout variability, object and decoration complexity, and multiscale and viewpoint changes. In this paper, we propose a room-level indoor localization system based on deep learning and built-in smartphone sensors combining visual information with smartphone magnetic heading. The user can be room-level localized while simply capturing an image with a smartphone. The presented indoor scene recognition system is based on direction-driven convolutional neural networks (CNNs) and therefore contains multiple CNNs, each tailored for a particular range of indoor orientations. We present particular weighted fusion strategies that improve system performance by properly combining the outputs from different CNN models. To meet users' needs and overcome smartphone limitations, we propose a hybrid computing strategy based on mobile computation offloading compatible with the proposed system architecture. The implementation of the scene recognition system is split between the user's smartphone and a server, which aids in meeting the computational requirements of CNNs. Several experimental analysis were conducted, including to assess performance and provide a stability analysis. The results obtained on a real dataset show the relevance of the proposed approach for localization, as well as the interest in model partitioning in hybrid mobile computation offloading. Our extensive evaluation demonstrates an increase in accuracy compared to traditional CNN scene recognition, indicating the effectiveness and robustness of our approach.

A Review of Wireless Positioning Techniques and Technologies: From Smart Sensors to 6G

In recent years, tremendous advances have been made in the design and applications of wireless networks and embedded sensors. The combination of sophisticated sensors with wireless communication has introduced new applications, which can simplify humans’ daily activities, increase independence, and improve quality of life. Although numerous positioning techniques and wireless technologies have been introduced over the last few decades, there is still a need for improvements, in terms of efficiency, accuracy, and performance for the various applications. Localization importance increased even more recently, due to the coronavirus pandemic, which made people spend more time indoors. Improvements can be achieved by integrating sensor fusion and combining various wireless technologies for taking advantage of their individual strengths. Integrated sensing is also envisaged in the coming technologies, such as 6G. The primary aim of this review article is to discuss and evaluate the different wireless positioning techniques and technologies available for both indoor and outdoor localization. This, in combination with the analysis of the various discussed methods, including active and passive positioning, SLAM, PDR, integrated sensing, and sensor fusion, will pave the way for designing the future wireless positioning systems.

An Indoor Location-Based Augmented Reality Framework

This paper proposes an indoor location-based augmented reality framework (ILARF) for the development of indoor augmented-reality (AR) systems. ILARF integrates an indoor localization unit (ILU), a secure context-aware message exchange unit (SCAMEU), and an AR visualization and interaction unit (ARVIU). The ILU runs on a mobile device such as a smartphone and utilizes visible markers (e.g., images and text), invisible markers (e.g., Wi-Fi, Bluetooth Low Energy, and NFC signals), and device sensors (e.g., accelerometers, gyroscopes, and magnetometers) to determine the device location and direction. The SCAMEU utilizes a message queuing telemetry transport (MQTT) server to exchange ambient sensor data (e.g., temperature, light, and humidity readings) and user data (e.g., user location and user speed) for context-awareness. The unit also employs a web server to manage user profiles and settings. The ARVIU uses AR creation tools to handle user interaction and display context-aware information in appropriate areas of the device's screen. One prototype AR app for use in gyms, Gym Augmented Reality (GAR), was developed based on ILARF. Users can register their profiles and configure settings when using GAR to visit a gym. Then, GAR can help users locate appropriate gym equipment based on their workout programs or favorite exercise specified in their profiles. GAR provides instructions on how to properly use the gym equipment and also makes it possible for gym users to socialize with each other, which may motivate them to go to the gym regularly. GAR is compared with other related AR systems. The comparison shows that GAR is superior to others by virtue of its use of ILARF; specifically, it provides more information, such as user location and direction, and has more desirable properties, such as secure communication and a 3D graphical user interface.

A Machine Learning Approach for Movement Monitoring in Clustered Workplaces to Control COVID-19 Based on Geofencing and Fusion of Wi-Fi and Magnetic Field Metrics

The ubiquitous existence of COVID-19 has required the management of congested areas such as workplaces. As a result, the use of a variety of inspiring tools to deal with the spread of COVID-19 has been required, including internet of things, artificial intelligence (AI), machine learning (ML), and geofencing technologies. In this work, an efficient approach based on the use of ML and geofencing technology is proposed to monitor and control the density of persons in workplaces during working hours. In particular, the workplace environment is divided into a number of geofences in which each person is associated with a set of geofences that make up their own cluster using a dynamic user-centric clustering scheme. Different metrics are used to generate a unique geofence digital signature (GDS) such as Wi-Fi basic service set identifier, Wi-Fi received signal strength indication, and magnetic field data, which can be collected using the person's smartphone. Then, these metrics are utilized by different ML techniques to generate the GDS for each indoor geofence and each building geofence as well as to detect whether the person is in their cluster. In addition, a Layered-Architecture Geofence Division method is considered to reduce the processing overhead at the person's smartphone. Our experimental results demonstrate that the proposed approach can perform well in a real workplace environment. The results show that the system accuracy is about 98.25% in indoor geofences and 76% in building geofences.

Recent Advancements in Indoor Positioning and Localization

The current era celebrates the rise of mobile devices, most of which are mobile phones [...]

Performance of Fingerprinting-Based Indoor Positioning with Measured and Simulated RSSI Reference Maps

Numerous indoor positioning technologies and systems have been proposed to localize people and objects in large buildings. Wi-Fi and Bluetooth positioning systems using fingerprinting have gained popularity, due to the wide availability of existing infrastructure. Unfortunately, the implementation of fingerprinting-based methods requires time-consuming radio surveys to prepare databases (RSSI maps) that serve as a reference for the radio signal. These surveys must be conducted for each individual building. Here, we investigate the possibility of using simulated RSSI maps with fingerprinting-based indoor localization systems. We discuss the suitability of the two popular radio wave propagation models for the preparation of RSSI reference data: ray tracing and multiwall. Based on an analysis of several representative indoor scenarios, we evaluated the performance of RSSI distribution maps obtained from simulations versus maps obtained from measurement campaigns. An experimental positioning system developed by the authors was used in the study. Based on Bluetooth Low Energy beacons and mobile devices (smartphones), the system uses fingerprinting followed by a particle filter algorithm to estimate the user’s current position from RSSI measurements and a reference spatial RSSI distribution database for each Bluetooth beacon in the building. The novelty of our contribution is that we evaluate the performance of the positioning system with RSSI maps prepared both from measurements and using the two most representative indoor propagation methods, in three different environments in terms of structure and size. We compared not only the three RSSI maps, but also how they influence the performance of the fingerprint-based positioning algorithm. Our original findings have important implications for the development of indoor localization systems and may reduce deployment times by replacing reference measurements with computer simulations. Replacing the labor-intensive and time-consuming process of building reference maps with computer modeling may significantly increase their usefulness and ease of adaptation in real indoor environments.

A Proposal of the Fingerprint Optimization Method for the Fingerprint-Based Indoor Localization System with IEEE 802.15.4 Devices

Nowadays, human indoor localization services inside buildings or on underground streets are in strong demand for various location-based services. Since conventional GPS cannot be used, indoor localization systems using wireless technologies have been extensively studied. Previously, we studied a fingerprint-based indoor localization system using IEEE802.15.4 devices, called FILS15.4, to allow use of inexpensive, tiny, and long-life transmitters. However, due to the narrow channel band and the low transmission power, the link quality indicator (LQI) used for fingerprints easily fluctuates by human movements and other uncontrollable factors. To improve the localization accuracy, FILS15.4 restricts the detection granularity to one room in the field, and adopts multiple fingerprints for one room, considering fluctuated signals, where their values must be properly adjusted. In this paper, we present a fingerprint optimization method for finding the proper fingerprint parameters in FILS15.4 by extending the existing one. As the training phase using the measurement LQI, it iteratively changes fingerprint values to maximize the newly defined score function for the room detecting accuracy. Moreover, it automatically increases the number of fingerprints for a room if the accuracy is not sufficient. For evaluations, we applied the proposed method to the measured LQI data using the FILS15.4 testbed system in the no. 2 Engineering Building at Okayama University. The validation results show that it improves the average detection accuracy (at higher than 97%) by automatically increasing the number of fingerprints and optimizing the values.

Wi-Fi Access Point Design Concept Targeting Indoor Positioning for Smartphones and IoT

Indoor positioning systems (IPS) have been regarded as essential for many applications, particularly for smartphones, during the past decade. With the internet of things (IoT), and especially device-to-device (D2D) cases, the client is supposed to have a very simple structure and low cost. It is also desirable that the client contains minimal software modules specifically for IPS purposes. This study proposes a new IPS technique that satisfies these conditions. The evaluation of the technique was previously executed based on a manual procedure. This technique utilizes Wi-Fi technology in addition to a new design of two orthogonal phased antenna arrays. This paper provides a complete design of a Wi-Fi access point (AP), considered as the proof of concept of a commercial AP. For the system to be fully automatic, the proposed architecture is based on a Raspberry Pi, external Wi-Fi modules, a powered universal serial bus (USB) hub, and two orthogonal phased antenna arrays. The phases of each antenna array are governed by extra-phase circuits as well as a radio frequency (RF) switch. Extensive design parameters have been chosen through parametric sweeps that satisfy the design conditions. Software testing results for the antenna arrays are included in this paper to show the feasibility and suitability of the proposed antenna array for IPS.

Clustering-Based Noise Elimination Scheme for Data Pre-Processing for Deep Learning Classifier in Fingerprint Indoor Positioning System

Wi-Fi-based indoor positioning systems have a simple layout and a low cost, and they have gradually become popular in both academia and industry. However, due to the poor stability of Wi-Fi signals, it is difficult to accurately decide the position based on a received signal strength indicator (RSSI) by using a traditional dataset and a deep learning classifier. To overcome this difficulty, we present a clustering-based noise elimination scheme (CNES) for RSSI-based datasets. The scheme facilitates the region-based clustering of RSSIs through density-based spatial clustering of applications with noise. In this scheme, the RSSI-based dataset is preprocessed and noise samples are removed by CNES. This experiment was carried out in a dynamic environment, and we evaluated the lab simulation results of CNES using deep learning classifiers. The results showed that applying CNES to the test database to eliminate noise will increase the success probability of fingerprint location. The lab simulation results show that after using CNES, the average positioning accuracy of margin-zero (zero-meter error), margin-one (two-meter error), and margin-two (four-meter error) in the database increased by 17.78%, 7.24%, and 4.75%, respectively. We evaluated the simulation results with a real time testing experiment, where the result showed that CNES improved the average positioning accuracy to 22.43%, 9.15%, and 5.21% for margin-zero, margin-one, and margin-two error, respectively.

A Semi-Simulated RSS Fingerprint Construction for Indoor Wi-Fi Positioning

Fingerprinting-based Wi-Fi positioning has increased in popularity due to its existing infrastructure and wide coverage. However, in the offline phase of fingerprinting positioning, the construction and maintenance of a Received Signal Strength (RSS) fingerprint database yield high labor. Moreover, the sparsity and stability of RSS fingerprinting datasets can be the most dominant error sources. This work proposes a minimally Semi-simulated RSS Fingerprinting (SS-RSS) method to generate and maintain dense fingerprints from real spatially coarse RSS acquisitions. This work simulates dense fingerprints exploring the cosine similarity of the directions to Wi-Fi access points (APs), rather than only using either a log-distance path-loss model, a quadratic polynomial fitting, or a spatial interpolation method. Real-world experiment results indicate that the semi-simulated method performs better than the coarse fingerprints and close to the real dense fingerprints. Particularly, the model of RSS measurements, the ratio of the simulated fingerprints to all fingerprints, and a two dimensions (2D) spatial distribution have been analyzed. The average positioning accuracy achieves up to 1.01 m with 66.6% of the semi-simulation ratio. The SS-RSS method offers a solution for coarse fingerprint-based positioning to perform a fine resolution without a time-consuming site-survey.